diff --git a/.model_cifar_2.pt.icloud b/.model_cifar_2.pt.icloud
new file mode 100644
index 0000000000000000000000000000000000000000..6c06f35a7ef6b1421332d2d9029d91cbd86abe43
Binary files /dev/null and b/.model_cifar_2.pt.icloud differ
diff --git a/TD2 Deep Learning.ipynb b/TD2 Deep Learning.ipynb
index 2d3b13864ca1e926e967c8c375e20ce94730d88e..42a25fe72ce23aebe25ea6b75533c2315daa368a 100644
--- a/TD2 Deep Learning.ipynb	
+++ b/TD2 Deep Learning.ipynb	
@@ -33,7 +33,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 43,
    "id": "330a42f5",
    "metadata": {},
    "outputs": [],
@@ -52,7 +52,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 44,
    "id": "b1950f0a",
    "metadata": {},
    "outputs": [
@@ -60,34 +60,34 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "tensor([[-2.3607e+00,  5.4115e-02,  4.9507e-01,  3.6159e-01, -8.5778e-01,\n",
-      "          4.5956e-01, -8.8629e-01, -6.0125e-01,  6.5430e-01, -7.1638e-02],\n",
-      "        [-3.7324e-02, -1.9366e+00,  5.1760e-01, -2.3415e-01,  1.7051e+00,\n",
-      "          3.5178e-02, -4.5054e-01,  7.8318e-03,  3.0202e-01,  7.5834e-01],\n",
-      "        [ 1.5517e+00,  2.4430e-01, -4.5208e-01,  3.6358e-01, -1.4379e+00,\n",
-      "         -3.6165e-01, -1.7371e-01,  1.0310e+00,  1.2356e+00,  8.2880e-01],\n",
-      "        [-9.3246e-01,  1.4105e+00,  6.3625e-01,  8.0029e-01, -1.5855e-01,\n",
-      "          6.1297e-01,  1.2969e+00,  3.9439e-01, -6.7246e-02, -1.0996e+00],\n",
-      "        [ 2.0068e-01,  3.0889e-01, -8.8722e-01,  2.1104e-01, -2.3675e-01,\n",
-      "         -1.1841e-03,  3.0041e-01, -2.1807e+00,  8.2948e-02,  9.4078e-01],\n",
-      "        [-2.2245e-01,  1.9374e+00,  7.1297e-01, -1.2079e-01, -7.2212e-01,\n",
-      "          6.3039e-01,  1.7831e+00,  1.1655e+00,  1.1550e+00, -1.0992e+00],\n",
-      "        [ 6.7595e-01, -1.0273e+00,  6.1578e-01, -1.3084e+00,  1.4724e+00,\n",
-      "          3.5496e-01,  6.3366e-01, -5.6040e-01, -1.2631e-01, -1.5371e+00],\n",
-      "        [ 1.1345e-01,  4.4327e-01, -5.7340e-02,  4.6848e-01,  4.9520e-01,\n",
-      "         -4.5004e-01, -1.6508e+00, -1.2056e-01,  3.6590e-01, -2.0178e+00],\n",
-      "        [-1.3768e+00, -6.5848e-01, -4.3599e-01,  1.3649e+00,  1.3631e+00,\n",
-      "          6.6154e-01, -4.8119e-01, -6.0175e-01,  8.4058e-01,  4.9436e-02],\n",
-      "        [-4.6834e-02,  2.5556e-01, -7.2044e-01, -5.1362e-01,  1.3457e+00,\n",
-      "          9.1977e-01,  6.9046e-01, -5.7536e-01,  3.7154e-01, -1.1754e+00],\n",
-      "        [-1.8877e+00, -1.6248e-01,  3.0085e-01,  4.8246e-02, -1.3587e+00,\n",
-      "          1.3279e+00, -1.9786e+00,  1.8293e-01, -9.3734e-02,  7.6291e-01],\n",
-      "        [ 1.2920e+00,  6.2483e-01, -4.9176e-01,  3.1898e-01, -9.1096e-01,\n",
-      "          3.6108e-01,  3.8194e-01,  8.2897e-01,  5.8593e-01, -1.0492e+00],\n",
-      "        [-5.6329e-01,  7.4392e-01,  5.4138e-01, -3.8151e-01, -6.4775e-02,\n",
-      "          3.7337e-01, -7.6831e-01,  4.2655e-02,  2.0429e+00,  1.0273e+00],\n",
-      "        [ 9.8523e-01,  8.4943e-01,  4.2481e-01, -1.0436e+00, -1.1542e+00,\n",
-      "          1.1222e+00,  1.2146e+00,  3.7417e-01,  1.8091e+00, -7.1749e-01]])\n",
+      "tensor([[ 2.2400e-01,  1.1198e+00, -2.2734e+00,  7.3091e-01, -8.4817e-01,\n",
+      "          9.5979e-02, -1.1137e+00,  8.0476e-01, -5.5248e-01,  5.8485e-01],\n",
+      "        [-1.3363e+00, -1.2189e+00,  6.6468e-01,  1.9214e-01,  5.9726e-01,\n",
+      "         -5.7852e-01, -1.3901e-02,  1.3929e-01, -9.7677e-01, -1.7839e+00],\n",
+      "        [-7.8952e-01,  2.5631e+00, -2.4471e+00, -2.0691e-01,  3.6557e-01,\n",
+      "          2.3152e-01, -3.8706e-01,  1.8432e+00,  3.7805e-01, -3.0303e-01],\n",
+      "        [ 1.1176e+00, -3.0045e-02,  1.0185e+00,  3.0626e-01, -9.1977e-01,\n",
+      "          8.6205e-01, -1.2110e+00, -9.4570e-02,  2.8866e-02, -1.1312e+00],\n",
+      "        [-1.4773e+00, -3.9592e-01, -1.1743e+00,  4.2192e-02, -2.4926e-01,\n",
+      "          2.0231e+00, -1.7204e+00, -1.1192e+00, -4.1509e-01, -8.8177e-01],\n",
+      "        [ 2.1733e-01,  7.9250e-01,  1.1766e+00, -9.9754e-01,  2.8116e-01,\n",
+      "         -1.1993e+00,  1.4818e+00,  2.1967e+00, -3.6964e-01,  9.4043e-01],\n",
+      "        [ 1.6402e-01, -2.4423e-01, -6.3861e-01,  2.6986e-02,  6.4567e-01,\n",
+      "          8.6479e-01,  3.8213e-02, -8.8419e-01,  5.0839e-01,  2.4499e-01],\n",
+      "        [-3.2671e-01,  1.7348e+00,  1.0104e-02,  1.3061e+00, -1.2017e+00,\n",
+      "         -5.2614e-02, -6.5584e-01, -2.9356e-02, -7.3594e-01, -3.5871e-01],\n",
+      "        [-1.1636e+00,  4.6832e-01, -1.1873e+00, -1.6389e-01,  9.9313e-02,\n",
+      "          1.0854e-01, -1.5940e+00, -8.9458e-01,  1.1512e+00, -7.8412e-01],\n",
+      "        [-5.1027e-02,  2.2311e-01,  2.0765e-01, -1.9253e+00, -2.7610e-01,\n",
+      "         -8.6998e-01, -3.0869e-01, -7.9933e-01,  6.3981e-01, -5.9056e-01],\n",
+      "        [ 5.6367e-01,  1.2427e+00,  1.5677e-01, -2.6534e-01, -2.4739e-01,\n",
+      "          7.4222e-02, -3.3286e-01, -5.3660e-01,  1.3341e+00,  8.2639e-02],\n",
+      "        [ 8.3451e-04,  1.1993e+00, -4.2901e-01, -1.0044e+00, -1.1175e+00,\n",
+      "          1.3373e+00, -1.2388e-01,  1.5406e+00, -2.7129e-02, -3.8578e-01],\n",
+      "        [ 1.1614e+00, -5.7106e-01, -5.2233e-02,  6.3513e-02,  9.8294e-01,\n",
+      "          3.1201e-01, -9.2693e-01, -2.3462e+00, -1.1374e+00, -5.5490e-01],\n",
+      "        [ 4.3770e-01, -7.7089e-01,  2.5496e-01, -1.3459e+00, -2.0906e-01,\n",
+      "          6.5663e-02,  1.1195e-02,  1.1923e+00,  8.6221e-01, -1.7183e+00]])\n",
       "AlexNet(\n",
       "  (features): Sequential(\n",
       "    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))\n",
@@ -157,7 +157,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 45,
    "id": "6e18f2fd",
    "metadata": {},
    "outputs": [
@@ -191,18 +191,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 70,
    "id": "462666a2",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -280,7 +272,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 71,
    "id": "317bf070",
    "metadata": {},
    "outputs": [
@@ -344,7 +336,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 72,
    "id": "4b53f229",
    "metadata": {},
    "outputs": [
@@ -352,8 +344,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 0 \tTraining Loss: 16.708747 \tValidation Loss: 21.955085\n",
-      "Validation loss decreased (inf --> 21.955085).  Saving model ...\n"
+      "Epoch: 0 \tTraining Loss: 44.368091 \tValidation Loss: 39.154789\n",
+      "Validation loss decreased (inf --> 39.154789).  Saving model ...\n",
+      "Epoch: 1 \tTraining Loss: 35.481135 \tValidation Loss: 31.957360\n",
+      "Validation loss decreased (39.154789 --> 31.957360).  Saving model ...\n"
      ]
     },
     {
@@ -364,7 +358,7 @@
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
       "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 15'\u001b[0m in \u001b[0;36m<cell line: 72>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=68'>69</a>\u001b[0m             valid_loss_min \u001b[39m=\u001b[39m valid_loss\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=69'>70</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m train_loss_list,n_epochs\n\u001b[0;32m---> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=71'>72</a>\u001b[0m train_loss_list,n_epochs\u001b[39m=\u001b[39mtraining(model,\u001b[39m\"\u001b[39;49m\u001b[39mmodel_cifar.pt\u001b[39;49m\u001b[39m\"\u001b[39;49m)\n",
-      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 15'\u001b[0m in \u001b[0;36mtraining\u001b[0;34m(model_, name)\u001b[0m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=35'>36</a>\u001b[0m \u001b[39m# Validate the model\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=36'>37</a>\u001b[0m model_\u001b[39m.\u001b[39meval()\n\u001b[0;32m---> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=37'>38</a>\u001b[0m \u001b[39mfor\u001b[39;00m data, target \u001b[39min\u001b[39;00m valid_loader:\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=38'>39</a>\u001b[0m     \u001b[39m# Move tensors to GPU if CUDA is available\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=39'>40</a>\u001b[0m     \u001b[39mif\u001b[39;00m train_on_gpu:\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=40'>41</a>\u001b[0m         data, target \u001b[39m=\u001b[39m data\u001b[39m.\u001b[39mcuda(), target\u001b[39m.\u001b[39mcuda()\n",
+      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 15'\u001b[0m in \u001b[0;36mtraining\u001b[0;34m(model_, name)\u001b[0m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=16'>17</a>\u001b[0m \u001b[39m# Train the model\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=17'>18</a>\u001b[0m model_\u001b[39m.\u001b[39mtrain()\n\u001b[0;32m---> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=18'>19</a>\u001b[0m \u001b[39mfor\u001b[39;00m data, target \u001b[39min\u001b[39;00m train_loader:\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=19'>20</a>\u001b[0m     \u001b[39m# Move tensors to GPU if CUDA is available\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=20'>21</a>\u001b[0m     \u001b[39mif\u001b[39;00m train_on_gpu:\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=21'>22</a>\u001b[0m         data, target \u001b[39m=\u001b[39m data\u001b[39m.\u001b[39mcuda(), target\u001b[39m.\u001b[39mcuda()\n",
       "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py:630\u001b[0m, in \u001b[0;36m_BaseDataLoaderIter.__next__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=626'>627</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_sampler_iter \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=627'>628</a>\u001b[0m     \u001b[39m# TODO(https://github.com/pytorch/pytorch/issues/76750)\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=628'>629</a>\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_reset()  \u001b[39m# type: ignore[call-arg]\u001b[39;00m\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=629'>630</a>\u001b[0m data \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_next_data()\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=630'>631</a>\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_num_yielded \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m \u001b[39m1\u001b[39m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=631'>632</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_dataset_kind \u001b[39m==\u001b[39m _DatasetKind\u001b[39m.\u001b[39mIterable \u001b[39mand\u001b[39;00m \\\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=632'>633</a>\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_IterableDataset_len_called \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m \u001b[39mand\u001b[39;00m \\\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=633'>634</a>\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_num_yielded \u001b[39m>\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_IterableDataset_len_called:\n",
       "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py:674\u001b[0m, in \u001b[0;36m_SingleProcessDataLoaderIter._next_data\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=671'>672</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_next_data\u001b[39m(\u001b[39mself\u001b[39m):\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=672'>673</a>\u001b[0m     index \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_next_index()  \u001b[39m# may raise StopIteration\u001b[39;00m\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=673'>674</a>\u001b[0m     data \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_dataset_fetcher\u001b[39m.\u001b[39;49mfetch(index)  \u001b[39m# may raise StopIteration\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=674'>675</a>\u001b[0m     \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_pin_memory:\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=675'>676</a>\u001b[0m         data \u001b[39m=\u001b[39m _utils\u001b[39m.\u001b[39mpin_memory\u001b[39m.\u001b[39mpin_memory(data, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_pin_memory_device)\n",
       "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/utils/data/_utils/fetch.py:51\u001b[0m, in \u001b[0;36m_MapDatasetFetcher.fetch\u001b[0;34m(self, possibly_batched_index)\u001b[0m\n\u001b[1;32m     <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/_utils/fetch.py?line=48'>49</a>\u001b[0m         data \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdataset\u001b[39m.\u001b[39m__getitems__(possibly_batched_index)\n\u001b[1;32m     <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/_utils/fetch.py?line=49'>50</a>\u001b[0m     \u001b[39melse\u001b[39;00m:\n\u001b[0;32m---> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/_utils/fetch.py?line=50'>51</a>\u001b[0m         data \u001b[39m=\u001b[39m [\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdataset[idx] \u001b[39mfor\u001b[39;00m idx \u001b[39min\u001b[39;00m possibly_batched_index]\n\u001b[1;32m     <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/_utils/fetch.py?line=51'>52</a>\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m     <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/_utils/fetch.py?line=52'>53</a>\u001b[0m     data \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdataset[possibly_batched_index]\n",
@@ -372,7 +366,9 @@
       "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torchvision/datasets/cifar.py:118\u001b[0m, in \u001b[0;36mCIFAR10.__getitem__\u001b[0;34m(self, index)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/datasets/cifar.py?line=114'>115</a>\u001b[0m img \u001b[39m=\u001b[39m Image\u001b[39m.\u001b[39mfromarray(img)\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/datasets/cifar.py?line=116'>117</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mtransform \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/datasets/cifar.py?line=117'>118</a>\u001b[0m     img \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mtransform(img)\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/datasets/cifar.py?line=119'>120</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mtarget_transform \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/datasets/cifar.py?line=120'>121</a>\u001b[0m     target \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mtarget_transform(target)\n",
       "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py:95\u001b[0m, in \u001b[0;36mCompose.__call__\u001b[0;34m(self, img)\u001b[0m\n\u001b[1;32m     <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py?line=92'>93</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m__call__\u001b[39m(\u001b[39mself\u001b[39m, img):\n\u001b[1;32m     <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py?line=93'>94</a>\u001b[0m     \u001b[39mfor\u001b[39;00m t \u001b[39min\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mtransforms:\n\u001b[0;32m---> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py?line=94'>95</a>\u001b[0m         img \u001b[39m=\u001b[39m t(img)\n\u001b[1;32m     <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py?line=95'>96</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m img\n",
       "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py:137\u001b[0m, in \u001b[0;36mToTensor.__call__\u001b[0;34m(self, pic)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py?line=128'>129</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m__call__\u001b[39m(\u001b[39mself\u001b[39m, pic):\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py?line=129'>130</a>\u001b[0m     \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py?line=130'>131</a>\u001b[0m \u001b[39m    Args:\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py?line=131'>132</a>\u001b[0m \u001b[39m        pic (PIL Image or numpy.ndarray): Image to be converted to tensor.\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py?line=134'>135</a>\u001b[0m \u001b[39m        Tensor: Converted image.\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py?line=135'>136</a>\u001b[0m \u001b[39m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/transforms.py?line=136'>137</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m F\u001b[39m.\u001b[39;49mto_tensor(pic)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py:172\u001b[0m, in \u001b[0;36mto_tensor\u001b[0;34m(pic)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py?line=169'>170</a>\u001b[0m img \u001b[39m=\u001b[39m img\u001b[39m.\u001b[39mview(pic\u001b[39m.\u001b[39msize[\u001b[39m1\u001b[39m], pic\u001b[39m.\u001b[39msize[\u001b[39m0\u001b[39m], F_pil\u001b[39m.\u001b[39mget_image_num_channels(pic))\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py?line=170'>171</a>\u001b[0m \u001b[39m# put it from HWC to CHW format\u001b[39;00m\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py?line=171'>172</a>\u001b[0m img \u001b[39m=\u001b[39m img\u001b[39m.\u001b[39;49mpermute((\u001b[39m2\u001b[39;49m, \u001b[39m0\u001b[39;49m, \u001b[39m1\u001b[39;49m))\u001b[39m.\u001b[39;49mcontiguous()\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py?line=172'>173</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39misinstance\u001b[39m(img, torch\u001b[39m.\u001b[39mByteTensor):\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py?line=173'>174</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m img\u001b[39m.\u001b[39mto(dtype\u001b[39m=\u001b[39mdefault_float_dtype)\u001b[39m.\u001b[39mdiv(\u001b[39m255\u001b[39m)\n",
+      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py:166\u001b[0m, in \u001b[0;36mto_tensor\u001b[0;34m(pic)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py?line=163'>164</a>\u001b[0m \u001b[39m# handle PIL Image\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py?line=164'>165</a>\u001b[0m mode_to_nptype \u001b[39m=\u001b[39m {\u001b[39m\"\u001b[39m\u001b[39mI\u001b[39m\u001b[39m\"\u001b[39m: np\u001b[39m.\u001b[39mint32, \u001b[39m\"\u001b[39m\u001b[39mI;16\u001b[39m\u001b[39m\"\u001b[39m: np\u001b[39m.\u001b[39mint16, \u001b[39m\"\u001b[39m\u001b[39mF\u001b[39m\u001b[39m\"\u001b[39m: np\u001b[39m.\u001b[39mfloat32}\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py?line=165'>166</a>\u001b[0m img \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39mfrom_numpy(np\u001b[39m.\u001b[39;49marray(pic, mode_to_nptype\u001b[39m.\u001b[39;49mget(pic\u001b[39m.\u001b[39;49mmode, np\u001b[39m.\u001b[39;49muint8), copy\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m))\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py?line=167'>168</a>\u001b[0m \u001b[39mif\u001b[39;00m pic\u001b[39m.\u001b[39mmode \u001b[39m==\u001b[39m \u001b[39m\"\u001b[39m\u001b[39m1\u001b[39m\u001b[39m\"\u001b[39m:\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/transforms/functional.py?line=168'>169</a>\u001b[0m     img \u001b[39m=\u001b[39m \u001b[39m255\u001b[39m \u001b[39m*\u001b[39m img\n",
+      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/PIL/Image.py:678\u001b[0m, in \u001b[0;36mImage.__array_interface__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=675'>676</a>\u001b[0m         new[\u001b[39m\"\u001b[39m\u001b[39mdata\u001b[39m\u001b[39m\"\u001b[39m] \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mtobytes(\u001b[39m\"\u001b[39m\u001b[39mraw\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39mL\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=676'>677</a>\u001b[0m     \u001b[39melse\u001b[39;00m:\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=677'>678</a>\u001b[0m         new[\u001b[39m\"\u001b[39m\u001b[39mdata\u001b[39m\u001b[39m\"\u001b[39m] \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mtobytes()\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=678'>679</a>\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mException\u001b[39;00m \u001b[39mas\u001b[39;00m e:\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=679'>680</a>\u001b[0m     \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39misinstance\u001b[39m(e, (\u001b[39mMemoryError\u001b[39;00m, \u001b[39mRecursionError\u001b[39;00m)):\n",
+      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/PIL/Image.py:731\u001b[0m, in \u001b[0;36mImage.tobytes\u001b[0;34m(self, encoder_name, *args)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=708'>709</a>\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=709'>710</a>\u001b[0m \u001b[39mReturn image as a bytes object.\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=710'>711</a>\u001b[0m \n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=726'>727</a>\u001b[0m \u001b[39m:returns: A :py:class:`bytes` object.\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=727'>728</a>\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=729'>730</a>\u001b[0m \u001b[39m# may pass tuple instead of argument list\u001b[39;00m\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=730'>731</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mlen\u001b[39;49m(args) \u001b[39m==\u001b[39m \u001b[39m1\u001b[39m \u001b[39mand\u001b[39;00m \u001b[39misinstance\u001b[39m(args[\u001b[39m0\u001b[39m], \u001b[39mtuple\u001b[39m):\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=731'>732</a>\u001b[0m     args \u001b[39m=\u001b[39m args[\u001b[39m0\u001b[39m]\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/PIL/Image.py?line=733'>734</a>\u001b[0m \u001b[39mif\u001b[39;00m encoder_name \u001b[39m==\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mraw\u001b[39m\u001b[39m\"\u001b[39m \u001b[39mand\u001b[39;00m args \u001b[39m==\u001b[39m ():\n",
       "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
      ]
     }
@@ -464,28 +460,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 49,
    "id": "d39df818",
    "metadata": {},
    "outputs": [
-    {
-     "ename": "ValueError",
-     "evalue": "x and y must have same first dimension, but have shapes (30,) and (18,)",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
-      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 17'\u001b[0m in \u001b[0;36m<cell line: 3>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000016?line=0'>1</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mmatplotlib\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mpyplot\u001b[39;00m \u001b[39mas\u001b[39;00m \u001b[39mplt\u001b[39;00m\n\u001b[0;32m----> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000016?line=2'>3</a>\u001b[0m plt\u001b[39m.\u001b[39;49mplot(\u001b[39mrange\u001b[39;49m(n_epochs), train_loss_list)\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000016?line=3'>4</a>\u001b[0m plt\u001b[39m.\u001b[39mxlabel(\u001b[39m\"\u001b[39m\u001b[39mEpoch\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000016?line=4'>5</a>\u001b[0m plt\u001b[39m.\u001b[39mylabel(\u001b[39m\"\u001b[39m\u001b[39mLoss\u001b[39m\u001b[39m\"\u001b[39m)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/matplotlib/pyplot.py:2812\u001b[0m, in \u001b[0;36mplot\u001b[0;34m(scalex, scaley, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/pyplot.py?line=2809'>2810</a>\u001b[0m \u001b[39m@_copy_docstring_and_deprecators\u001b[39m(Axes\u001b[39m.\u001b[39mplot)\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/pyplot.py?line=2810'>2811</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mplot\u001b[39m(\u001b[39m*\u001b[39margs, scalex\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m, scaley\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m, data\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs):\n\u001b[0;32m-> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/pyplot.py?line=2811'>2812</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m gca()\u001b[39m.\u001b[39;49mplot(\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/pyplot.py?line=2812'>2813</a>\u001b[0m         \u001b[39m*\u001b[39;49margs, scalex\u001b[39m=\u001b[39;49mscalex, scaley\u001b[39m=\u001b[39;49mscaley,\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/pyplot.py?line=2813'>2814</a>\u001b[0m         \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49m({\u001b[39m\"\u001b[39;49m\u001b[39mdata\u001b[39;49m\u001b[39m\"\u001b[39;49m: data} \u001b[39mif\u001b[39;49;00m data \u001b[39mis\u001b[39;49;00m \u001b[39mnot\u001b[39;49;00m \u001b[39mNone\u001b[39;49;00m \u001b[39melse\u001b[39;49;00m {}), \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_axes.py:1688\u001b[0m, in \u001b[0;36mAxes.plot\u001b[0;34m(self, scalex, scaley, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_axes.py?line=1444'>1445</a>\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_axes.py?line=1445'>1446</a>\u001b[0m \u001b[39mPlot y versus x as lines and/or markers.\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_axes.py?line=1446'>1447</a>\u001b[0m \n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_axes.py?line=1684'>1685</a>\u001b[0m \u001b[39m(``'green'``) or hex strings (``'#008000'``).\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_axes.py?line=1685'>1686</a>\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_axes.py?line=1686'>1687</a>\u001b[0m kwargs \u001b[39m=\u001b[39m cbook\u001b[39m.\u001b[39mnormalize_kwargs(kwargs, mlines\u001b[39m.\u001b[39mLine2D)\n\u001b[0;32m-> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_axes.py?line=1687'>1688</a>\u001b[0m lines \u001b[39m=\u001b[39m [\u001b[39m*\u001b[39m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_get_lines(\u001b[39m*\u001b[39margs, data\u001b[39m=\u001b[39mdata, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)]\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_axes.py?line=1688'>1689</a>\u001b[0m \u001b[39mfor\u001b[39;00m line \u001b[39min\u001b[39;00m lines:\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_axes.py?line=1689'>1690</a>\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39madd_line(line)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py:311\u001b[0m, in \u001b[0;36m_process_plot_var_args.__call__\u001b[0;34m(self, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py?line=308'>309</a>\u001b[0m     this \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m args[\u001b[39m0\u001b[39m],\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py?line=309'>310</a>\u001b[0m     args \u001b[39m=\u001b[39m args[\u001b[39m1\u001b[39m:]\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py?line=310'>311</a>\u001b[0m \u001b[39myield from\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_plot_args(\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py?line=311'>312</a>\u001b[0m     this, kwargs, ambiguous_fmt_datakey\u001b[39m=\u001b[39;49mambiguous_fmt_datakey)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py:504\u001b[0m, in \u001b[0;36m_process_plot_var_args._plot_args\u001b[0;34m(self, tup, kwargs, return_kwargs, ambiguous_fmt_datakey)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py?line=500'>501</a>\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39maxes\u001b[39m.\u001b[39myaxis\u001b[39m.\u001b[39mupdate_units(y)\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py?line=502'>503</a>\u001b[0m \u001b[39mif\u001b[39;00m x\u001b[39m.\u001b[39mshape[\u001b[39m0\u001b[39m] \u001b[39m!=\u001b[39m y\u001b[39m.\u001b[39mshape[\u001b[39m0\u001b[39m]:\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py?line=503'>504</a>\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mx and y must have same first dimension, but \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py?line=504'>505</a>\u001b[0m                      \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mhave shapes \u001b[39m\u001b[39m{\u001b[39;00mx\u001b[39m.\u001b[39mshape\u001b[39m}\u001b[39;00m\u001b[39m and \u001b[39m\u001b[39m{\u001b[39;00my\u001b[39m.\u001b[39mshape\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m)\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py?line=505'>506</a>\u001b[0m \u001b[39mif\u001b[39;00m x\u001b[39m.\u001b[39mndim \u001b[39m>\u001b[39m \u001b[39m2\u001b[39m \u001b[39mor\u001b[39;00m y\u001b[39m.\u001b[39mndim \u001b[39m>\u001b[39m \u001b[39m2\u001b[39m:\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py?line=506'>507</a>\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mx and y can be no greater than 2D, but have \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/matplotlib/axes/_base.py?line=507'>508</a>\u001b[0m                      \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mshapes \u001b[39m\u001b[39m{\u001b[39;00mx\u001b[39m.\u001b[39mshape\u001b[39m}\u001b[39;00m\u001b[39m and \u001b[39m\u001b[39m{\u001b[39;00my\u001b[39m.\u001b[39mshape\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m)\n",
-      "\u001b[0;31mValueError\u001b[0m: x and y must have same first dimension, but have shapes (30,) and (18,)"
-     ]
-    },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -516,34 +497,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 75,
    "id": "e93efdfc",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Test Loss: 22.074360\n",
-      "\n",
-      "Test Accuracy of airplane: 72% (722/1000)\n",
-      "Test Accuracy of automobile: 83% (838/1000)\n",
-      "Test Accuracy of  bird: 48% (487/1000)\n",
-      "Test Accuracy of   cat: 36% (360/1000)\n",
-      "Test Accuracy of  deer: 58% (584/1000)\n",
-      "Test Accuracy of   dog: 56% (567/1000)\n",
-      "Test Accuracy of  frog: 78% (784/1000)\n",
-      "Test Accuracy of horse: 64% (642/1000)\n",
-      "Test Accuracy of  ship: 76% (763/1000)\n",
-      "Test Accuracy of truck: 56% (566/1000)\n",
-      "\n",
-      "Test Accuracy (Overall): 63% (6313/10000)\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "#on définit la fonction test\n",
     "def test(model_):\n",
+    "\n",
+    "    criterion = nn.CrossEntropyLoss()  # specify loss function\n",
+    "\n",
     "    # track test loss\n",
     "    test_loss = 0.0\n",
     "    class_correct = list(0.0 for i in range(10))\n",
@@ -580,6 +543,8 @@
     "    test_loss = test_loss / len(test_loader)\n",
     "    print(\"Test Loss: {:.6f}\\n\".format(test_loss))\n",
     "\n",
+    "\n",
+    "    print(class_total)\n",
     "    for i in range(10):\n",
     "        if class_total[i] > 0:\n",
     "            print(\n",
@@ -603,12 +568,42 @@
     "        )\n",
     "    )   \n",
     "    return \n",
-    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "id": "1ef8ed96",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test Loss: 31.870164\n",
+      "\n",
+      "Test Accuracy of airplane: 53% (534/1000)\n",
+      "Test Accuracy of automobile: 65% (655/1000)\n",
+      "Test Accuracy of  bird: 11% (111/1000)\n",
+      "Test Accuracy of   cat: 14% (145/1000)\n",
+      "Test Accuracy of  deer: 38% (388/1000)\n",
+      "Test Accuracy of   dog: 38% (386/1000)\n",
+      "Test Accuracy of  frog: 57% (575/1000)\n",
+      "Test Accuracy of horse: 58% (581/1000)\n",
+      "Test Accuracy of  ship: 44% (445/1000)\n",
+      "Test Accuracy of truck: 32% (324/1000)\n",
+      "\n",
+      "Test Accuracy (Overall): 41% (4144/10000)\n"
+     ]
+    }
+   ],
+   "source": [
     "# on load le model\n",
     "model.load_state_dict(torch.load(\"./model_cifar.pt\"))\n",
     "\n",
     "#on teste le modele\n",
-    "test(model)\n"
+    "test(model)"
    ]
   },
   {
@@ -638,7 +633,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 51,
    "id": "ed876879",
    "metadata": {},
    "outputs": [
@@ -697,47 +692,60 @@
    "id": "77f1c0c2",
    "metadata": {},
    "source": [
-    "### On entraine maintenant l'algorithme"
+    "### On entraine maintenant l'algorithme."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 52,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch: 0 \tTraining Loss: 44.958917 \tValidation Loss: 42.081095\n",
-      "Validation loss decreased (inf --> 42.081095).  Saving model ...\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[E thread_pool.cpp:110] Exception in thread pool task: mutex lock failed: Invalid argument\n"
-     ]
-    },
-    {
-     "ename": "KeyboardInterrupt",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
-      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 24'\u001b[0m in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000023?line=0'>1</a>\u001b[0m \u001b[39m#train\u001b[39;00m\n\u001b[0;32m----> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000023?line=1'>2</a>\u001b[0m train_loss_list,n_epochs\u001b[39m=\u001b[39mtraining(model2,\u001b[39m\"\u001b[39;49m\u001b[39mmodel_cifar_2.pt\u001b[39;49m\u001b[39m\"\u001b[39;49m)\n",
-      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 15'\u001b[0m in \u001b[0;36mtraining\u001b[0;34m(model_, name)\u001b[0m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=23'>24</a>\u001b[0m optimizer\u001b[39m.\u001b[39mzero_grad()\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=24'>25</a>\u001b[0m \u001b[39m# Forward pass: compute predicted outputs by passing inputs to the model\u001b[39;00m\n\u001b[0;32m---> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=25'>26</a>\u001b[0m output \u001b[39m=\u001b[39m model_(data)\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=26'>27</a>\u001b[0m \u001b[39m# Calculate the batch loss\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=27'>28</a>\u001b[0m loss \u001b[39m=\u001b[39m criterion(output, target)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1515'>1516</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_compiled_call_impl(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)  \u001b[39m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1516'>1517</a>\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m-> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1517'>1518</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_call_impl(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1521'>1522</a>\u001b[0m \u001b[39m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1522'>1523</a>\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1523'>1524</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m (\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_backward_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_backward_pre_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_forward_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1524'>1525</a>\u001b[0m         \u001b[39mor\u001b[39;00m _global_backward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1525'>1526</a>\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1526'>1527</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m forward_call(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1528'>1529</a>\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1529'>1530</a>\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n",
-      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 22'\u001b[0m in \u001b[0;36mNet.forward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000021?line=14'>15</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mforward\u001b[39m(\u001b[39mself\u001b[39m, x):\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000021?line=15'>16</a>\u001b[0m     x \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpool(F\u001b[39m.\u001b[39mrelu(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mconv1(x)))\n\u001b[0;32m---> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000021?line=16'>17</a>\u001b[0m     x \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mpool(F\u001b[39m.\u001b[39;49mrelu(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mconv2(x)))\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000021?line=17'>18</a>\u001b[0m     x \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpool(F\u001b[39m.\u001b[39mrelu(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mconv3(x)))\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000021?line=19'>20</a>\u001b[0m     x \u001b[39m=\u001b[39m x\u001b[39m.\u001b[39mview(\u001b[39m-\u001b[39m\u001b[39m1\u001b[39m, \u001b[39m64\u001b[39m \u001b[39m*\u001b[39m \u001b[39m4\u001b[39m \u001b[39m*\u001b[39m \u001b[39m4\u001b[39m)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1515'>1516</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_compiled_call_impl(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)  \u001b[39m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1516'>1517</a>\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m-> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1517'>1518</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_call_impl(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1521'>1522</a>\u001b[0m \u001b[39m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1522'>1523</a>\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1523'>1524</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m (\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_backward_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_backward_pre_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_forward_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1524'>1525</a>\u001b[0m         \u001b[39mor\u001b[39;00m _global_backward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1525'>1526</a>\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1526'>1527</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m forward_call(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1528'>1529</a>\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/module.py?line=1529'>1530</a>\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/pooling.py:166\u001b[0m, in \u001b[0;36mMaxPool2d.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/pooling.py?line=164'>165</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mforward\u001b[39m(\u001b[39mself\u001b[39m, \u001b[39minput\u001b[39m: Tensor):\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/pooling.py?line=165'>166</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m F\u001b[39m.\u001b[39;49mmax_pool2d(\u001b[39minput\u001b[39;49m, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mkernel_size, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mstride,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/pooling.py?line=166'>167</a>\u001b[0m                         \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mpadding, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mdilation, ceil_mode\u001b[39m=\u001b[39;49m\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mceil_mode,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/modules/pooling.py?line=167'>168</a>\u001b[0m                         return_indices\u001b[39m=\u001b[39;49m\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mreturn_indices)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/_jit_internal.py:488\u001b[0m, in \u001b[0;36mboolean_dispatch.<locals>.fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_jit_internal.py?line=485'>486</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m if_true(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_jit_internal.py?line=486'>487</a>\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_jit_internal.py?line=487'>488</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m if_false(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/nn/functional.py:791\u001b[0m, in \u001b[0;36m_max_pool2d\u001b[0;34m(input, kernel_size, stride, padding, dilation, ceil_mode, return_indices)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/functional.py?line=788'>789</a>\u001b[0m \u001b[39mif\u001b[39;00m stride \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/functional.py?line=789'>790</a>\u001b[0m     stride \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39mjit\u001b[39m.\u001b[39mannotate(List[\u001b[39mint\u001b[39m], [])\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/nn/functional.py?line=790'>791</a>\u001b[0m \u001b[39mreturn\u001b[39;00m torch\u001b[39m.\u001b[39;49mmax_pool2d(\u001b[39minput\u001b[39;49m, kernel_size, stride, padding, dilation, ceil_mode)\n",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+      "Epoch: 0 \tTraining Loss: 44.340077 \tValidation Loss: 38.804056\n",
+      "Validation loss decreased (inf --> 38.804056).  Saving model ...\n",
+      "Epoch: 1 \tTraining Loss: 34.841362 \tValidation Loss: 32.756121\n",
+      "Validation loss decreased (38.804056 --> 32.756121).  Saving model ...\n",
+      "Epoch: 2 \tTraining Loss: 30.017414 \tValidation Loss: 29.293331\n",
+      "Validation loss decreased (32.756121 --> 29.293331).  Saving model ...\n",
+      "Epoch: 3 \tTraining Loss: 27.297434 \tValidation Loss: 26.449850\n",
+      "Validation loss decreased (29.293331 --> 26.449850).  Saving model ...\n",
+      "Epoch: 4 \tTraining Loss: 24.793885 \tValidation Loss: 24.340960\n",
+      "Validation loss decreased (26.449850 --> 24.340960).  Saving model ...\n",
+      "Epoch: 5 \tTraining Loss: 22.472584 \tValidation Loss: 22.743124\n",
+      "Validation loss decreased (24.340960 --> 22.743124).  Saving model ...\n",
+      "Epoch: 6 \tTraining Loss: 20.469634 \tValidation Loss: 20.657408\n",
+      "Validation loss decreased (22.743124 --> 20.657408).  Saving model ...\n",
+      "Epoch: 7 \tTraining Loss: 18.691486 \tValidation Loss: 19.574470\n",
+      "Validation loss decreased (20.657408 --> 19.574470).  Saving model ...\n",
+      "Epoch: 8 \tTraining Loss: 17.069575 \tValidation Loss: 18.978400\n",
+      "Validation loss decreased (19.574470 --> 18.978400).  Saving model ...\n",
+      "Epoch: 9 \tTraining Loss: 15.620560 \tValidation Loss: 18.343518\n",
+      "Validation loss decreased (18.978400 --> 18.343518).  Saving model ...\n",
+      "Epoch: 10 \tTraining Loss: 14.248934 \tValidation Loss: 17.410915\n",
+      "Validation loss decreased (18.343518 --> 17.410915).  Saving model ...\n",
+      "Epoch: 11 \tTraining Loss: 12.951946 \tValidation Loss: 17.612909\n",
+      "Epoch: 12 \tTraining Loss: 11.686462 \tValidation Loss: 16.468992\n",
+      "Validation loss decreased (17.410915 --> 16.468992).  Saving model ...\n",
+      "Epoch: 13 \tTraining Loss: 10.426255 \tValidation Loss: 17.783119\n",
+      "Epoch: 14 \tTraining Loss: 9.262303 \tValidation Loss: 17.189074\n",
+      "Epoch: 15 \tTraining Loss: 7.990563 \tValidation Loss: 19.057054\n",
+      "Epoch: 16 \tTraining Loss: 6.890593 \tValidation Loss: 17.812142\n",
+      "Epoch: 17 \tTraining Loss: 5.665097 \tValidation Loss: 20.522196\n",
+      "Epoch: 18 \tTraining Loss: 4.753225 \tValidation Loss: 20.223908\n",
+      "Epoch: 19 \tTraining Loss: 3.810058 \tValidation Loss: 22.100663\n",
+      "Epoch: 20 \tTraining Loss: 3.231981 \tValidation Loss: 24.364110\n",
+      "Epoch: 21 \tTraining Loss: 2.513453 \tValidation Loss: 25.854331\n",
+      "Epoch: 22 \tTraining Loss: 2.220183 \tValidation Loss: 27.044351\n",
+      "Epoch: 23 \tTraining Loss: 1.816957 \tValidation Loss: 27.724067\n",
+      "Epoch: 24 \tTraining Loss: 1.694099 \tValidation Loss: 32.318546\n",
+      "Epoch: 25 \tTraining Loss: 1.402909 \tValidation Loss: 30.840882\n",
+      "Epoch: 26 \tTraining Loss: 1.254589 \tValidation Loss: 33.739605\n",
+      "Epoch: 27 \tTraining Loss: 1.069033 \tValidation Loss: 34.077868\n",
+      "Epoch: 28 \tTraining Loss: 0.863811 \tValidation Loss: 34.959962\n",
+      "Epoch: 29 \tTraining Loss: 0.499509 \tValidation Loss: 36.604774\n"
      ]
     }
    ],
@@ -751,27 +759,18 @@
    "id": "087efcde",
    "metadata": {},
    "source": [
-    "### On affiche le train lost en fonction du nombre d'époches"
+    "### On affiche le train lost en fonction du nombre d'époches."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 53,
    "id": "4616e1bf",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "KeyboardInterrupt\n",
-      "\n"
-     ]
-    },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -797,12 +796,12 @@
    "id": "72cdf907",
    "metadata": {},
    "source": [
-    "### On calcule la precision du modèle sur une base de données test"
+    "### On calcule la precision du modèle sur une base de données test."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 54,
    "id": "78dd3429",
    "metadata": {},
    "outputs": [
@@ -810,20 +809,20 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Test Loss: 41.885628\n",
+      "Test Loss: 16.478442\n",
       "\n",
-      "Test Accuracy of airplane: 13% (136/1000)\n",
-      "Test Accuracy of automobile: 23% (239/1000)\n",
-      "Test Accuracy of  bird:  0% ( 0/1000)\n",
-      "Test Accuracy of   cat: 42% (420/1000)\n",
-      "Test Accuracy of  deer:  0% ( 0/1000)\n",
-      "Test Accuracy of   dog:  0% ( 0/1000)\n",
-      "Test Accuracy of  frog: 66% (664/1000)\n",
-      "Test Accuracy of horse:  0% ( 3/1000)\n",
-      "Test Accuracy of  ship: 39% (395/1000)\n",
-      "Test Accuracy of truck: 54% (548/1000)\n",
+      "Test Accuracy of airplane: 78% (789/1000)\n",
+      "Test Accuracy of automobile: 78% (783/1000)\n",
+      "Test Accuracy of  bird: 65% (658/1000)\n",
+      "Test Accuracy of   cat: 58% (582/1000)\n",
+      "Test Accuracy of  deer: 69% (698/1000)\n",
+      "Test Accuracy of   dog: 57% (578/1000)\n",
+      "Test Accuracy of  frog: 73% (736/1000)\n",
+      "Test Accuracy of horse: 74% (741/1000)\n",
+      "Test Accuracy of  ship: 82% (821/1000)\n",
+      "Test Accuracy of truck: 81% (816/1000)\n",
       "\n",
-      "Test Accuracy (Overall): 24% (2405/10000)\n"
+      "Test Accuracy (Overall): 72% (7202/10000)\n"
      ]
     }
    ],
@@ -860,7 +859,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 55,
    "id": "ef623c26",
    "metadata": {},
    "outputs": [
@@ -877,7 +876,7 @@
        "251278"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 55,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -902,7 +901,7 @@
    "id": "d1fc547c",
    "metadata": {},
    "source": [
-    "### La taille du modèle 1 initial est de 251.278 KB"
+    "### La taille initial du modèle 1 est de 251.278 KB"
    ]
   },
   {
@@ -915,7 +914,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 56,
    "id": "c4c65d4b",
    "metadata": {},
    "outputs": [
@@ -932,7 +931,7 @@
        "76522"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 56,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -954,7 +953,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 57,
    "id": "6cc06abf",
    "metadata": {},
    "outputs": [
@@ -962,20 +961,20 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Test Loss: 28.639511\n",
+      "Test Loss: 21.765956\n",
       "\n",
-      "Test Accuracy of airplane: 58% (586/1000)\n",
-      "Test Accuracy of automobile: 81% (811/1000)\n",
-      "Test Accuracy of  bird: 21% (219/1000)\n",
-      "Test Accuracy of   cat: 36% (364/1000)\n",
-      "Test Accuracy of  deer: 30% (306/1000)\n",
-      "Test Accuracy of   dog: 42% (425/1000)\n",
-      "Test Accuracy of  frog: 64% (643/1000)\n",
-      "Test Accuracy of horse: 55% (550/1000)\n",
-      "Test Accuracy of  ship: 39% (396/1000)\n",
-      "Test Accuracy of truck: 54% (542/1000)\n",
+      "Test Accuracy of airplane: 67% (677/1000)\n",
+      "Test Accuracy of automobile: 78% (789/1000)\n",
+      "Test Accuracy of  bird: 54% (546/1000)\n",
+      "Test Accuracy of   cat: 35% (350/1000)\n",
+      "Test Accuracy of  deer: 51% (515/1000)\n",
+      "Test Accuracy of   dog: 52% (529/1000)\n",
+      "Test Accuracy of  frog: 78% (783/1000)\n",
+      "Test Accuracy of horse: 62% (622/1000)\n",
+      "Test Accuracy of  ship: 75% (750/1000)\n",
+      "Test Accuracy of truck: 65% (655/1000)\n",
       "\n",
-      "Test Accuracy (Overall): 48% (4842/10000)\n"
+      "Test Accuracy (Overall): 62% (6216/10000)\n"
      ]
     }
    ],
@@ -989,13 +988,13 @@
    "id": "50c95c3e",
    "metadata": {},
    "source": [
-    "### En terme de précision, elle est la même en pourcentage pour presque toutes les classes (en comparaison avec le modèle non compressé).\n",
+    "En terme de précision, elle est la même en pourcentage pour presque toutes les classes (en comparaison avec le modèle non compressé).\n",
     "\n",
-    "#### Elle difére de 1% pour la classe horse.\n",
+    "Elle différe de 1% pour la classe horse.\n",
     "\n",
-    "### Au global, la précision est la même.\n",
+    "Au global, la précision est la même.\n",
     "\n",
-    "### Le modèle compressé conserve la précision du modèle tout en réduisant sa taille.\n",
+    "Le modèle compressé conserve la précision du modèle tout en réduisant sa taille.\n",
     "\n",
     "\n",
     "____________"
@@ -1029,25 +1028,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 91,
    "id": "7bcbbc0a",
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Net(\n",
-      "  (quant): QuantStub()\n",
-      "  (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))\n",
-      "  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
-      "  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))\n",
-      "  (fc1): Linear(in_features=400, out_features=120, bias=True)\n",
-      "  (fc2): Linear(in_features=120, out_features=84, bias=True)\n",
-      "  (fc3): Linear(in_features=84, out_features=10, bias=True)\n",
-      "  (dequant): DeQuantStub()\n",
-      ")\n"
-     ]
+     "data": {
+      "text/plain": [
+       "Net(\n",
+       "  (quant): QuantStub()\n",
+       "  (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))\n",
+       "  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
+       "  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))\n",
+       "  (fc1): DynamicQuantizedLinear(in_features=400, out_features=120, dtype=torch.qint8, qscheme=torch.per_tensor_affine)\n",
+       "  (fc2): DynamicQuantizedLinear(in_features=120, out_features=84, dtype=torch.qint8, qscheme=torch.per_tensor_affine)\n",
+       "  (fc3): DynamicQuantizedLinear(in_features=84, out_features=10, dtype=torch.qint8, qscheme=torch.per_tensor_affine)\n",
+       "  (dequant): DeQuantStub()\n",
+       ")"
+      ]
+     },
+     "execution_count": 91,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -1082,63 +1084,43 @@
     "\n",
     "# create a complete CNN\n",
     "model_aware_quantization = Net()\n",
-    "print(model_aware_quantization)"
+    "\n",
+    "# Quantize the model\n",
+    "model_aware_quantization = torch.quantization.quantize_dynamic(\n",
+    "    model_aware_quantization, {nn.Conv2d, nn.Linear}, dtype=torch.qint8\n",
+    ")\n",
+    "model_aware_quantization\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 90,
    "id": "2bfe62ab",
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Epoch: 0 \tTraining Loss: 43.657235 \tValidation Loss: 38.291903\n",
-      "Validation loss decreased (inf --> 38.291903).  Saving model ...\n",
-      "Epoch: 1 \tTraining Loss: 35.202289 \tValidation Loss: 32.071317\n",
-      "Validation loss decreased (38.291903 --> 32.071317).  Saving model ...\n",
-      "Epoch: 2 \tTraining Loss: 30.819177 \tValidation Loss: 29.494602\n",
-      "Validation loss decreased (32.071317 --> 29.494602).  Saving model ...\n",
-      "Epoch: 3 \tTraining Loss: 28.422607 \tValidation Loss: 27.280901\n",
-      "Validation loss decreased (29.494602 --> 27.280901).  Saving model ...\n",
-      "Epoch: 4 \tTraining Loss: 26.796054 \tValidation Loss: 25.787639\n",
-      "Validation loss decreased (27.280901 --> 25.787639).  Saving model ...\n",
-      "Epoch: 5 \tTraining Loss: 25.409215 \tValidation Loss: 24.846678\n",
-      "Validation loss decreased (25.787639 --> 24.846678).  Saving model ...\n",
-      "Epoch: 6 \tTraining Loss: 24.222166 \tValidation Loss: 24.243641\n",
-      "Validation loss decreased (24.846678 --> 24.243641).  Saving model ...\n",
-      "Epoch: 7 \tTraining Loss: 23.165727 \tValidation Loss: 23.421383\n",
-      "Validation loss decreased (24.243641 --> 23.421383).  Saving model ...\n"
-     ]
-    },
-    {
-     "ename": "KeyboardInterrupt",
-     "evalue": "",
+     "ename": "RuntimeError",
+     "evalue": "element 0 of tensors does not require grad and does not have a grad_fn",
      "output_type": "error",
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
-      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 42'\u001b[0m in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000052?line=0'>1</a>\u001b[0m train_loss_list,n_epochs\u001b[39m=\u001b[39mtraining(model_aware_quantization,\u001b[39m\"\u001b[39;49m\u001b[39mmodel_cifar_aware_quantization.pt\u001b[39;49m\u001b[39m\"\u001b[39;49m)\n",
-      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 15'\u001b[0m in \u001b[0;36mtraining\u001b[0;34m(model_, name)\u001b[0m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=16'>17</a>\u001b[0m \u001b[39m# Train the model\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=17'>18</a>\u001b[0m model_\u001b[39m.\u001b[39mtrain()\n\u001b[0;32m---> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=18'>19</a>\u001b[0m \u001b[39mfor\u001b[39;00m data, target \u001b[39min\u001b[39;00m train_loader:\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=19'>20</a>\u001b[0m     \u001b[39m# Move tensors to GPU if CUDA is available\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=20'>21</a>\u001b[0m     \u001b[39mif\u001b[39;00m train_on_gpu:\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=21'>22</a>\u001b[0m         data, target \u001b[39m=\u001b[39m data\u001b[39m.\u001b[39mcuda(), target\u001b[39m.\u001b[39mcuda()\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py:630\u001b[0m, in \u001b[0;36m_BaseDataLoaderIter.__next__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=626'>627</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_sampler_iter \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=627'>628</a>\u001b[0m     \u001b[39m# TODO(https://github.com/pytorch/pytorch/issues/76750)\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=628'>629</a>\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_reset()  \u001b[39m# type: ignore[call-arg]\u001b[39;00m\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=629'>630</a>\u001b[0m data \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_next_data()\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=630'>631</a>\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_num_yielded \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m \u001b[39m1\u001b[39m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=631'>632</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_dataset_kind \u001b[39m==\u001b[39m _DatasetKind\u001b[39m.\u001b[39mIterable \u001b[39mand\u001b[39;00m \\\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=632'>633</a>\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_IterableDataset_len_called \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m \u001b[39mand\u001b[39;00m \\\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=633'>634</a>\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_num_yielded \u001b[39m>\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_IterableDataset_len_called:\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py:673\u001b[0m, in \u001b[0;36m_SingleProcessDataLoaderIter._next_data\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=671'>672</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_next_data\u001b[39m(\u001b[39mself\u001b[39m):\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=672'>673</a>\u001b[0m     index \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_next_index()  \u001b[39m# may raise StopIteration\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=673'>674</a>\u001b[0m     data \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_dataset_fetcher\u001b[39m.\u001b[39mfetch(index)  \u001b[39m# may raise StopIteration\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=674'>675</a>\u001b[0m     \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_pin_memory:\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py:620\u001b[0m, in \u001b[0;36m_BaseDataLoaderIter._next_index\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=618'>619</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_next_index\u001b[39m(\u001b[39mself\u001b[39m):\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=619'>620</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mnext\u001b[39;49m(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_sampler_iter)\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/utils/data/sampler.py:283\u001b[0m, in \u001b[0;36mBatchSampler.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/sampler.py?line=280'>281</a>\u001b[0m batch \u001b[39m=\u001b[39m [\u001b[39m0\u001b[39m] \u001b[39m*\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mbatch_size\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/sampler.py?line=281'>282</a>\u001b[0m idx_in_batch \u001b[39m=\u001b[39m \u001b[39m0\u001b[39m\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/sampler.py?line=282'>283</a>\u001b[0m \u001b[39mfor\u001b[39;00m idx \u001b[39min\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39msampler:\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/sampler.py?line=283'>284</a>\u001b[0m     batch[idx_in_batch] \u001b[39m=\u001b[39m idx\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/sampler.py?line=284'>285</a>\u001b[0m     idx_in_batch \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m \u001b[39m1\u001b[39m\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/utils/data/sampler.py:186\u001b[0m, in \u001b[0;36mSubsetRandomSampler.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/sampler.py?line=184'>185</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m__iter__\u001b[39m(\u001b[39mself\u001b[39m) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m Iterator[\u001b[39mint\u001b[39m]:\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/sampler.py?line=185'>186</a>\u001b[0m     \u001b[39mfor\u001b[39;00m i \u001b[39min\u001b[39;00m torch\u001b[39m.\u001b[39mrandperm(\u001b[39mlen\u001b[39m(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mindices), generator\u001b[39m=\u001b[39m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mgenerator):\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/sampler.py?line=186'>187</a>\u001b[0m         \u001b[39myield\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mindices[i]\n",
-      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py:1000\u001b[0m, in \u001b[0;36mTensor.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=990'>991</a>\u001b[0m \u001b[39mif\u001b[39;00m torch\u001b[39m.\u001b[39m_C\u001b[39m.\u001b[39m_get_tracing_state():\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=991'>992</a>\u001b[0m     warnings\u001b[39m.\u001b[39mwarn(\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=992'>993</a>\u001b[0m         \u001b[39m\"\u001b[39m\u001b[39mIterating over a tensor might cause the trace to be incorrect. \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=993'>994</a>\u001b[0m         \u001b[39m\"\u001b[39m\u001b[39mPassing a tensor of different shape won\u001b[39m\u001b[39m'\u001b[39m\u001b[39mt change the number of \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=997'>998</a>\u001b[0m         stacklevel\u001b[39m=\u001b[39m\u001b[39m2\u001b[39m,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=998'>999</a>\u001b[0m     )\n\u001b[0;32m-> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=999'>1000</a>\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39miter\u001b[39m(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49munbind(\u001b[39m0\u001b[39;49m))\n",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+      "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
+      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 43'\u001b[0m in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000041?line=0'>1</a>\u001b[0m \u001b[39m#train the model\u001b[39;00m\n\u001b[0;32m----> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000041?line=1'>2</a>\u001b[0m train_loss_list,n_epochs\u001b[39m=\u001b[39mtraining(model_aware_quantization,\u001b[39m\"\u001b[39;49m\u001b[39mmodel_cifar_aware_quantization.pt\u001b[39;49m\u001b[39m\"\u001b[39;49m)\n",
+      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 15'\u001b[0m in \u001b[0;36mtraining\u001b[0;34m(model_, name)\u001b[0m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=27'>28</a>\u001b[0m loss \u001b[39m=\u001b[39m criterion(output, target)\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=28'>29</a>\u001b[0m \u001b[39m# Backward pass: compute gradient of the loss with respect to model parameters\u001b[39;00m\n\u001b[0;32m---> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=29'>30</a>\u001b[0m loss\u001b[39m.\u001b[39;49mbackward()\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=30'>31</a>\u001b[0m \u001b[39m# Perform a single optimization step (parameter update)\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000014?line=31'>32</a>\u001b[0m optimizer\u001b[39m.\u001b[39mstep()\n",
+      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py:492\u001b[0m, in \u001b[0;36mTensor.backward\u001b[0;34m(self, gradient, retain_graph, create_graph, inputs)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=481'>482</a>\u001b[0m \u001b[39mif\u001b[39;00m has_torch_function_unary(\u001b[39mself\u001b[39m):\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=482'>483</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m handle_torch_function(\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=483'>484</a>\u001b[0m         Tensor\u001b[39m.\u001b[39mbackward,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=484'>485</a>\u001b[0m         (\u001b[39mself\u001b[39m,),\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=489'>490</a>\u001b[0m         inputs\u001b[39m=\u001b[39minputs,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=490'>491</a>\u001b[0m     )\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=491'>492</a>\u001b[0m torch\u001b[39m.\u001b[39;49mautograd\u001b[39m.\u001b[39;49mbackward(\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=492'>493</a>\u001b[0m     \u001b[39mself\u001b[39;49m, gradient, retain_graph, create_graph, inputs\u001b[39m=\u001b[39;49minputs\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/_tensor.py?line=493'>494</a>\u001b[0m )\n",
+      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py:251\u001b[0m, in \u001b[0;36mbackward\u001b[0;34m(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=245'>246</a>\u001b[0m     retain_graph \u001b[39m=\u001b[39m create_graph\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=247'>248</a>\u001b[0m \u001b[39m# The reason we repeat the same comment below is that\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=248'>249</a>\u001b[0m \u001b[39m# some Python versions print out the first line of a multi-line function\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=249'>250</a>\u001b[0m \u001b[39m# calls in the traceback and some print out the last line\u001b[39;00m\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=250'>251</a>\u001b[0m Variable\u001b[39m.\u001b[39;49m_execution_engine\u001b[39m.\u001b[39;49mrun_backward(  \u001b[39m# Calls into the C++ engine to run the backward pass\u001b[39;49;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=251'>252</a>\u001b[0m     tensors,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=252'>253</a>\u001b[0m     grad_tensors_,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=253'>254</a>\u001b[0m     retain_graph,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=254'>255</a>\u001b[0m     create_graph,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=255'>256</a>\u001b[0m     inputs,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=256'>257</a>\u001b[0m     allow_unreachable\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=257'>258</a>\u001b[0m     accumulate_grad\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m,\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/autograd/__init__.py?line=258'>259</a>\u001b[0m )\n",
+      "\u001b[0;31mRuntimeError\u001b[0m: element 0 of tensors does not require grad and does not have a grad_fn"
      ]
     }
    ],
    "source": [
-    "train_loss_list,n_epochs=training(model_aware_quantization,\"model_cifar_aware_quantization.pt\")"
+    "#train the model\n",
+    "train_loss_list,n_epochs=training(model_aware_quantization,\"model_cifar_aware_quantization.pt\")\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 76,
    "id": "7cbf3f6d",
    "metadata": {},
    "outputs": [
@@ -1146,30 +1128,31 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "model:  int8  \t Size (KB): 76.522\n",
-      "Test Loss: 28.639511\n",
+      "model:  int8  \t Size (KB): 251.342\n",
+      "Test Loss: 28.070383\n",
       "\n",
-      "Test Accuracy of airplane: 58% (586/1000)\n",
-      "Test Accuracy of automobile: 81% (811/1000)\n",
-      "Test Accuracy of  bird: 21% (219/1000)\n",
-      "Test Accuracy of   cat: 36% (364/1000)\n",
-      "Test Accuracy of  deer: 30% (306/1000)\n",
-      "Test Accuracy of   dog: 42% (425/1000)\n",
-      "Test Accuracy of  frog: 64% (643/1000)\n",
-      "Test Accuracy of horse: 55% (550/1000)\n",
-      "Test Accuracy of  ship: 39% (396/1000)\n",
-      "Test Accuracy of truck: 54% (542/1000)\n",
+      "[1000.0, 1000.0, 1000.0, 1000.0, 1000.0, 1000.0, 1000.0, 1000.0, 1000.0, 1000.0]\n",
+      "Test Accuracy of airplane: 61% (614/1000)\n",
+      "Test Accuracy of automobile: 65% (655/1000)\n",
+      "Test Accuracy of  bird: 64% (640/1000)\n",
+      "Test Accuracy of   cat: 37% (376/1000)\n",
+      "Test Accuracy of  deer: 58% (584/1000)\n",
+      "Test Accuracy of   dog: 44% (446/1000)\n",
+      "Test Accuracy of  frog: 77% (772/1000)\n",
+      "Test Accuracy of horse: 68% (684/1000)\n",
+      "Test Accuracy of  ship: 73% (737/1000)\n",
+      "Test Accuracy of truck: 58% (589/1000)\n",
       "\n",
-      "Test Accuracy (Overall): 48% (4842/10000)\n",
+      "Test Accuracy (Overall): 60% (6097/10000)\n",
       "None\n"
      ]
     }
    ],
    "source": [
     "#on affiche la taille du nouveau modele\n",
-    "print_size_of_model(quantized_model, \"int8\")\n",
+    "print_size_of_model(model_aware_quantization, \"int8\")\n",
     "# on teste le modèle compressé\n",
-    "print(test(quantized_model))"
+    "print(test(model_aware_quantization))"
    ]
   },
   {
@@ -1177,7 +1160,8 @@
    "id": "a2201f4a",
    "metadata": {},
    "source": [
-    "# ajouter des commentaires sur les résultats"
+    "La taille \n",
+    "La précision globale est plus faible par rapport au modèle, elle est de ."
    ]
   },
   {
@@ -1188,15 +1172,52 @@
     "## Exercise 3: working with pre-trained models.\n",
     "\n",
     "PyTorch offers several pre-trained models https://pytorch.org/vision/0.8/models.html        \n",
-    "We will use ResNet50 trained on ImageNet dataset (https://www.image-net.org/index.php). Use the following code with the files `imagenet-simple-labels.json` that contains the imagenet labels and the image dog.png that we will use as test.\n"
+    "We will use ResNet50 trained on ImageNet dataset (https://www.image-net.org/index.php). Use the following code with the files `imagenet-simple-labels.json` that contains the imagenet labels and the image dog.png that we will use as test.\n",
+    "\n",
+    "\n",
+    "\n",
+    "La prédiction d'une image se fait en plusieurs étapes :\n",
+    "\n",
+    "-On resize l'image a la taille 224.\n",
+    "\n",
+    "-On transforme en tenseur.\n",
+    "\n",
+    "-On normalise\n",
+    "\n",
+    "-On charge le modèle pre-entrainé.\n",
+    "\n",
+    "-On fait la prédiction.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "184cfceb",
+   "metadata": {},
+   "source": [
+    "Experiments:\n",
+    "\n",
+    "Study the code and the results obtained. Possibly add other images downloaded from the internet.\n",
+    "\n",
+    "What is the size of the model? Quantize it and then check if the model is still able to correctly classify the other images.\n",
+    "\n",
+    "Experiment with other pre-trained CNN models.\n",
+    "\n",
+    "    \n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 97,
    "id": "b4d13080",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<PIL.PngImagePlugin.PngImageFile image mode=RGB size=188x282 at 0x12A5A7B20>\n"
+     ]
+    },
     {
      "name": "stderr",
      "output_type": "stream",
@@ -1253,6 +1274,8 @@
     "image = Image.open(test_image)\n",
     "plt.imshow(image), plt.xticks([]), plt.yticks([])\n",
     "\n",
+    "print(image)\n",
+    "\n",
     "# Now apply the transformation, expand the batch dimension, and send the image to the GPU\n",
     "# image = data_transform(image).unsqueeze(0).cuda()\n",
     "image = data_transform(image).unsqueeze(0)\n",
@@ -1272,18 +1295,169 @@
   },
   {
    "cell_type": "markdown",
-   "id": "184cfceb",
+   "id": "d958a750",
    "metadata": {},
    "source": [
-    "Experiments:\n",
+    "On va tester ce modèle sur une autre image : un king crab.\n",
     "\n",
-    "Study the code and the results obtained. Possibly add other images downloaded from the internet.\n",
+    "Il faudra bien que l'image soit une image RGB."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 96,
+   "id": "88b2ef3b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Predicted class is: red king crab\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAASoAAADnCAYAAACpOxvxAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/OQEPoAAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOz9R7BsSZrnh/3cjwgdV4untciXWlZmlspSraa7uhszPYOhDUEABgLEgkajGTbkgguuuCC5ADhDM8AwIInmdE/3zHRXtaguLTOrKsVL8bR+72p9Q0cc5c7FkRE3rniZVc1epGe+e2/EOcfl5//v/33+uR+htebT9Gn6NH2a/iEn+f/vCnyaPk2fpk/TfulToPo0fZo+Tf/g06dA9Wn6NH2a/sGnT4Hq0/Rp+jT9g0+fAtWn6dP0afoHn8y9LtrFqi6MzkSfsquDYo+ndN/de935q09xab/qlcxhrRhWxn73iSHPib0v75mtHnhuv97eZ1TEnh937dVhvb5bU3Z7/nFHLFu33Xp0PxnUj1H2buWJHVdE9Fd/riL+KWCvlXaR+TmYT1LWPmJ04Kn6K02DlRr2ee/U2V7BbdeH3rgnUBVGZ3jtv/q/A3GH6T0mRFwxHQ1G+J3IXP74fbbfFBn8fBDR2z1PjUYAQohd26tRyb3hHf33iExddCavpB+je+L7RHS71nsI52Addrt3lxROkHT6CjFQZ5HpPx3WKXuP1vEI6+Q2IeJydxHKTLviz0L0fymE6B+NwYks0umrtEYIEZoC0XNxu3TUB0n2aUt3doYArXSm5lnjYmf5/TiQ5iyFSJ/QOqmrztwlsx0RA5XOgFq2u3T0rRg+lrFcDoJd/zjp/gd2yObu17I3aS2T/ESmD7RI25uUu0M7hD0bV2U32czW+yf/7X89vC7sA1S7NWC4UOq+74f3sxj4u/+ZnXpo/8nXn/TA793S3nnuMqx73LtTxelE/CMw0tlr/RpzJ8j15wQxyA0r//H6J54eu8yDzAiE9dIZMMnWT2e7WsQCqXdkPLwY3XdlT4YhxI6yMw+GICJA62xPDPKSbIUJ67ijSBVVXQ6tddK+PoCPJ2momXV2bmTBTWfLFwgd1ncvgtQHArskvbO7h6adzDiVKTEwZiJmfZECissQ8TUGFV70OdTbSZ3FgRj+wdPjA9VAinXh4xtbgyD1SdPfZ+BqdqLtI0zJHVnmw46/s0K302SJOd4nTBmBkwjUYF0HAKMfTuJnd5LMoTizW3X1wB9C7JLB8HoNn9QHKLc/w/S3yPBBDQjFQcd2aDUyeQ6t4GMHWMdAPDg28cwTKa8fAOPday+GolzM75N8ow8xeMUKKlFeUmRLf+y002zePR0AqPYRosFbBgS4n2bulpfeMSn2Kl9nfww8dCA57WMxg/nvUces+RKPXHJt907vb9tu5Q6T4aHTMgNbjwteok8zDuY5eGdsney8O2Ne6SGDP/SZIbXJmk27pKFsSwwI2WOk3eUsI1KZth2EseyVdmPcfUppzybo/Zs4XEx2YeDR7TEKxTWMgU2n9yW/+0AvZXoiYpdC7wFWie03wNoysnWQETwgozpIVp9wRDVRhxxM8GIe93imz+4gMey+GGjTzhx4LgYnIXYI9KBwxVqqv4wUMndC9XCt/rjaS5CdFJKs4SkzRWrd72/LWCYDbRioVZ/A7167YdbWx96+pTVaiIGxGQZCiaHbx9yS+0TYTq1346uZiZz5LvlG9F83EEm90jR8Emf9dLuBZ+wbGpbScU3blJ0Ne3EVQabWIvWzZa8TWXNZ9IqBSQqB0ipsV4JDe8/DpF4yBLbINsxIDsM7IUoHZlQZ8tDf8CH0MbxtfyFMnbJZ9+R+KRa4+NkDPdT3+EADktr0V04nnTecgWSm5gCLHu5AHA44cXXC/DITa2eNHj9l6KzI/E08MRPpiWqRAG8/3d+3iIQZDeNeRNc+sSobUngKPnHKlqMHC82iZQLe/T2fXuw3NxFZYN2pmLIO/7766Gxu/SymL/9d0q6LNRlGFoNU/DkLYMMLyLRUiP7cM/n212OI6tSRqt0LpEQKcHE7RNSh2TkkdrSwPx0AqPoHLduALG3dUchBZ1kMfLG229W27gfAfgjo1+qfPGVgNnKS7ga8sY2uMp2x7+pbBppiMPj73huuh3yIBSh7PWYbO0BoD+TZlYn9qoYnyXgIU+kvMXGC7xyTnTKzo0mDk3aAle1Wj3BVbr/KZzlaygl3UZsZ8rabbKWrngfVCslCRUbnD+Z5kIz2uisBqczYZ+dWaEXtrxH3AarYPt6t+zJfDSkoq6GGmXSCSIknamAYcc3msJtgDvvmcWdEKriDnHA4SA0Oz4AG08O1YZY79rf4YHxj97sen7PE4QYJwIpIz8UO5ohVhvLUb+YMK+1AbPhXhFS6LxQgU37cpqhzhY4ZRxZqB7lT/wgN3tNXbsIMssos/GaH+d/X1qyjevcr/d9kCUJqcu4MTYjuGai6iEiyGDJYIkvJ4nk+QDgHeWUfwPQ1dMCkGJgWGh2ae8Tjls14/9VNOLCPKpNztj46/hF/kRHhvrL7ByHbHbsL+yClH4RjMfjAjmceNyXQkQy0HrxhoE5q4FLUNtVHUYaktC1ZbXKw2g8DvSHV22/sIwHaaXQPjInOwK0I+6R/gqbPit2GPQbuJNRhoCqDInTApAcnSLJ6E864VJPr9HpSoX7lmTj2+/RNurIWX+yHDjJXUzSIJ6PIouaA/hRxOEPf/M4Cb3aeRPcOoE7yaKTtZQTJWRWYgNUQOEwqlO2ebP/3IX+6YNSnwKN+TgAoe0OcBhZSE+e7Tvt4v3H/ZOEJe2Q+HHCGP9DnP9kt6WGdHD/18ZdI+4tIdWvC9g6YUuEQfQC2R2HsBPTHS4+3kLDj4UjLZaRrmAc9pYfJtE3mfXQ1q5wPWqMUGD6pctk/j0F2slOShj0vdl6PgLqf/WcXROJ7IwYxAESQ0eVZf9dAuXFuqVzHCnSAOgm5o5Y7fE5xFfSAPO/T7Tqp5oBSjfJTWcjOCgQMDVvYc4wOEBC2P1AJMoOwX3ocUR0oZN/rUddlNeWB8zxI7fXQP3dXE3uUJwY+D739E4DMYPYfd6735SGGfLnPyA9Owo9Zjb+3tNdQ7vgulOU9u3lQmyX+qzisISsTKeDvPWAi/aV3Qs4g4CZsN56okc9nsPiDiIiI6hmDitY6Mv9D4B0mssPMtqzzPARInTDqcEU5ZR199+1RyT2B6nFNEYiWNEnD0XbeuVeug7b7YE1EBgSyJPwADGYgq938XXFe8XCnWlL03TdY4511GDSpBksKk9JZGE4Z3V7OeyFiAdYZP1N/fZLIYBEL3M4apXgfCk8yPimBSHV7phlygAEfFHP7+m0giHPfZ/djYAOLMHHYwdAaDJqEO2oQj7eOtrsQOZ7juqvMbcMnqoaMV2T4LBxUDSGGKbQIQ0diuchytwi9BqQjZXn9W7V279k+wzVDRrRSfXdlayjiHQiJ/KW3DAKWzoB23z0DjY5lfj9W/Akj07OTOVIug7Eqv6qUmVR7GYH7ff94JmK/XZ8MTlyXZAwOnuduoQ7pXyJz325gRbIANXhX/wrocC2VFb9U80blDvHLpZo28/WB0CXza+D+QYBNpGjAD7JfWcMDQqNrGb6R9kdG2ydlZkyPxFGTuZZkm+4DTYoZMFsO4hjOCPNAt/R38OCSfRKAmiihvQJg4vz2qU9Wa8VhK/FjmZCLtC/7eyCOmt815mtAF+zYkxiV9cmB6kCIo/t+7T9xP66t8snSrybUn0SYf/WtSEEm0o8DSiD6Gwa6cLe1xP1TmFei8j5etR8jHUScBvu1r467PjRkdHfIY7rJti8Wj/6JknUM9zOaA6QhcV1APwvZK4mUzfdNarIMd2gPpRmQKrFdixwyEAksZRhb6iUbiqx9ZmKSz26AlQGkx/VRfuK9fv01YVifZe44ON3f6/ruTXu8SPWsw29XBjNESvej1dlrckDY9pL2YXXv06h9f/dVKBHKrHDuLgMDQNtPCnavX+aeveRrtwmSCHUUEZ41MX+l/Hufuu3rKsiMed82n/4lwYPJWrICOHyi95Eo0hWwOMYpW77Wut806xvANHPR93d/uTpDZYeFLST3DAhekmVm4BJGP0QYhgG/yCzWPO4iymNsodk/Y/F4ZQ/PI/n562VdSeT1Lkt7ib/oY1QjO/Gy4BQeZ9IP1rsBhNbpFgZB2reabGxbrJ0ybUrqv7MX+0l7ujKVlfc9sW0vLZSUEJtE8W39mjPOZuc2a9H3134lHSQNN4X6vx+u2XcBlSSXqO+ik2H2l3uBEJLhfFIP3BkzKlL5y1anr756Ry5i4HcWXIfi0iDTGVKtBLdVf16xyQcgpUzqd+DVPnZhX0PSnkCVmWqZbx6LCP+DSv1dohHIPbXrsCNY4pySiZbul8k8N3zA9z8wbccjOwQmFs9hkznRxsPyGShnx3Q5IKva774QYKMtEfvQYk3omE9uE8mlXyW/6i90yDePXZYOWZnQxs5rMahkQF8MXhwM2Oz7kEqcUipRqFkwCW8bdEDLJG+9QzrSUvTAV3vaBXEbBm7akXNc574VvIPhw0E3z+3DqAQDzLHv2kG++nWkTxQ/lE0fE2sTwNB7d/NePrG0DUM6eDcHsR78KmaFcWk6Eq69JHD4LoH+gqL8dkPM+M5BAd5xfx932aPM/S/Ht/zK1eNBEXrwsSHf9bODVIFp6FukGHbG10BGYbV0HJArdjy3NxAMuZZVqHtEkWfrdZD4tMG+Cxn/Hs71zNMJK9x121yafoU+ql3SLm0dtLiS6TFoYuzo049jFAyvxE5f0zCNm6XYH5dNDq9zDHaw03xQmXJDQU9PoIz7QQMyim9RUbRvcu6oHqyrGFp7vcuHVDnGJsHefd1PLEXfd5mvMpNhGKtLN4JnbdJ4bvXLxi7UcQD3DzJS8T1pfXWCs7u1WkT1FWRkeRf2HG+nEwPf9+U34AAMl/LFjnsSc2swn8QUjDtgeM3DdaBMH2oVYwUheOzS4Gw9iORCZFm+GJCfXXou08ep4okBeffCf/1AdeDUX+30218nTdNRCVkIfAxNJfqf3D0NCNyQNvXhxZBBS83QvafgcMIffz+o/X61KQaZbFzMYEuzuxAGVUTSar07QKQLlBoikN5Nde3FwNIJptnR3Trze1fDIZyYySZ6HY2RGM5Xh6nDZDQTs0X0M7xdVi8GQzvCvAYqvVvdM4wqxLZ0D2EIulG7hj/eX14cvrBjWgw/GXZ4PgfbVbIvUPXZu30SMYxeDtz0GJQ6Fph091kaCLZ7YweZzrBrByz7Y6W4zmnaWdVhIvW452ilWmzoc79qxNk1y2x/Z9u+e1v6Yn/iSayzE2tnOggch/FQkaLpV+b7tKH/ms5M1PhXyHzYe6Zm8+pjk/RN+B0CIUS6X3LI9eQ4lKy/J6NC91em+1U2raVkAEiECPfhCRBa7XxmV3op9q3SjlXqvnbvpVLCdHBGlazaRD6OQdWn4532KZImFJFhND+jmZJ69m94jTXUrz7tDnz9snNwgch2dcyy+ibAkLL6jbjB/IZxtYHZE3Xi8JL6n0zEU/TfucOc2qUeffkM6i2RjrFOxm0nMelbsh5a2s42iKFXhtRT7CRG+0lONuBwxzNi8At2EYeYwWTYVfz9QHBjOicG5CUSuh1tHSgvu8r2+Kk//0S6RH+puq+C2Z0Sg9l9snnZt692CEMcTPse89KP4ToCpBSg+gQwuwTN/mMc9kf8M81jP3fvrzZl6twHxgdPyZaWrI3ef8eOElPzbnhLMwvUmfszOWidDLAQeo/67nFlkAEPPrVDu6S1ybZlr93beseHjOIaZBNDnhwE0mwAeXot830mr93AMAXYwc3EJNp+Z/12kch4rsf+o6jwQV9r1hzqmx9aJ92asqnMTYNKIZP2szOi7KN7dUqMdokG1cSdOkxxpm2MMx6uCner7S51/fUFfA4u58f7iyKNovfmEUlKBnVgG0AStt//e5/Mkrrs30l755dEBdO/Q3zXfLKOyeR41TRKaPANrzsZ0vCUnWSCrEGs+4pMBW74ovSOfIfcMOy5UJbTglJFNaSWQ7p0h683k8t+TGrYNEn7o3/Fa+iiXZYo7TLcfWClB1Y4PymJ1zv7NOvCSNmt6Pt7ZzYZAhCDGY8DA/H9A9HlWU43lEHEX8qBr3Xyu/8kht0V7mNUcs90YKDacebMzhtSudX9zw2mYSi64z6d1ZTZDv71pKwGTX9+8vISjhbL3CedBDB0Bu71Ka3LLppyyD0pHU/HfPjZ4rvxlnSC7F6j/VI6BgfluPuNmobEPJVR5HfCWJP5Owz9DpYS2R7GjuI6DviFdnw3UNks24e9pmBWtaU37/nyhSFFxr+HKo+PbXoOTzveC7hLeqyD8wb7PMk7prkxfd2n0DD+J80zSTFvTr5V2Qu/orR/Xo83pPGnHZyk766+fsug1VDgSsyGrHAOzSnxIPQL1sftr7SMPo6qSSZUXDURAVh4TobKgPtgbglU7wTFPYR+UNr2vHeQEcXlZhxlactSJpGtnxzQsFlw2A+yhtZN95e/o25ZdTjAAPuYSx89HEgDqwi77beLT8ZIvxE7Vg77QSkda5G5rpVOXz460JrBAdg1Fkvs/Dj8pIv+tC9Qxb6SGEMG+yvlOrFnaacDfEcVRGxi7V7qr5M97Z8+jjbdfdh3Zhn31m59sJNKhwI9KIjZw9UO2mOZEiPU6XtT72712TVzDTr1NO7u1zk4t0pb83HpZ4xO/fXZCfWZMiKZTGoZ48MnYMB7PTpMyetB4BkqO/15DB+WjDz0MbxklHbcnnCEgQuJjO4DJI8TjvBxhvUA4Qk75thgyckgD7u8d85kVv+y3Tt4xO/j5flJ08cJHxhM/VynL/OBP8S+QrBX+vihFenTn6ilmfFL6ReEvp++23amfQseBm7D2Mvu+eohWWQneJ9fWafTOOmXT4BWex59MjTLlEntqvcOUm6Yye7XkssDvFUPA5IDStgB67hbn+wHcI/hTB+O3/0LCIPrdQe0jWNtpvVu0/vvOe10Pj5effSuT+zqX+Dvl0M+VnnDVHAmn+zXaZR2xmzKglmWwe1XAZGF+339CX359fMokdZB6AHsiT4P2uBD9Egq5/tXZbfvdpi/A0oxBqmD7AjY7dQCnUXeTN3TYM4oT62ijugbnT3GJTVXdyoH0X/9V5wO/qbkPYQqi+A72dFBk+gzHXYc4PYrSlmhG9rX6Z0ZsBLJ+kf/No9PUI89vxxO+Q8UU7Znv/UDb2gZ7SGYwyKjh844vaPqWZOq/0JWngbXRAfy7VsC75/SfVXrK3fwuTgwNMp8EDT7yhVkP2p2yvFup21k677XS0MPkgaVXHZIh2YdDaEWOumLwXEdtu0mmbcHZYw7ECoDTCLOfzdI/mTpY78pebdo4Ojq8GcGYCybvRaqv22/Dlj+BCkFrU8GoHuZWh8neuzxAgBjqh8LcaS9951Yu9tWaewNqZLp66fdzLaPY9RnYOsx6KDOnPed1iyzYLDHRM3i7EHm88cR2zQMYci1rDm9SwnZ59PXUYk9nsgWJXcVyr5YsMxWoSTfmJhlWNgwuhJ+s0fPHGAsHzOOqr/D9garg9Xo1xJ4/mtOnwiuxKBcDLNX9pvkA2nPlZX+Dk6n577G1B557lKXWDvvlfFB7ae9it/v3oGI8PT7NK/0a5E+M4AHO8rMTNxfz46JgZQlJwcROJ0BrAxk7PWojhB4v9YcvLV7EZSD3D08PXbAZzzJ9i5g+NWD6dNfj8kH/fN5d44w9Mnk5yeund4FpMhqsIi/DbG8+kFMp1o0TgNO7D4qkJhEKVR+3OnWr+T3ymXvadKXhgLssOf3uRaxisGo9kEBSNhl5nf/+OzWLt1HIg/IG/pzOICGDy0p3VenZP7t8ryIKjXMANu9RL3zoojBeKgQDi93WImZ2ETdZxoOJLl3zx0gPCHzR4beDfMVDH2O3Tto15Wxv+eUVfJ7BQwMSPFAHsMJ9jBA3N3Ey5pRwy5n9npl2Nfg2dq7KoTshtjk4h4qYzfBHATG/diF2PHHARDyMQBux7V+IMtG2A+7Pz6iJNzDKval+eF8Cw+162dme9uHe71Bp++jZviCw2DYz6DzSqTnawx/jRWorAwNFLBzo/DBUnbFf1AJa63Tk1AZ0BWZkIb9Sts/PGFQk++gVJke/XXY8Lsp1L0U7a+q7F9n2mGu7S/g/UQp/dRH3yNBTALuInAKyyChAOFWnLgjB2dFxqzfReP0HePy92i/D072/c89iloYt3louEAI72lz45WxLFfKfgoVSuoGynaWZsfBIoMKQey8nPS87v/df9MQOehrQ3zv8IP1hgVhDh7C1/+q92HtGChTDKzz68wi1C5ZDaubUnufY/8YpycQ0cHBrzMCuyNFA7frtexdaTmD+i8mj9nN0INZxe+x6xOmITcNniv+KzDmDpx2OOMfc37vZfCQuRZH+gotkRJERKu1NEAFCFTCruJJJrRGS0IKrnT0Gu6dkpZo+8Th8/cL/wcrbZhMhm3Nmh+67+5YDtP3HqfYkImuGsYOsyQ3RsW+otNxD49QEZkHBrId1pQ+JIu+HgTswfoMuS97Im32u5Sc96+yhqAlM/fGZcUVHmCCSb/p/m/6WHzKWuOQpIOYwQcy/cKx+uQCGdLSneKDFqmJKtLNwIl2ydjKyWHyEXDFb+ro32oQG1hqx6wW/T/iCgzcEFdu2MNpxYe0ZHjq4/KDee1GDwfqoAeCUCMwytZfE4GSInqzrQVaIbRCS6isL9OdmMAXJgZB+MZaIaMyVLLvDQEaE0SQTkI9KJSkLC5bz+SGXxOAfYJ8d1tdEzsHM2POpDI0iM3ZYNLktAuhdxaQlB/+SF/GkvK33R5IwPIgWiq5RffdNwygsmnYTpIUdFW/yZbUQ6QrkiKGcpnszdVRudk9wBDNaaEzw3iw8RwSyDKsIfHUz/wT/f+Glxdrtvg/OZDLQDmEoGMKGf6TMnxCa9BBYsLEk0RKiRQSIUSywTTNXYfH9BK+sip9iUA/nf9YjCqW6zg2RcfCufNfemKADplMdrLoOI9sJ+wBfwNBlH0gq6J6BD4ShZAmwuwihEIphekFVD78FjPuClIbSCFQWqK0QGoDHUjQFkIByugbnYRADU7mvz8yum8K65j6y4aNRpp0v+zum9KJJYbKb1zCbubL7kDUJ0OD/4jZhk6YR3oU8WBW6X8HLB3of51bnLI2R4onMSCFd2hS/1yMzULERygbOxVzpiJCZ/6Rka+96rn35UwBg0h1gGfiykCqobIRwWQqGX8tBUhDYBgy/GdKpBQYUiKlxBAyAiiRgFQIcDIRVCFi0MtWOd1d2C/Kw5jRbtfoY1J9YL1HF4nsMwx7OO6bAZWdlBkKZr+g6mRuiJhKa4ER/20EPNGZZyrXQUuJqG0z493nqe4dCjmNMm2QYK5vYv7kW0xv3aPqdKiu3EIYGo2/R/jOzom6ExR2B+/HTo/12E52lE1ZMp39PVy0dd99OyfTbhUbLg0JmA7PbGeusU4bUkTMmrKikNV9H7erdzQj8yFVBjtZWPpA2lnxjOu7c0AUYnlWau/KHthHNbjAsHfqXwfoE+lkBDKmjCAFnYj9JCsYSqAMHTPMyKbODHyUGwKUIO2AzCglWilB3HQqDVFNu7SIxA8WN6Qv/nlPzfSrTZmWhWadEFg6wDfyqNAJgqUsNq/c5LmzK9w88gJzl++ytrzBOWeOL3OTuw8cRqYn+dm3/2fqm3c5xPOUuprKi89zVfphkKSWfaUJyJgtKcuKx0QpRfxSgl3dDuIx+0Xv8vcglkP/iuauKd3mlWw8HpDRnXfHQtVf+fjaDiV0kLRrB6VsqU9Vaoa0Wfc9NpBLwrwHud+wIvvblf7s6/Ik1CCcQ0JkHhbxwYEpq0nPj9dIHT0/iFq7N6Ev7cuoBne97WjgEOSOTbiY5ezsqvTYCUHob5ICDCEwYrCKxCcx6URqxsVZSgFSRr9j849sF8emV7aSA6wkqfPurKi/BTrRyoNvs/1VpN3y7APJTKW1lBgi4MidH3NEb4dvIZagbUEjV+XNv/xTjv/yrzm6eYtHLcWNGzUuiTWK97/H0zNlLj1xlskRk2DuFmfL67iTh9C+wNChFzBlphohdNjfEgypw35Hh0I0oNK1Hm6GHETL9zFHdJ+ZsOdz+2cd9ZvYOdZ9cpZ4nJCAQSyPw2RD9IPBgPmWyLgQSCkQMmX6DMjgQCdkaFVCP/ry3O9f0tyBfzLzL2EA7Jy32XnXn2849kKkJnQ/exmQ3fi/SIazzC87P/ca3wMd8xL6w8TQTo0zH1zKHqIAhucftTR1nMelhhlodsb+xEAer+DoqAI7TyroP3Rs153s2YYMqyOkjsEhtw8TtWQ1ZYfnNc7gccFtgFpownOGtET6DlvX3uP100V04QUCX2AXCjTKZXIj42x7G6y3O6z22ty/d523vtekg2Tj1tu8cmqccS6wcO0Rmw0Pz66Cm0cYHoYOt1cIEZAoFynTPtXRS710Jsg0258JgR1gnsP6PMvYM49oEY/wIJ3Q6c3DuihzMSwyzSPdRzrIHaK/BsduWEpCQHSEH4Nt1BlATCd9fJ5TXJ/YTOuveirLO/YWxv06cHd6WQxc63822+Lkax22dceLJZIcBg4XyDKrqK1puEpYSIizewz0AVb6sulAx7yknv3+NIwrZXty96pkuEoE6PEKQh8wRQLQB0QZ+RxczYj3nSVmoojyGjK4O6qy2+XMylY/WGbPLtrZ3lhLp88Mapk9+icrE7EWEqk2TZbQo9U80dG4yiBXb/JK7z3czW08q4BRVBS+/FmWtlu8aG3x+uHTdL02t+aWEAasK4+mVWWz3mTbcVArHifbKyzlJwmERJgSrRQSiRIglUbIOGgwfINgGiAZLl7EExcyzIHM5M/2+WAHDDBcHbV/z1P0d+gm3TdmsXwJVHhYgCER+AjMsJTk6NX4R2rs9VUzs5Cxv27LgCIh65AiZFPpKbmCQOtkeSWrApP3BWbaBCnI72ng9p1Tnb72Ixvzlcy+rOJNVwv62p0umPSzkMQKzi7wRO0Nv4u5ts4+tmsown5q+wABnymSxCyn73q2MD3wTaxZst/uogFVzFhUeo+O+GGcQ9rIzPJnZuDTSRLfmwHEgcEdGvw2gMYiuU+Eq/hRUFrKAvvbJjL5CWlEzdcD1+OmD6EgmclCn7DG9/iEYQOxxjawLBOnWaNUmua73/wxpw6XePJQGcYq3LzfoFK2OT9ZYOKYT6V8GCxJoMt0N5dZWG3zl29eZ6PlUBKafLHEic4W+WmDa76Ni0QpjUGASZeekgSK6KTHkM7HPtCsJo0FODSdUkd7ZuR29P2wNHRCZW/InpSq04mZ+TZdrRMm0vAREqTOAwGIIDU4RPaV6JnxEXGtI7AU0Wmg9EtUH7joMDtB6JYwpEAakXhHbVYZFrpzkooMSKRAOjxgNStHGXlPcaff+S0GWFei+2PZjlsXMaXMHE4brNPn+rRP1vJJV0BjKzYJoRpkdPuhFAcx/aJMkmNOMtf6NcHeSQ/+ITI5RGxJoPEDleBK6t9KASjWgllqmR3QBKh21HavyulwgGRIxdNQhuwKhwCjX0NkezjxqYhUWEJASwE2rVs88DrtQN1vo/dP7AChTRA2vvYxhEYIE+wSjUcPyG8ts+b2aNQ3aXhbtLrjFAvrfP43f5PWSo3NpZsUsNG+ZHxqnKCzxdT0FLfWXTzlM1bOc6wkqYxM0F64zvjCI14fmaY+MklraZvlxftYBYuTL7xIjQk2y1M0lQBcpM6hiMcv9F+lUBQHlob6VUfdGEdDZ2VcxKKwY2yIGHZm5g1wmuxYp3FM4ZiCRgrNSLeDUYIGFaRwI7YrU1BJUCasWxB/1BqNItwwIzLlp8yRSHaFECGIo5E6WqWWAjNawY6HPFAqBD4R+r+SHFWfgdqnzAYXgiIJy3SUSNwm4f9pjGGyQh4H/saLS1mLpM/siPowibGL6xB9nRQ5RGIT0daZ8RQZFnZQxOhPB1j124VCJaprt4KzenSXy9EfiaDFA59hRVnmo4kFKnovS4bRiMFsdzRjjw4SGTMl6sxkkGWiXxLgydrkad30QH/EgiNTIdQ6mtTJLXEGUXdmz5dMB1kbNrKxynm1jnPkCPe2bcy8hfA6qPUF/OYG25trjM4cZt1z6Kkym9cesLzxN5wZL1DMdbldM5CmZmZ8i6lDoyx1HOaWNb/5uSe5dLxM2XJpOHlW1+s4m0t01z5iemycC9Uy6jR8eG8e//vXeeLSk1y/8I/p6ArggdQIodBKk/g5Yr9F1Ach8ZVhIO+QYUi+Gn45Cr+I+jgbMZ9cTydTDFRCRyvJ0gid/6sf8tLJCtfzx9nqWJATkRtJRIsyEqEDNAYKkFoREJpmIojBlUQ2Q/+TimQvYmFaJ0rOiJiUZRgYMvwMgkCL5FgdYYRgqbVGK1CxWZ0Ofl8n9cPSwOWMf0mI9MUVUsQhPYSOfARKq3DzgYrD73TCJLPARBL3GDOodPLvGKeB+orBr8TOPwdJz17pYJuSM0iQFSoNoe9k2HNDKj78s+7/K/Z9ZCZrH9bH2mAgvwNyp531jDVQvNoRaSKZ0Z6x4MlwqWPAARpq1uxWpdTcEGROgCLIyoAKyAlND42hLLThopGIQICQCUMRAkQQUCiPsvidv+Q3f+sCR058jvfXJdsbKxSDDvXVRUqmxvOhpvJsb22Qo8vlxWWur2oO5yzGbcHE+Dj3110q97u88Y+e4R89Y5MzHPKGouOZzMzOkkPSzRV5uLSO50tW17bpBDa1Whej16a+skb+KYWlQUXmUhjgLhCYaKkSxhsDjxYRvujsu+3SmZes7u0yQlKIyJRQ+HFmAATxLenzWmHI0HwxTI3t9SjlLTquw+U//xu+8L/+L2mMzXJv06VljmBYAtPpYJkuHSHo+RpTmUipkSh8YSD8AE+CFhKho/cpRr/FADMxZFhfUwoMQ2CbBkaK3QTRc0YUzBwCnEQJDYFAa5Wy8yx7EsODKPpZlEhWxUOTM449FCFQETnzlQalI+VJAlIaENELHEQ8sInADkl65zwcHLvk/D7R/3348yDhJGE68OkJou9TnPYuaDcNkHVNJGIr0u+zDRCZTux/5vFS2PHDBjoOe4jERke3iZg0xtG20LdXMHHYRuwussnjclKGFgmeFKHWFJBTBo52OLp+ndKpc1xtGBhKobWFlDqcECKcKCEp0yhRpmVOoW5c46QBm/Vx2uuazcUH9GpLVIs2zXYLv76O47YwDItXnznEyeo4P3v7GvOOT0FtEviKw0hyf/N3nJ3NUxkpkstJNhtdpto+lrQojhe4VDrFw7tzrNfr3Fls0dEGpUCRX60x7dRp3XtI5/QFHEww/RCpRcoWkv7R4ZYoJUIdpFTEtiKGpIjZgMgMrM4odoUvNeXAQwhBSxmksQoqYW7xWBpILBlu5bClTalb4+TaI0aePMblGxV+9Kd/xld/+3XOHhrnre98AxNJd3MJ3/W48JnfonvuZe5v9fClgURgKQgMA0O4SGWiRLpdKx5jFTEp0zAwJZhSYhkSwzCxDCMxdYMgwDSMpJkxe1Ii/KGEIlZtqXIOGVKWhWfJQ6JoiXdqxI77kA+FdYryUJpAh30WLoiINKNEMWYsmkgj6B0sT6fGzy6TMV751FE7wy1dsVN/F+q8RzpQwKfIdEhf0mlNd6LmwK1DG5QiduwXTwocspI2eG3XymYd6bHWHlK9WCCS+CuZsfOT6/F/Q8qMi9Bh/FdcRgxsAhmaRSKKvDU08UpIIWfTXdjidOMvKb/y27y7VkVYmlyvxUhV0TDG8IMCljCw/Bb5ziam0eXDd2/Tvb2EEwQ0ay61hsPIyChSSxy3Q+C1KBqSipFjOj/C8uY2q36ANA3+l1+4wOSxszy6vUZn/j4PVlpUGl0OHR6hND5KdaSMIQ0cT1MeGeX8EzYTjR5r9dtcWVvGdeGS3GDm5lsc6WjWJ16k2VPowEYFDlI6+CoHSaBoCFCS0OQNItNMxywUdrz8c/BkZI1EKpdy4NKRIEQRrVVi2iDDfkaEyqaAImcJXNMm52vk5AyX3/4Rs3eu8ZV/+s/48Hv/M8XeGssf3GbaWGdtuUa3ucXJIzMcdj5ixixRKpd41LJRnRx69TbNY2fpWPnQlxWxqXiOazRGFB9lGRLLMLCNkE0ZBqD9sD+iuAQZM3JU6AKKxUiHnrCs6leJxPb7nxLZzICVECIyN4l2coRmXxifGOYZAkYmnCJhaQOzI/6qbyErOybRU9nHdOZZSN02MTCIuJTooewgHwC0DsSoEhahY+2XOrczXckwoyxtoO77nJKb/vtF5qZh4BJfk7HjMUJprcOl89B0DCdK7LwF+uJRshQ6MfEiQchqFIFKV0F2jKcm5shKKKSKJo3USCWRSLQIUMJHaIklJL4IwnqYBipwMM5c4PJf/C1nm23e+NI/4WZQxV94QO/732J64jhtPYJBl0J3DTyP6/duMd9qcvHsCxQCB7H2ASMFg+nxMdpdh1qzRk4a5KWBrz1+cPkWLd/BEzmenZpkY76JpeocOfwE79y+w+pWg8mqjbZNZoTNew9ucvrSUU5dfJHmRgu32+TDm4/YaDU5lMuhcoKclHj1dV7+6u9yee4e9txthG9y98EdTlw6T+fSF/G0wEehpUTr6LQGRUZCVMqSsyZODFI6dVwLrTFNyYTnUrfyGFHEvBE6faLg03CMJHlGNj5kdPkm1ae/yOboNEqPsVEqcPWdXzD36DqXZhXNtft0moLLb9/mjS9/ge2tNa5cu87aRoMLjssXvvpV5px5fvLj79LcbjF6/L+hp6oEwg8ZjwzlTUqJQIbO8ggcbMPAjFb4YialCNBaRq6AKCAh8iOFXaAh8324ACGQfaZVRuOmwhsGoso4oFRjxKYepCAVPSNFBPwiQBLuaNA6nuH9lktazMBCVsK2MnNisH7ZSRsDaTzvhk3qoRO9Px1o1a/v2IbMKla/61fs8EuRuQpkGtz/fcpg+mOlBu/KfqG1io7MIHGKxjllLYm4bjscsJn2ZT/HC3Hp3aHPrC+sYBBsRcyiBKYKiLgUSoCBCSJ00QamSaHnMrN5E/fIUe50AnpOD/XBVV6rjHHenKAnJZ1Dh6iaDjrYwm2vcW1phTubdUxLMDJSRR46jpAFRmtdglyOvNdkffkhBh6WUqEQauiiAYktAvJWkQebHlcevE3be5Plbo9AQ67b4VHP59iGQSFweLB8g7P1aV7+zGf4zt+9yVsPF9F+j7JhYZsG2spjOB023/0xL0xNMGd7vHPzKq3FZWrdDarnnsO1KpgqZJFaKAjSA9uUVsnqVrzUlvRjZqZIGftVNFXbZCpf4p6bI6cU0jCRRghSlhTQrjNbXyJ3+gz1ylNs3L6H+Pb/wOGnP8sv7vVYuvI9DpV6XDg0wqnjsyxsKb771k0CXzH+cJvffuNLbNZa/Pyj2zzYsvGnX+bJS2P81n/0ZX78k6sot45ZGA0BFxBCIg0wRLiaZ0qBJQWmNCK/kEDrAKVF6HtCgJQRKMQuglApKg1S6xBw4v6IASsrmYncRxIdAXS84T5cEDBCkBLZleu0b+OVVkMItCkjUzxk+TqafWqQPem0zJ20aWAyDaaYtQm962192LGXobRXLMvI4bP6c//l/22Ha2eHUZax+wZzi5114bW0wf15JnwxAoK0hPT5uDtlcnZSvMKjlBEeWyLzaKEwZJxHuGox2E3pxuVosI3UUdnfVJ3UNQ3UI3FsijhYRgeIALBMcvUax8ZdVvUUXU8ipYvddDm5/TaLZz5Px/PRf/J/5cL5o6x0FNbq+4xYkrU1B21oThwbYXJsAsw8wqwycXiEtfVtFh+uUZ09Rrdep3n6ea6vdHDX16mUTEZrt1lZvM3d9S6+kFgaTLvIcrtOO3DJAUetAiUh6AQ+XSBAg/IZLZYpWzlKlmC8YBA4HsIoc+zQJNcf3mGxpTCVg5ImQkosQzFasBgxbE4cP85rf/Cf4dYV99/5LoULZ3h0/Dm2gyraN/BNH+1bKOGjVECgfJRKgUrHsUvRUSrhIka4WSXclK5AaiYaLTzbp2FNYssAZOh3MSyFpSxsFO2//tdcGM9TeflZ/Pkud977Du+ubPCZS0/z1PkTOPc+YGFjjctzG7Rdi7wUHJupMlsaZXZ6iqlRi//uu2/S7iguTk7w+7/zDMfPn6CeO8S1ez1uHn6Zbi9AKg9paqTWkf9HRiaXxDJNjCg+QymFH/mCgmhFVMVATQh2mtAA8BV4WuMFAZ4fpIxTR7CVsbFipWxIwj6KzLtk21liIOjEUkxmXQwG0U2B0mHQqQKtQhhWxP6reGTCOidxlINzlr7pn8yP/rkmkjkzGDgUM2iAn/zL/y21xdtDYW9/H9UAoPSZdkNesRvHNCVIGdY2W63BTEk5/5DiQ1swpNwaDAJAogiQgSCPw8tTJje7irWuSS7wyUlNmwLICGgQfQZ1skcJkEJH+wsjMErYWRono+Oldh3b2ilDS/bgCR2aOcrD/Nlf8NzFi3RPvczdRp7G5iJLP/ompw8f47o6yp3tDis//D6f/dJX+Or/7v/Ez7/9PR7e/Tab7TaPNttMj9ZwfQfb0zx/4RAv/OaXmDhzCePIM1x75wPW1rZxWw6mUOTNHIIC2hMcnjnOVq3G555/ghNnTvDf/8Vf4WxvYQlJI3DZilecCD1llmHgBC6O08Uv5PE9Qdky0X6ND+5s0nB9dEDkCNfkLM1zJ8f44nNHWHCKvP2Le5S//W+QxTHe/egDntpaRNxZZeaFl+iUpwi2awSuR2d0hh52FCg5cCKkgDjYMjRbDKQAyxAIYWBoQZlVtkszFDGwpEJogY2iqAUqD0qWqTz7Btf+4n8k+OAjtO6yqgSzU0eZxKe1MMfYyc/yzvW/5NpGmxPFAi+dOY4uWPScLtduXeGzF4/y3/z+03zryho3rz3i7XcCDp+ZpCJdqqMFXi92uNPbZrswg1ZgGmAZIawagmhlLZIDNEKGDmStNL4RBmppdBIOIIQMr8VxZ7Fz25AEEdDtXP8miRgIQUpEDCplY/Hsi0FJpeiUglk0M5PpKzRaarTKmGjRHE6OcNnTPsvM39h1MgBcg6uWcW31Xtlm0p5A1W+9Zs2jFA+1imI2GOaj6kefQYd8ko+GkBKHAisTe06hhQFahruvDYmhPSSCwPcgMAk++hljZ9r89hNP8G1xEef+I14bWea90S+y4RuAC8lxMLHNlmFVAuI9aym9joVJhM8Sx9xohA6BUgiQqoCSDkJIlHQwfIEIAtzlRWp+k8VffsDMiSfpXv8QZ7SMenib0/4iM6fzBP4pVA9u3GkwfvRpnjj5iPeuvctWq0un4zFtKTDz/PLKHG7xXZ753Nf4xr/9ExYeLTL6/OcJ3C55LQiEpGOU6GmbiYlpimNT5A2DWz//IUdEgGnbuK7C0QF1NKbWjEgwLRPtg9MLMISg3urhWgZeTodmNWBaeWzloFToGBYC5jc6fHCvxRd+//eZX/dobd6nuT1Pw+2wsPAAa/4RF3JLuKLM/Ic3yT/1Ar3PfB1TRSBlGpHgkwRaxnJhCIkhDUyhMYQPFMj5DYq2xXbOIO97GNpEmBJ5433U/beozByicuIpHjZ9Vp0utWYPP2dx8cx5et0ul+/eo1tvsea8Tc/vUBYmgfI5dX6ap3/rd7h1+SHf+uu/4Dvv3uaZk6N89bVXWFpq8XCxwfKdh8wekiy8fQfMCm2rwMTn/xlt8ggdYAgwRbxgkhFtEZpyUoMyBFIa4Hr4MpRhqUTIaA0DrYJI5kJ/kSC+LlAR40llNjI7oxCI2F4Q0YyPw0KV0kkEfHbKxauB8WdDyHDeyTAIVUpAhyESsYIPV3FlCn5D5/YQOxOx47/k3uxEi77ba30M9mNUCbNQKchkctRaJ3ZyHPQYVyPZl5SNxRjgiP2uCYlEYcR7srSF0D2UESANG9p1JpeuM12UVEqKUy+8xrd/eYv1G9/mQbPI1P0bvPHSGzwSTfzlO1wYn2VbXkBrK3QRCIWQcQhC5HgnA146gmSdxgCHnRtOWkMQruJ4Es+0sVRARW/gUqL0wS8Qzz7NtlllY3WBhdvzPGUcoyIk3avf59xUhZlTz7Ly6CHTh0c5/IXnsMxRPnj/Fre++adUCj1ee/IUR3PPcfnhfa6s1ygjOawDpDBZvr/IpecX+F/83vP8m3/XZmFlkbFcAafZpr7l4G6sIwyD+tY6Z8+cp9dYo9ZokTdzSO3gyzACuhqEUe2HxycQQrC0uYUkjD7WhoHvB/hak7ck1XIBKXNseS5eoDC1xtCCZqC59aBG8S//mi+8copv/c0crUaDJysWowgwbdrLS1AeoTszi3zpqwhpkTeyjDbW3FHkuhBpvI8AUxgYQhMYEpY28Sp5bGViKh1JrKb41EV6mwvcfucXuDfucmd1kydnTP7gS89y617AzY/u8NHqGjY+trRQpkm5YmF1LWypuXp1gXu3/z/UHFiu9fDcgNqtLX7ngsvR40eoLd6jt7ZBW5tMlxTLQrLhFhg1bUylMYWBRmMID09LhDAIVIDUILVASY00CwjAXLhG49pVCm+8QY8qQpmYpo+nFcIQSFTYNhmf1gA+MjLPQ2YVb6kM3fcSI2FG4Y8kiDMyN1Vm2kVQEAadRkiVnFgSWxtCgFbJSmoYFyiSldkYYIbhya5sS8TZRmaozLC+fWOw+tOBItPTLhFRI+NaKEwZrWYk9DBmSrE5JDIBbEPbkgBCuNphYhoeqAaoPJYhGFv8kMPND5HtOpPbkJ8ZZ7pdZuzGT7m7vc1N02Vls8ap7nd58rlTNDs2cmObUjmgKQVCZNkaJJuFdeoLEEKEwXwZZ2e8Vm5IE7G2yuy9nzB6eppO/git8iy9t3/Eam2T4oOPuGA16Uw9hXf5O4yPFrGqMzz/xc9x94PL0K3j1HucOHwI3/Npb+XI2YrxSpG31u8jVZfK4QqHTh/nXKHEiriL5zmsOw5V34fNFm/+6Bf0Cje5cX8FzAKV2Wma6ytYuQpWZwMVONSbmtr96xh+G2WYaKUo5S0s7VPK52l2etTbXbbaHYLAD529hKavNMIYpOpIlaJt4fbadJt1gkARAEEQYMsclpBYVkB9dYkx4yyvvvxZHr75E8ZMA9M2keUi9UDQzk8z/pWv0zbGsYRASI2p03PHQuXR/3e8WhX6/nLY2iXo1fFnZjCkoKDCVVTHVyijSPmL/5i7j1ZYXbjGsUPHmTl9hua9R0xYZbrCJW9ZBEHIBv7p6+d55rmL/PG/+wmL6zXefrRIgMQNHISRo2gWMYsWqufxu7/xBT78QYfaco3lxW3MyUmOXXqa6sg5OtIgJyQEHoEwCBTkAGfuGvaxE7i6AFJRVB6FrQfcv/WQzk+/yckXXkSVSrg9C9FYwLvxEearn8fTNlKrcOElAiolBUIJZKBBhD6uWPlnjec4oj0EqsjfxECoT5J0FCERXjekTkxuSViOMASBJlo4l4n5GMdECRFFsvflGs3jAYKV6P9onoEITcvMa7GyvGc/6+9gq34igSYE6Z4hQezIkwlQxf6cpCFaJ1M/cZQn9nTsQwq/10qhHzxicv0yvV6bni4iciN0Wlvc2LzOZ37r93jqxVe4d3+N//5f/Rv82hLHDleZKZoEgcVyrU1lJWDq0EWefv1lbryzQas4FR4AF+2IzCgHIHRwSq3QUqCUDI8xiVY2LQ3CzKG1IDc7zfaDKm/9yZ/w5OFppg6dpVVzGd28hzVR5sShSYzrP+PkTI7S7GfITZ3BoYJplqhM5ZmaPozbdjnz6sv8/Ic/Zaa4gjDyTB45x6PVR3S8PLpQ5czFKc588auYpTH+9s/+HWtXf84RAmpz2xjTTSraQXXqGLUWs6ag3u4h8fFVQIUuvXodw7IJkPS6DngOz54+Sr3VpNMFJS3ajkshb2Ph0/MVSgdULYuZ8SrVYh7btlhb6SaOX60VuZyF6zq4OYN6r8fkiMXVy1c4eelJmudOsXF3mVPnzuBJE3+1QUNWyZWPYLkNkDYmEil0uHAhYtmKJ0ocrBiaG4GGQCqstU2sco6ulJR8l96Nj5iZylO99Cw37q7z4x/9HHtzkdmjR5k+dIpfXr2Bu75Ix+hSGRuhZLs0egrLMFl6tMn83I9Z3azjeNE56JbAMnOM5U1+6/WnefFrX+Oj96+Tl/DCay9w5cc/4/biBn7d4bxxD+dECWv2GZTjoKVAag9hCrylLYKrP2P22CTbnoeWFYLr1zHvfYcnZ8dYPTXN8ddeYs4cofPoHp2/+n8ye+4IyvwKrhtOZ6Gi7S0CpApXApUIWVAYhxf7e8PZrSI0ypp6sekXm1LZ7WehyKtkM7RQWfdHCJA6YmQCFe0iEEkeMajIaFFA9yFMXE486aM27TjtLlwJ7t9krskuFuyWDnYeFXGD0o2OcfWiKibfhZHGMapnoJUs6qYgFXe2iAAjPzvJ2pLGvXud2elJFlYclmsbTBgBt3/wU3K+5s5aj1uP5qnYDsfzkumRUTxRoBtI3JbAqB7DHj3GVG+OtXK0LQEjteN1OjimDs1OFfQo4oO28QNJoAWGKajOX6F49gxbjLI9exGFZqu2xoWzZyhbebRVJj95DNuaYvLwNsKxcHwXI/AIVpcoWJJuR7Gyvoll5bl+dZ7r1x7gzzSYOvIsz146y4Uzx5AqYLPZpTomEY06rY0uz188w1/d/YBNr8tYp82LZ5/iwrPHefMHP2VcaTqei+gGmEJStE0MFdBqK7R0Q/PJMBDKptXsUjQNxop5Au0yMZLj1MlDLC7XufFwESHA1IqCITC1T6fZQ/l+uM1CQ840KeVyBIFLoAJy+RwtqXjr5gILW4rPfOFV3n+4gLu2zUuvPc+th+9SeO4kCE3OzPeZNEZWo2ZjQ0S62chQGpRLb22N/NnDlLRBr5BnZPIQK9//t1hNH3OzxdHuHLmTx+i6Pd7++Y9od2qU80X+8esvcu6p8/zk3fvcvXWHza01vv9wjW3lYWvBEStHPm/S9l2Ur7CUSclZZ/PO+6zfX2Xulx9w4dIUz/3eV9j+u3ep17aouYIjzzxHx+qhAwO352EaCmUarNy8T+HhQza/8eesri/jF4+TD7rceXCDM91jTBenWPnZBwSFB0xsXGGltszZI6/S9GOnd8STgnCRw4tDb2J7I/IlhYAjE19wDFYqIgPpthsZkYeIecWmWQxw0RYkHc1nIzHLRDwUobWho28Sihbd08eWSCyPFLD6Q3pSZiCiavS7jzKfdsWhfZ3phohjNFKAIkZUIRPnm0Yl4fExSPUdcdJHGTXxknTcMK0UIvBpFcrIl79OYWuZuaXb3O66PDk9xb/40ivcf7TGrevX+Nm1O2y4PXztYzUMJtZ7XHzhSRxjFNXVnHrpde6/dZvJ7gPG3MOs2XboSIw6NVQCYfCdMEJtZjpdrJ//HSdHPSpPPMNW4QirLUH7h3/OU97zHD/8NK2t9/jiK8eolKepOR2OPPcitfsWnu/TWf6AvOjS1TYqV6DrO5RLJUAi80UMGdBu1mnMz3O40qKx1aUw3sKy8tiGwMfECzSBD3pjlVatxfT0CJcuXWD+wTyN2iZ3Hqxz9qkzOL6iWKxQ26iTkwpDBOhAkTcMsHM0fZdCwUQHLvWeQ2Olx7mJUaaKVZ68dJza9jIb8/P4PUHRCMM9bMOiVmvTkeEOOtdVGKbE9gOUKbBsE+36FKWk5zrca7UIXJOV+kO0Vvzuf/xHvPm9n7Iyfxt7ZhqOn4KIKRFNuvhU0MTXEccEIRIFEiiNVi5ms4Fub7LyvQ8R7SYdo8IEml5tk7f/7s9pOR62pXm0rGh323TbNdCS0YJFa32Jb/6HK8xtSbQK8JRPPXDposhh4WoPmc9heSaq0wPb5CfX5vGvPWSj4VLEpKy2aQuP3/0v/jkffPct9OwFTq3cwmvXaBZnuLHdonjhc6zUPR7cu8Z0T7Lw3oeYtkXp+AiLtQaLHZfclosYLfBoaY5D3irHjlQxXnuSs2eOcN1t0SpMoV2PQPdQUqB8iSkcgq0Gnm1BvhLFOkXMKAYBoiAGHb/dTNEfvKkyDuyoxyPbTYmQXYVmtiAQIIPwvQThXA1ZVRg/nfUkh7+F1Jnpq/tjDxM3S8rmwpXQgVipLIHS/cGmw9LeQCXANo2kQTGKp9Qv+luFwBNEr1wKC4+iXgeN5awxG6Gr1gFaB+Fnt0vtB3+Ls7JBtZDnqJHj/vIyf/x3P0PlC5jFcbrdTbxAYeVsHASrLZfxR4uceOkYj1amubE2jtz+iHxzkQv2+7hHXqUTSLRB6DCMzNTQF6IwdIBZGCEoTfDgnW8ir1zn2FMv85U3vsLKF5+jsXKL0XaNczM2fvFpjGaTnBwlV6xy6ORptmt1fMfF13m0AaY2wNMszz2i19pmcuoQY2MjNEQDoRULy/cZqYxy8cnnWZi/i1IekKe1tsD8nTlGZo8ye/oMwmtx4Zmnub+6TW9zk06rB84G+aJNU5owNoVsbBF02+hA4QmJJiBnS84dOUyxWWe7vYgbmDzcbHJy3Gbj0UMMWyGFiVYelhFuCvOVR6VYIieh0emF4xv4FCwTkbPo+X6odYVBs+ez3XGpSIHI5fhgscbUL+/zta/+Jk7BxG8ZbI/M4Pfc8BQDKZNQkVS4U80eTpzU9NAYGO0m5RNH2Jy/SX79DiNWiQeNOhu1OjnD4tD4ON2gx4OlJcYKFSZGR2g2OrS7XR5uSNyOgeq1WXPa5JBMC4mnDGxTUs4bKBRBoKkUC/Q8l4VWgLQNaq5GmD5aBOiFFR7+3bd4/stfxN3osPHeX/Hg1jY1a4TJZ16lVF/h/bcfcMpu4hsBwfgIh86+FMbKtTyOHHuCDafH/JWPuHT6DMuP6jR8nze+8gLbH7xPzphn6sTzdMoF/I0VAruAb4+R++U3kKtzdH77n1NTBVAGsQMlnuMRb4qCnjN7UIniriKAiL+Lo+STvie2fsInJSIyy2LwUNH+vOgjhPsEE3IUOayylYoNz8Tmi+MiE1WUvTmpUxyjuJfxty+jsoyoyMhxlxxXosPVQKVF6FuKgSapjEwaiNZ9aJntMKUFBgY2ATNBne7mGqo3zwsvnaS3tIDpt3Enx/hwcRtbBsxOzSDtHHhtRgp5nKDDfKPD2PIyE48WufTEYa782b+iYswxPu5SqN3lUmGM25OXaGoTrcOTKKXQSG2AATntYXbqdGobFCxQ/hadtbu428+w3jBpNzxKlS5za9DRPcaLeSaqAZ3FOaxclbINLWGh3Tz1lfuMjU9QqI7S8Vo0Nua4fe8jPBnw9KULnDz+JOv3LK7euYeR+3POnL9AV+XI5338luCHP73GF2SP8kyAPPQsrY06te06vu/xRCXH0dkx2l5Aa2OT9Y7HtG1gRIcnSdOk67hoBMtr66y1OliBxJcKH+gELhWjyEi1iq8V260OUmuQErtgU61W6NTqyRhrCR4aVwgajsvFsTGWGk1WWx3GDAtLSuychev1uPXwF+SKLaqXXsPXEsvV+MJGaicjpFG0eiScIqN1w6vhqqzh+3itGuLEUxz70h/R+Mb/g3vLi/Q8ievDZKlI02lxe2sbgUnXdcO4Iinw/YAHKzVsO0fdc7AwyZkCy5Jsdx3ypuT8kXHOnDvDzUdbPLx9D1sqpDTpOA6GDDByee7Xu1Qcj+Vuh83NJTrbCstzWe8aLDdbrPz0b/l6/g4jC1uMW5IlZ5tTl56hZZnUNzYYmz3F1uoj/IJk4swlNlYeMr9ew/e30Z2/pFLJUR6bprx2l/HpcVY2l/FGLlC/eZP82h146Us41RmUaxCeSJqd4lFPRY6j+Mz60NGtiGdhzHTCiRk/qTNzMF04MqURbgGL7bkBghGCWew6CTXLUGDROqpDCnJEz8QhVpCaVzGT+sTO9OQcHUKbVgsZBqOpcJOpTihgGkmVVi5T/8QnFV8L/xZK4amA1s+/TWnjMnPrTSzb5dDJM0w9fYxDOYtWc4Mzx0/zy7UmRr5Mzs6Rd1tYBhRsm9/6wmu4248w1TrbD9+jFCxh503Wl2sU802qzk94qrvC4uwXWcoVyHkunmEgfIm6f5viylu0b1xjRLewhIXjB2wtzvPmv/vX3FtZxzcMDp85xvFjZ1nbrDN28jS2LNBcfUSj3mB1/j4nTpzAtpoURcCDjz5kerpKvlomXxzh+vw8D2tNpianMGdc6tLk9voGnfc6rKzUEF6Pw4fH8GWVuXaba7cfkJM9/BWXrjBptpsUDIOLT17kw/l1lruKS8cOEawtUDBztB1FoSAoVQoIKel2HTZbHXwzh2E6PDkzxmK9y6Nak22nR36rTrlYxPMNbCko5Gxs26TebNLt9FBKYUkDMGhIg4e1BqPS5t72NvWOQ0VYVGybgpCIwOPwaInqRJkPV5tcOu9x7sxJHtz9AHt8hkZhHKUNZHQOjop274eO2UjzRr6S8IgThfY1wnFQ0sfRHlvtcOHG81wKpqJSABebc2fOUqs1WF1bpdNxsQ2Dlu/TC3wKnodQPrYQ2CJH0cjTkxopBW2nx9yDeyzMNzCkIGda9DR4SjNWynN4pEKjUcewBSibzdwFJp8d4+5bv2BLSLqWZLJicefmA6Tr8eHtOoYBZ5wubm+ZQ0eP0m64SCUZGZ+hsbHO+tw9tKe4cHKGUycmyQU+I5OHUSMzdNsBrs7x3g+/zSG3TnOswuT5J2gqM5x5EkwdnTKa9FUM8OE8DJ3hKjoptw85iM9ESz5mDJ3Y0R7ogHj/ooztOpEBpcj9kxieWXTpyzxTcl9dBvEgomaiX1ntlg7kTA99ayE4hYdthfaxivZRJiiZASqdbA7u75Dw75CZEdncwlDYM7M0l3Ns+2tYgck337xFQfq8eHiUz7zxVV5//iTlW1d4936HnJ2jaOcIhIHruayvLjI5UqZTa+Kvr2HbOXRHIBwXKRWBDsivXOVcp8GxmePkD5/iPXeaAIfO+kPW3v4ZPc9npZhDOC0mLZu6q1ieX8LzPCZHCizeeYC13eXo+aeob22y0jYwa/fIjc1id2p8968v8+ILp7B8i3fm71NZ9Xjh/ElGDz3F4rVrVAtlttouM45Ls6cx8gU22x7NpRplo8OZZ55gbr1DVwiurLdYbNwnX6jjGQrfU1h2nptLXbyJs7z89Vc5evY01fffZP3DnyONHrYhOTI1xZ3WPL1eD7OUR6OoFEMnewGfsgStoNbqsNloEQBlO0chl8PrdekFAS4aW0ryhknT89l0HQoYCOWz2taMWwaHSjamaSEDTc9xED1JTozyaLXG5KN1njj9JLK+wdpb3+DYK2/QO/4CdW1FilolSioK1YlOQCDal6sQngfKQ0uJXRyjUBhHd1dwLUFO5BgvmGgp2HKaBEZAI2/T7XRRSuEEAT2tQXuMmSaeUmy6Duu+g6UE1UKRre0OK8sNhDY5NFPh9MnTvHf1CkXbYKycw+l1kJaNaeaRRoHnzs7SqNXo5CfwizZFKdnYXuTa3TXMos2mA47ukLtylUMnj+A7HR49WOTwiXP4fkB7fR5dqHLu9DG+8tQoF164wPb8Bo+uzXH52lXW6i5ut8ls0eA3XjyDOHaextRh1t2QzXpShu9rBNIA5FDZBwqUCJIVuowBGP2RgloGJQbMwMhjpaLdFTKc9SqmZRGwCBUztnQZLSpiIPWXNUiXEiqT4tSeIAX7AlXY3NAvFSRAFRN5QUweQ9BRse0afZUczxoJZoLkMasiiILaAgrnniEnDfQP/g3NXoMzo3nOl6vk0dx6sMLGVpvJ0SLnzxxifaOG43XwtUHXF/zovVuYtslUweTU5AR+q0lOQyln0XYlvm4zPako5lc4piUbWwaj49PUgxLTn/0Ntls11u5e5u7KAuOGw6EjZU5MHKU0P8dqr0XJHmG9KanPvUcxDyPHLvHWWz/A78zz+mtfQY6Pce2qy9i9OabGDuEYkjOjVTob21xeeItLJ2dZm1vnxtw8joarN+9jmyaGNFitN3BLJh9cu827d5fIB5IegqWuJtfdplowOXXsMK2uj3npDeSxp3ElPOoKHs53efX1L9J5eBW9vcK9e3M4PZdqMYddyqGFxMsbrK7XKeTzTOcCdM5i0XXQAnL5HMoPaHZajJaLGIaB2eqiXA+lFflCDqOjmC6XWaxtozGYnhzl6FiJpdUtWl0PgUGr57O6tEHRFXQfXmP9vU3Wbzxi5f48cuvfk39uGf3S7yG0hRYKEdkYUpMIfbj/TyCEhfaaCFugggof/finVLZXOTVZob1Sp9l1aXsBtvSxNTjtNq1WC9MI99k9d/oYN5e3qHeaBCKgrRTI8CC8YiHH1Pgo7WYNo2BiCYPxiSkeLs4xXs5h6gBpaBodhRAWtYbL2cOHOfaFr7H54BFnOx63Vzw2NzdpbazS0R5WDyxLs970+dDZ4H6zxtGpKcrVEcy8TWN1g2Iux/jp8xybKfPRW9/l8ltXEQrWOm3mWl08aTFdKDGer3Ln3jrnDl9ipvGAz9hV7tZNVqZPEwiBHQShnziyclTo/glDGAChBAbx/Mw4s3V84nsmrCCy7sKAbImhXCZEQKkgWejlwQhAmRAHSYdeKhAGSslQ4WTjDxJGFK/d9uPIUEDKrAB+QtNPEwThKTlBRDOTZVDdH4me1rffYaYzxmzqToviP+ITdwLomRabfomeA184Pcnv/OZr2PlJttYarC/N0XMFsvoSX/ydL/DgXo1GewnfcSkYJk1XYHmae90OTiAZreQQPYeJnKJSLiACn0a3h1fbIFc2sBsNzm77PDz5At3CGIVLr8L2JqOB5Pl8h0vTk0yeO8PPSxNcf+sHfP5Mldf++X/Mn//L/ze3rnzIZytlLh7Ns1GbZmvxAfbkIV574nnsxn1urDco+D6HRqd571GNWneDF87N8vPWQ56fHqWtNFPHz6LbXba2lpiwDT7//ElWvDKOXsWS4AUe5XKRSmGUZq3GmKxw/o3P0pk8TduVoAN012H8zHk6syPYuQKd97/HocMW79+eJ680JW2gLINCZYSOA063Sz6Xo0sUFKg0hudTyJkcPTLN6GiFrXabcrXK7QeP0NJg1JBUJaw5HepoZvMCtKJW66D89ETNjhBIT5PPGYjyCOWTL5Of38QdPYT9wivI808ihAFahTHV0RJwdGBq9B4AgRYe2oSccimOjPPOex+y9uZ/wLe2mK6MhexNQMfxWe10ETkTN9DkpYmrFMoQWLiYCCwhqdo5ZsdzHJmZYm1hC99x8dpNpICx6THKlQoPFlbodduMFHIcnZlE+4qVlVVMS2OYJs7KIjf+7E84drzM8WKHe0ZAs97A9T2kISiWLEZGiszdblPzPLQnKB8+z8ixS9RrNaS1hTl1iolDh9mcew/ldNGOh+EbjBfzuJaHZxTZskv8ZGGJN86cpV1rsHHnGxSnx5joaMbk59habrMycZLc0TP4ESsN/VQiOqheoqQiDivQkakTGi4RqGnSE6+i9Q2tJWiDUrPGzLU/5tBslUPPfp33GtVwUYGIjEgTJWwCPzy+KDwpVKVzPRsRkKBHPyrF+2sThBggXnulPYFKa/Aj51igQpoZU84EpOK4g9RTlhSd+q4yLCxiVzrqpJBqmjQWtll++9tUi5KmX+Vv//IX5OwS08fOcPzocQIhcPQozbbDzKTB/EqeZrcT7h43wp3rQaBZ7nj4dg7dC9jstZl0PA6X8xiFHLYp8Bt1rPEiUxN1Nm69TeH8y4iSoGQorJMnWVy6wpPHL7J09z6zBYsgJ7m/us7k+z/hteeP8tZbK2ysPGTmxGkaQZHFlRWOyEd06wFbLZd7zW2O2TaFZz+L07vC2YZmbbtDwSiRO/kkhWc+R9keob64SnV7GXH9LYLCKA+3fU6cO4WdM+ht1ZmeOsZGz6RydoIjl55HHz9PXQO+DwqMfIHCs6/SzpmUxk5x/zvf41C+zfhYhXqtiesHbG03MIpdDMMmUAqzVEL7krztgR9gWgY5W1K2JNppUDEla2vrqCDAyFkY+BwtF9hsdAkUjBTznB0pc315k7JhkLMEPQWr3Ta+bVBSJitbE7zvXWL6acUTr1XxqjN0hcRSXQzDTGRDEAY1ijiGShgoYWMZJp3tBZYf3GLjxl1suYUvBC3Hx5KaimmSs3LMOw06nR6OF4RR2UFAR2t+/mCVTqCYMSSzo2VOHhun63iE54iDQDE7M8rkkcP84JfXmawWKKscSgmWljfodBzcIFwRdU2Djurx3ttvc3fjCRZzUyxsL6O6W5hSYBtFqqbE9HoY0QKTo31W1hawp09RyBk0/C4T0zNsr9xFz9+ATpcRYdHA50vPnOKNmTF+ca3B23OrfPWZ56hIl5+++TOePXOSsiqR1w95+I1/jZUb59A/+9+zrsMJLrTCjw8oVOF2GKHDM9izr7dRKjz7HXT0HkjQESMKX2iiOWn6dL/317iNBe7M+TxZGOXlF/+Qny8G5CwL07Cwm+uU7rxL98IzbOSOovEQmGjtRZaUzIytiE5wTVz5sREV1StdXonv2Gk+PgZQQeQ2iBBZaY3KHg6elksaXTpokKYxIHFD0uaA5yo6t6/Q+uhnHMr5NF2Dm48WUEGXimXwvNPA6k5y9PnXcQpleqpAbcOkZFjUIvorAD/wUYbJSquJ4ynyOsAyQQQCqRVidRNRtpG6RLnic/7k0xTFQzaW3qI8MUI752OU8/zb+RXem/9zLlqa//S1I/xvvnCKf//2Ip3v/pQ/+MozfPm3X2Nps8XF40dY/MV17i0scGrmKMu1dS4cP4IsH6G4XaM9fYmzv/9ZjOX7LF15jwtffh3z4ktsCxMv8LGPnUZMnWJ7Y5XyoUuce+IEt//mjxE5mH3uJconnqBUHIOiTVuI8KBIIsUgJAQuyhMIKbly8wEGPgubHbqBYrRio6ViZrKKlgLXB7NSoKlcNlouthBIU6CVj6ktjMCjYFssrm3T6/bwlcZxXAoTVcZzRa412/jA7VqbnF2kUiqhWj08LOq9NraUiEDR0A4ba+/R+zuH1z97htzEMRwnfN28bZnJ2UnxwYYiiXyWIBW602bl3XfYvn6FtdVlur7HRKlEr9vkg7UN2h4YwqHcDQi8gG7g4CuBwgcpEFphRJM4l7ORBjx4uE6j1UFaFgVTYAuJbeSZezCP7nTY7nUoGAIVKCwjj1KaguWDD7ZVIX/8HLMvfo1NUaXx9vegvUmgHGwpCZTLRlPjKA9Ph476QGnWFuc5+rykUD1CcWuV7uJN6g+v0am3sJRmSbl4luT0cp1NnacmbN64dIaGq7nSsjl5/jU67Ydce/fnnHzyJHVtYp55nqAyinAix44OX9igtREx0tS8i+dZfEqD0EEyM7UWhGcSSQwpOd26zcVCm7dWruLZIJTBg7c+5MLsM/zGsZPUV5dYv7nA/C9/QLGoOPrERVzRpa1zaO3ih/ZjuEgSz/745TWJJSX63iSUDVMQQyBjWNqbUREuJyvC95AljtBs6gMp0uWE6JrI1CS7vUaKAF8pVL2OvT1HpeCgKNFsNLFVl4plcmwsj12S+Nqndm8Oa9THmmpz5lCbtfUelpAYCoQUBJ5LwZbMFguYRAfye5qtwEMYgmrbY7qcw3N9erUN5n75t1iVMpO5IkqbtH2Nsb3I8bEJ1mvrzHuCv7u2yX/0+iT/5PNn+eMfPuIHP3qfV15/iomTx7hx6z7rLYcp26A4PcXRp05SfPaLHJ44itNpsyEslDLxp84y+sWT2HlJywcRaCyMcJleecx+6fdxczb15S2mXv4i44emEKUJum4ohDigJUjpA+ERBkoIUAKhAgwkbSE4+dxruI9+wfLSMoV8jlK+wma9TafTolyuUB3L47Q74LsUiiXKRp6e12NqehzLLvJgfoV6q4sfhGOkAw2OYr6zjROEoSeOB7fWNzlRKDKaN1A6oKRsClhIDNZdDx1sYq5/yI0rXU56LsWjl1C5cQwCDBFEmjMU0PCV8GCIgEAbiLzJaEViVCRbq13yBAQOFK08wjSwLdjodXFR9LwuxyZHmJmssNIKWF7bpOc4lA2DmXyVasGk1elgaINC3iJnmbS8gAe1Jv5GDQ2URHiSg6fAQlAuasarZSwt2G5oikWD3/jDz5CbvMh3f3QV1dkkqC+hPYee9rFMiZQ2slBGt1YJVICPZtvrsH7/LvlLZTpWBWv5IbWtGh0lKRVGcJDMnjrOHWGwcPk2v/HcEwSmyWZgc/joBI7r8daVdY6agueffIOLsy5buQItM4f0AnqdFn6ujFIBWsrEjaREZL/E/mKdAli4TU1E/kEPIW3k5hre9ff4UX0jfNFsT+CaPiMTOezl9zE6c9y7fJ8HD+ahvc2xky9wUm3gvPM+3dIxnvzSy6xt1vila6EDA7QFIohW+4wUBPoQJQtiGq1lH7x+LKCCdFd2HG0eA05fiu3SuHNi30PGWRa75OJAV8P30WjM2XHKJ/4FevEWD7//75nIaY4USkwWLE6P55A5m67r0WrMU9JN2ksFRrx1XjxS5HuNNtqXGEoSSItiIYfZ64b0Vlp4XoCnFCv1Lk7XwRMBk2WLcRUwNlnErbc5dukF3lka4cqdaxybtBkfHaVSrbC1tYZvGty+3aFsOIggYKmhePTBHSbur+Gc+yxP/mf/R7aufMANSzD1tdfYCgR4FsIMj4EhCI/QkIbE19HxNUYcBKexynl8pZCeojw9AXKGnvLBD435eLN5OLjRvrtwO3t4dIiZ4+H7t3GXblI4WqJZa3Lk1EnaPcHK/BzNXofxYpHaZo2cNcJovkAw4lHIm8iewrQtmttttr069U4HtCAIIsG2LBytsQsFjLpDxYKu79P2fTa6HfJGDoBizmarF5pgxWqJVtNls7aN+egG1aLizOmnaQoX0wK0Ee3+V4l/SkY7GizloQ3N5Gu/ye2bDXz3Hobps9b1QELZhDPlIuO5PM2WTz5vc3y8xNSoTT4HvbqFJ2B6psx4tczWVpd2w0MYDhMTFcrmCGv3HuF4fvjuGq3pCrAjebSsHCoAaQiOjFWQukXLb/L+3/4to+faLN9bgo1FTK0wACUEQhoo02S8nOMpa4zLc+sgTJRWrN/4OZ2Fm0yfOc/95QXqjsfY2BTjxy4SFEaxR8ZobDd46vkZqhMBH9xaQVZOMr++yfb2OtWxUS5OFrnz7ntcXt7AMuHlrbs0F9axTzxJ4+U/QPd6BMpHiHBFNUClZ7pHcY5aheEgfW881hZ5y6b+4A5b7TbtdhfLzNHttDEDF6e9xeb6I775F99manwSD0EuV+HOvdsUKyXOHJ7k0YOrtN7ronoNDp35AkvCwgtctBWGVKR7CeMQlGj1cSCkQadvJf1kQKW1CkMSVARIeghQJUmkDlIBUW0TOzQMltVofHxhIjzNWHMRZ+ktmktzVNtLYBg0uj0a3TYnT5xnqlxhq97CypkEpiB/5CmUC1P332K8bLDe8jB9QdvX2L0uI1Yez/XpBD6+72NIA5B0Pcl2PaAgTaqjgk6zS6Fg02s2ufHRFQ6XLSzlMXPiKHOrderdOT5qaoKGyWefvcC5p0/x5s9/jrXkcH5kmpFTL9MszpJ74XdwRIe2F2AFClcGUSRxvPgg0dGbaMI+ifZOxisu0ZnsSkqs6FVF8epKMoBCRMf6hg4Kv+NRu3ufrYd3aW4s8sIrz/NgeZ3FlTpfPjTBl3/nq1y7eo+5j96n2a6Hr+YyDY6fOIK6c5dCocBWr47jBTQ9zZaryGPiuT0cDRgCR2nGpaQow60vo9JCqPB+rUHL8NWZXhCQMySWZTGeLzJmSvKWxanpAqctn5zfoTs6Ba6PwMMQKtqWFTlXo6hlJSSmMcLl719m7eGHSMOj4QU0Ak2j16VkwKF8Ec9xUX6AlTOptTt0vR5dJ0D5AaOVEtLzWVhcw3M1s9OHOf/Cq/i1+yw9WMISFmOmohlE0UDxCzkj61Npg3bLZdndpqdt2sJmnpOsdadwNt5C+04UaxQqDAOBNCUzUxUCx+DGQh3X9xBSsu27mDqg1/PYdHqIXIHj556lQwF8D9VpURkZoRd4/PXPrzBx7CRe0KOFx8TEDOPlUzxwely/dh2zu8qXn/8sM/lRKD/Cm5jCePfbrHkW1nOfw4v9UDo6cE/rMJwo+p1OT4EUCkPa+PUtdLOBURkn2F6jq20cv0VR2eTNHHMr6zjaxO/10IbNfHMbUfco3r7K5EaJUVNhdg3q64Inxc+YDXo0Dl3gkT5Ex64ikniACIiS1b1+UEp913sj1QGASsTrROGan+i/RuzciwUv9u73bWAOz4vWQqGDMC8hJcH2Ipsffp/8xh0aTptm28Nze1TzJraR58b9BeqjZUarY9gqx8jYaYyR42yrLfKywMzoCBvtBsJ0sA0Dt+ugZI5AKQwpyNsWXqAQQuFpWGx18aIjNbTvMj5aQiL5g+cmKXzhj1ht+9QZ4//1H/4G7fn0AsWNlsvJtU2+cqFC/twhWkGBiVc+x+bMRYKegysD/EChAxNXe8SLnJro8LMMDY+3F8U7oQQRw9ThGUZagtZWFA+jErCLhxRCoM9rl61Hv8B+dJVDR8/ieh6tjQ3OHcrz6tkSE707jLz+Ap6lKc+tsrW6jNNq0q21ENKgXm8xPjGO3fPIYbK8tE5eCnAFnoaWr9C+h+s1OTFaxDZNJibGEEvL2HmLPBJPa1zPw/Y11VwuBK1Wi+lqAd/3mB0tcKQqWP/whxw6fB5n+jit0gSGlJgy3JystQDl4wUG9+894OEv7tJ9+HPywRZbfo+2CnB8h64KyMscqy2fVqCQhqTju/h1TdGyMEWAsExM06DVdhg5dIqTl57jyuUP+WCuRt5V1GttclYBz9fkhU+AxlcqPN1VCrwgoCN8hCqx0fHIVaf47T/6XRa8WTpzN7C8Gi4uOtpmYts2xWKJ2SNTSO3xYHEDrT1A42tNL1BIQ9BortP2NSeOHaY8Nsna/TuUSmMUx2apjo+x/PA+lRPPYU1O095aZiRvks/lWOn06HZ6HD56iGdGL9BYvM2P71zmheeO8+C7/18KXZj6p/8Fi4aCIPRBhYQiBqiYUYXKLzl3ygDblKwsLTBatFleWUA6XXqeoul3EXaBmdPjtE2L4qpP4Lsox8O2QPl5rs6v4M95HC2XGa13Cewcf3X5R0zYBiPVd6m+8ru4x55FYWfENruwFjv6E68ZiRn2yYAq9kulMRgxKoYfRTwLoxMJdLKBWUaH08VRp4oIuHS4m96anSQ/+oc4b/8txr138H3NRLnMF86MMlutEHRdcmNjdHwPoU0cP8/xkzM4G0+wNf8TivY2wiwSuE0MFIYw6Tgudk5gR4eLNXvhu+QMKfCDgHrPo9KSjJUsqGqa9RqBmad85gnOPfsEV376I8bLFVYsE096mJjcWVzm4ojPP3nlPBtHXmVleZutzhLaHEcHASIw8fCiw8Z0EmAWrpLG/j2d7I0yhIy2Pah09RSNFmHkscwMaXxmdnwWtxAaXSpw4Wv/mEc/qTBStrDdTVpui+eOTnJ4egICl1G9xKWZCm/ef0RhxEY3bZY3t3Adn1qjhxaCvJScmRqn027Ta7bwbIOxaolaq0utF7Do+qyv1ymbJkGzwWHTonh0lpX1beo9H0toRgomnueQs0qYhs9oNcfKZpfFjW1mR0rkEZTf+Tu88nEKf/ifhFHvRnjYogpAS8Xdy7dY/u7fYHh1Sn6bhufjKIUTKNpKYUqYLeaw8wazhSlWtjejt6+ESjGftzhz/BiV0VmuvfMuxyYn2G4qmh2HzTvvUus0GTUkBWHixIItQuXgCkHOMLBzNpOjVQ4fO0bxyDnGR6d44bWXCC4/4OrGIjkzT1d2EdJFojEMg5ydY3Njk3q7zvJ2CyFMAuljYyBtE8vOYwZdCvkCX339q2w8ukl36Qajlz6HXSjQWrpDa+EOp196nW6rjfI9GJmlh0ZKhyPTBSYKo1y+fYv1zXVeGp9k9rmvI9VfMe/lcWaeRHtm+Co24UdxjipzqkJ0UmegCWR4VLJh2hgIcr02zbUHtNYeYguXtutydLTIE+fG0AR49YCZfAnDzFEhx5nqYXxf4ro+0yOKs5OSbX8EDj1LV/yCuYcL5D7zB9RPPY1yBclLaDMphqWYzDAYKPBxgUpHq3zpql3Ga5+sgEZHRSSvllLI+Jyq6G6lZRLbIUSoTQMd4GmBY+exL71B+8E9xsuL/Od/+ARPPvs00jrHO9/4Fo3GGpiSYklTshVes8OxCzOsvV9mulSkVPTp9HL42sUXHgrF4UIORxqgHErlEk5gs7mxgVYBrgZh5nHdgFarx0ilTA5Yv7fIVnsEW7apym2mR3Ns1g1mCgbdjsePbm1j5hY5VViia+RY7LRRxbHw1VBa4yuNDkiBR6cbtuNN3EKrZDk+0CBEEIV4hEMY70E0ZbQ6Fh1sl6yniFQR6XKVi1//Q8TtD/Gv/oTpac3Zs2NUZ0q0ega351YIVIlyGbZWG1TGS1xdqhF0u5TtHEIZdL0e9+cfUc3nKZeK1LpdysU8I1KSFwHtdhOBxi6XcC2T49OzuKbGzFm02x7HKwXKuQAlJSiHkWIBu2CirDzL7QAwOfbEk6zdXUVN5rEtE89zsUwJKkAaBp7ncer0DM1Rm7W1Jtr3cAIPaVr0PI8jh49itbvk6SFwaTseSnkcn5lienqShbkFLFPj9No4a4tURgo0lu7wy8V3MHJFSuUS+UCz2drGwsOI2CsCAkPjakXThbZUqGabczT50okq+WNnKeam+MLkZQ69UuDNt0bIOV3cQBFoH9dxqDca+L6DY5r0MMLV3HyBqdFpZs9d5IUL5/ng+9/E1B7raws0Nh8iDEF75Q6FwKPXWMbdXqJx3We55jF1/kVy+dAELbk5RvDZXNnk+OwxvvbcBRr37vHtP/+fOJOXnP38Z/i33/prTjTmaV16Bk6/ilJutCMkXqEP6YFEgcxhyTy5Vpv1D37K9q0fE3Q2EFpQE+C4bV598Qyfe3GKH/xsnoctyaPaMi+98DSGKFEaKXP95hzCM1hZ3iLoFXn2c7/NstPgxPQY6thztE6+guv7CFTmxbLZFO5WSUMVMq/bG3yh4+MAVQxWyeyIX3ujY6+TSlhU+MLDCLQi9A5ZWOxA09GRpjqGNwjM8KREq4QSNuXqGA/vuty99Qsc/x1o1JCW5OjxQziBj+kbNDoFAtUgV6riKYet+jauq+n4Ci08xqTF77x6lJPPTSEZ4Zc/uc+3PphHoTENk47rM7/RQKgcUkrydoNCuUyw8g6WO89IOU+rZTJRPkrgrVGxBVrkmJrJ0eoGrN/4KbPnX2alWGLFtPGdVrL3UWeC7fqdmrF2ifwIkXNTi9D0AML3AaKxDIlphGcE6XgRI+rt2JTWBAjtI8wCrjVGY2mBDaGozjzDw+sGc+s9gvwU9a7P4aMvIZrvst3r8uqXf5cPfvgdPN9l2+kyapu4PmxtNShh4kvJ/GYD4UuMQh4rsJCBomzbIZDmCgReh3LZ4rAyKJlAPhfWKwBD2mzXeqxv93jx1c+x3O1RXm0xUa6Gwb2WAIzwfXZSogKFYeRxuw5mQzHuCVYDRc11wDI4Mj7OZKlMt9vDFjYtz6VLgGUKKnkbp1UH5dNzPDoLm5x64iJHpo9w79pVtrpdvF6PSa3AkxhB+CILX0AhZzMyWmF9YxMTyWgpT7FU4vhMmWq1zJ/+u79mpPImlw7NUppwufj6BebmW2xt+PieT8/vhkesKEUgTIrFUXJdheO2qVamePV3/1NcacFEgbGZ44yt15l/dIfa6jaFUpFLL38Vr+Nyf/EGh4+dRng9VPMhK1fbjE0dx545Qb4yiucGnDo+xUSlwkfXrnPv9n2KosPTn/88U0dP8uS738QuF6ieOstCaKgQxL7keAVMCIRtk/cCCnPv49x6l97SfZxODc91sAwTIVzylsl7t1e4OrfCVjNAWxaub7K2XqPZauIJwdpGg15vm4oNXVmgd1/xv/o//Ffc+PHf4N3f5r7qoZTATLb7JCjSt7CWgguZ0xqSHx8PqOKdPUb0ssMQvGKgCilc/CaMGCGNeELp2DpVfWELWkdvz9UBmCatrToFFSCUzQd3V+h029Q7HUaLeQ6Xc0gUo+MjCHeFd7/5l4xPlygKhxYKYUjIWwjPRWJhl6q8c99jaXUNh4estzTK98KXVGowhcALFFstj0o+YKznszq3RmmshB1YNOvjfP5rfwQdh1+88w10r0HQcXjxq6/z4L1FanPX8Pz3qdZg4tJvsybLBMqLTllUieWX7fOYWcamWzJIWkfvZxOYQpIzQ5CyzWi1JF64yET7huzVRAiJpSUrLqw5gvfXl3j7P2xydOY4J06eY7TiUKmM8Gh5jfev3uHF557l4vlnqRZLfPN738PamEPYJtWSRdt1QQl8zyNQAaa0aHZ7TBg2ba9HySpw9vQUr7xwkgePtrh9d4FjhTxza9s8WqlxeqTAWDWPtBS9dp1Xjpep1O4wPl3i0OhhXKEpeR46byZv68UHJXxQOS7/+GeU9TqPfBc38OkQLkyM9Lq4gY8hfZQpyUkbM1Bo5bG9tUneMjGkYCw/Qh7B2lqbX2zcp4RmolhEGBITRd1p40ZmkB3FD5mmhSkk1cIIF594jjNHS5yesXn/nSvcWq2hNzZoqy5yKcAameClS6PMPyxQq7XIWTae74Jhgm1SKFjkTIO8ncMWBh3DpFAss7KxRf78c1QfPqS2sU5LBciOw4P3vo+VK1BrNHBlePz2zOQsUyWLGws3GcmV2fQDJgqShYf3aZkuR2bHePr0KxTbLbqdLj/91veZUG2O2D5rb/8F25/7F2x7ObTwEIEKXz0vNYZpYa838a7+CLF+k8XaKq1eD89X+IEPBHjKo5jLM7fdZaXXpWTbVCyF7zqsL61hlY7SJUALhWUKxnKSY6OS8coWvbUl6usNpv0m5vYdHpaPUDMrieymp4xmJ0UKZAPffDyg0oSIZ0qBCdELIbOvO4rfyBpHlopkMiU+MnR0PIRKTBmBJo/CMRSGWWDrzvvoYJu1WhfX6aIxKdkW2u9RsAqYMtzGMzFTYv3hz9moweHJAhXToKQlPiBzOXpOQNd3KZ97lge3rrOxuslKu4fQMgIIAYaBH2iaXYe1hsBXLkdGKxwpWDTq28yeOcfRpz/PxqMmlz/4HrlqEd1zuH11juvXr2N7Dras8+ITDkFvgY3ipYj5hEvDRMeYCCmjQ87S8IxwkUEmzFMSgpRhSHKmQdGSmIYO37RL7J+KmVUcwBcqAgRIAzzPpYZgPG9RKo5gBB5bG4ssLT4kJw2EDPA8l+LoLLp8iHrtOrrVxCrYVEaKSAFHzBE2Wl2MtiCvJMo06Hgex6Yn6Kz4LGxtkh/NcbZm8/z5l6ltbPNguctK02HEzJFXCtXVBCpA+AK357Pe3uTIlMCrP6JZFngKRnImnueDH4ZpGKbk3vUVSnMf4rldGl6XvGUyKi0Oj46j2y0CM0DmTBzfp1qpsLVRI5/LY9mSXK6AbeV55rNfYPHuDX5xa4F7a+uM5yxmqhUC32e11SKwTbodhxyhy6Hn9FCr6xQMg1wux4kLT/Jbv/Ect976AetrG1D0sZDcXt+Cdgdvu8XESJGl7QAvCNC+j2FJcsUKxfEqBelROD/D1TsrlEtFDNchKI8wcfoC1Ykp3E7A0lvfZsxwaNZq6MDBbfUoCLACF0+5+HIC1xpBiSb3HlzljRcuEDBNzypQnhhl0tzm9LERyqVp/vh/+CH1ToNJ08ZdU4yfmaRiF9kMNMI1UKaL0JLR1ha6ts3WR5fxVm+AV6fjabqOh5RhuIwUAsswcf2AwA9wfJ+8YdHye1hSUC5W0IUiPbfLs+eO8IUXP4uztolyHRbufcAP/+UiY0dnsQzFve/8T4w+/Rk6F3+PrjaTGMsErCKI2HlE8f6+qgMc8yKwon+GjAEpcvPGoQjJVCTyaaUMwBASbYTHR2gVvpZHyYBA5LGUx8K7b+I9uoypHHqeixNo8njMFnJcOjzDzEgR0wSrkKP7aJEnn30FvzzF5t1fIKXPsWeex2oa1BfuUvZqtF2X92/eotCuU2u5jBRztLsBmgA/2jagtEIIg41ugDYspNGjuFVnTLls+h8iNiTjlSpHinB7boGqlaOz4TFm2qz0fG5udRl//zpTpwJOPTHOVWMSlCJ5qwpEiwoR2Ouwd+K34YZHaQiEFpgCTEOQsyR5K3zrriFjJ3zckzqKVJBRf2sMQ9B1O3huFztXZlpVGTl8CG2NMHv4EE2nycajeZYWFsAUiHyeTd/Dc1o8MW4RUKEX+KjAozoxzWq9Q75YouMFzG83OHJ4iounj2OWyly58YCW12Ot4fC7X36eR0v3eefWAo7SVGyDrgFtDXnPJSdNVroOG9suJ46OUXz2NN2FBeRMFcMyKFg2vghwPYVsuCzeuEtTdWi0HXKBQdPrMFsqIXsdlPax0YxUijTaGq/TplKwyJsFKI5y9jOf4e4H13nv/SvgNag3t1EqwHUUBiM0PI9N10V7LjbRO+6EIFAB5HKMjVQpGBbNG2+yNr7FjGpyabzASTfP+50eKy3BEycuIItFlpoNvGAbtEYa4UF2hmmwuVHD7dQ5+9JLTI3n8VWXu+/9kqd+7x8zfugYtbbD4c98BbPTpX3nQ4LRAtUjs7jbWzg9l5GpQ5ijVdYXljByY4zPuLgrDxlzt7i/usnM7EkW5u6w2VqhsFSmMF4E3aQgw2O0XS3YWJ7n7J2fIE+9wnxQwpESq91l5c2fMeKsYtaW6Lp13EAT+H7kew7dNRqNKU08FeDo8F1QUpq4nhv5VAWe5xG4Lsvzm3y3vsiUVSRvgKdc5uYf4d+3OTFV5ekjVdZtG608tIjfk0OiYPtQKfs5ubg7r9r34Ly8YWJGr602k21E8Ul/6Ys8hRDh22GjmB8RVyAGs+i6UhKlDbZqNRa//5eMrV+lMlKk0SxieC4jOZvpYo7TEzZHRw1mpssh4Nkm2sghS8cpzpykt3STxW7A+Bd/A2lOMX77CttXfkS+Pk99+RHrLR8bQSEwyZmgVBC96loQSIkbaLzAw1Eaicd0xUJZNk6wQd59k5HKSf7RP/09en/67/nc5z7Pd7/9bUyrAP46a9LjzcU2nwuu81R1nPaxL/GQHKDCl3sa4bveZBR/EL73UEcretGhfVG/mIbANiR5EywJpgwDPbXUCZsKV0lTthqIgJJt0dhqYnU2mTp6ko25JgE+Zy6eR6ocuUqVtQcLNJwuea24cvmXzK+sUe2uMFHJYShYWtlgdrxM2TY5NlVhbX2bou9zLJ+j43mUKnmMFY0lJNtrHVaqK9S2brKxVcc0Q2bY9Vwc08LvOUxOlNGBT63tMVEpU9t0cLwcM9vbuIemIF+EwKHjdAgaLlf/4hts3b7B9e01PM/D8wMOFysUFXhBBywwMHG7LnkhcQKP8bESXXGYE88+y7Nf+UfM395k5dEvsQzF8elx1hvt8Ghd26BoVRCtNqYGM5JVSwhKhkFZGBSKNq+++BKLd67zx3/yDaaEwVS5wA3HpHzxVX73/EvozUW6Kwt0a9v40qMX9JDKIJez2Npcp+5BgIGbP8xzf/g7NNbm+cUPvs2j999jdvII1WKReiHP7BtfYX1ighNTEwhD8uCjtzly+AzrK8scmjlBqTjN8pV3oFLk7Jnz3N72yRctVu9cpdHcYtQ2KL/xeR48miPX2yBveIzkcpx74Sy+q1j89p9y+rmbzHzpn3FLXWTh7k8xnTr15iKG28P3oeH08KNtNUr5WFYueuOzRJuSXq8X7vIIfHylKOXy+FaBntNls7aB8LpYQZ5TJ6ocmZ1gtdll0/W4ubjJ2mabC2fOk5s4h6tKIINIkAe4ktLp6U/72XsHBSqJwJYC0wgnkCFEeOZyhEFSxmHy8QbD0KwLaaWIfFsifC0SgsCQ+IHC14rxomDys5/FXZ6hfu8alqcp+R1GTSN8sWOlwAu//TXy5QmWrryP4Tp4eYtg6ya19asE9RWE9vE9Rdu0EeeeYXLqEFz5K2a3HnDn/gZ5adFzeli2Ga6mmRIVhE6kIFr9UX5AEJjMnjrLxS99hps/eJMxS0LNRUx0+d1XzzF9YprVz32dX771U4oUOTQzitvq8MHcVV7Jvc05F2rHv0RT2AnQyOiFBuGLDUKgklpFrEonB5GZhsCK/plGzFrTFRAd96MItUToULcwhcl2rQ7zl5mYKFM4fpzCSBXhhwe2Kb/FWNVmfGSEoOfSE4peZ5v5uQUOTUxSsXocPzaF26zR3KxhC8FkwWSqlOPWpkun7bC2ssna6hp5W9BoNnj/xh3+p3/vo4SPYQlM08AyLcbKOVY2e1xbrzM7O0a5WOGQLXnhfJVyfRPba5L3XdYfzbN16wFTzxxDjU7ysO7ycOM+dS9gulqi6LgUpGbNaTNTyWOogJ4X0G20qeTzFAol7MpRRi+9yNf+6A94tB7g5EdZbfYwczBbKnOknAdp8cwzz/Lh9ZsIHcqrL0L/ZNUweOroBF+8dIgzl0bYtIoY3kUePprDU3Dy0igTapTn/uA/58r7j6j27tHqdljZ3qDleRSLI1imAdrH9wNGpqeo1Ru01teZfrKMGDnE59/4LJtrm/zVf/d/4alnn+f0C0/hlaeYeeEzeB74gebYF09g4zHaWEcZJu3bDyjab6O0z9TYEdbUCs7WKhMjkqkTTzM7VuD9jx6wimbBUVQtmJ4yKVRHOfbyF9me+9c8fOddzgUBo2d/m8WHH2KrLTwpabkuXS88uie0uzSmaaJUqEw1kMsXCbZqmIZFoMJ9mCPjswTWCE67xmSlwExpguPVAsWcRsgRXvzqH/JCYYu1f/VntNpdzGqZZ4/kaPkeD3ogVMJiiH20MV48FkrtB1RCQN4S2KYM39+nQxNECyNxhIVL8Gn4giliB3t4VrZhyGS/n6fCxXalwC6UCGbPM3r8Rbrdv6K0+Zc4JrTcLmhFJ5jlnXcWcfwlpLtFPuhSnTE58dwZilrwaPM+5AQiZyMQ+IFDrzLN9It/QOvDv2Fq22Gz1sD1fAqGJG/lcHw3Ol9HgNRIHb6OqN2DubkFztTOUJ2corUyT3Gki7F0g5nxEo1Wjc0OWGWL4zOj/OzHP2DElwQE1O4ucbb5cz5/9DS/MI7TMgxsYUUmYHRKQAT6YfyUiGLOiFb5BLYhMKXGkpEfMPb3RW/xSffFyegUgPDYGuVpfM/jg/c+4MIrn+Opl17n5s0b/OjHf8fW5hpPPvcsr37l67z1/b/CGhnj7HNfpFGv0XDXeVjzOT41iuebKO1RLdoUzApdx8cyXXLK4v69eQI/CP1KSJrdDmuNOk9dPMuVu4vhaQhSYPoB5ZLF+naLmYkJSnlQjS468Bm7ME49uMiDB/fx/9v/MyPCpyhfYsE7xv3FBVqGha01Rs9nSiqcoMdYoYDSoWmVl6G/L5+3qffAFDN89atf4M/+7C22ay2W5z6i63exTBsMg4mJCRa3mvRknnKlgqHBRxEIsKTFVLnAc2dmKHcc8i2LM8+d56c/+g5GvkReaibGRljfynHv3fcxXAs3sFhv9hDlCaqGjWVJOu06pjQpVPKUKiM0a3WUhvr2FpOjeQ5PP8HfXP8GtFdor97FbRzFGpnC9TVSBRg6IBDQQ2JWD4FtYDw/iZQO50clm6tzHCr2OH5sBkNrzNGz6PETfOtn/yOus8Xh8UM8/8QFDo86XL2/yYO1b/PUZ55m/cocS898nfWrH1FpPMRtb9NoNeh4Dl4UDoKGIPCRhhnOTUPi+B5eux0eCx698ca2TSZnTqA9h0LOxnMDHq5us7ixzkzOZnKtzYYrOfXSsxw9dxrI4Y8e4TuX72HO5BDjUwjPQEt/f1iKWN7HBipDCkZyJoYRvU1EhSATaE2gFUG0gqMJnXLSCNmDKUXiqJMydL77gQqdyyo0j7Q0KMse1spNztUv80B0WAkkDpqcYbK5usy1jXVkALb0EYbAfFjjwZ0mRy4c4fTFc7Q6LbSvCHIBgbYwgoBts0Lxud+h3Oyi5H0atkWrtk2hWMJG4giJNIxoR7nACzy6KuDWw3Xaf/wtyobB0aNjVL0e7bbBT25usqLXKBy+yPFXf4eNjSWmS+/itOq0XLhf95F0OPSzb/H8ky/x4dFX6QU63MUvBEQsKo6NCgEnYlVoTASGEOnbfpIIf6KTFkmOKDEkgIFplbl34yaO20Lmxmh3H3D7xhV6HZdj557k/DNP896Pv8fVjz5kc3kdszTGkdMXGTl0lADFf/31c8zMVql1ysx9aDG3sE7TDbehlPMwVpBsbHYolicoCA+v4yIsn57r82hxidMzo1RLkqW1DtVCjsLMKGtbDUbtHNvrW5SOzHLxfJXzZ8bYeu86q3YVXatxxFKsW5IJr8faL7+DpZYpFgwqQY5C18VRGltqTOnQ0YJAm1RyNqYVvoa9XJnlyJNnKVSn2Xj4QzYWLvPg0Q0c5WIHAd7CEoVCmZItee/yO0yMjTBWLNDr9tAaLENiVEp8/50HnCwVeK5U4PVnNtne2mBqxOazT59ha2Ob45NTHP7801x5/yHzmwpVHcEycgSeR8/tUSyPorVHabSM5TmcPTpB9dQpLp47ytzDB9xca1IZm+Cp117j2KXn6WHjOj5GoNFGNJCBwkCgZbhX1SqXmf7i7zGx/CNKzRprLZcffzBPJWczVu4wO/U+v3XRpCJnGBs/z7Hf+094cP0DnPXv82h5BbNQofDsl7h2+TbOo5/hbrdRbgvH79H1vcgvGgZjhwHQEtO2CbSi43Zp9doIBIYOF7+K+RLatKk3lmk11jBMm/X2NhJomzbrTo8W9xk7+wSvv/QUK3Or3D/8Etu5cXDbERmIzk4nVbjpngz6wxNgTzTbG6iEoJIzEDJ0vgVChju0VXSmsgpnl1CxSULoHJYRMosUpIJA4/suXtejvbTARP0aZ61lyp0Wl7cXWHUdpG1jdTV5W9L1FabjklfRplUElmwiW/eZW7lLc+s45y89y6pqowNQUoXvovNBWVVGn/4yurlF4HUpjVRwOl2OTlbo6IB2N6DZCcJAVCS9wGOjK3E3e4zZPr4pub/SYcExaQuTfHWc49VtcuUxJo8+zTOvbnH759+hR4taL+D9+hbOLY83hOCp8VmuF07gKCM09+L+iIDKECICsZApGDKNO4vjpIQg9HVFwBW/Ck+g2N6q8+F7v2Dz/jXGgwUKhQKnz5/h2UvHOXP+CeYfrfDMiQmaU/8/1v7zSbIsPfPEfudc7dpDR2RkZKSsrKzM0rK7qruru9EKQEPMYFYMsdxZkkazNf4T/MJPpBn3A2k04+wsZzg7MxgMgGmF1t1V1V06S6cWkZGhIzxcu199zuGH65FVjZ1FYwC6WVV6WmZGeLjf8973fd5HzLLZ7rK3v8b04ilOnXySm9c/otvp8PPXxvz+I0t80tphb69PxXWwfJ/AdfBMRFPZeL2MaDBkmOUoDVVPkipJFOWEseHx849xd/dVhNbs9mJaSY5KM+Ktfa5v7rI27fNM9QmyGweMR/dZrvtsDkbs1ip0ru2SJDm5hM39Lk80qpTKLuMsw2AIAh+da1JtcBwXS4IuzfKtP/3fcuXmFt//ize4fvMDosNbgGbKc1iYnWH7oItQQyqezdxcDac8xeJMTPdgh6maB67FuNelZPtsxzFTh4c8tHafit3nK587T9rr8/Z+j/aNkG+Xf8hDZ85x/VqKE9TACjCjAZVKhXLJwqgYFQ8p6R6iNo3dnOf+ZptRotjabfPSV77G4vIqg3GMUJPP1aKwZDFyIn8rPlilDK1f/YLhwWVa/U36YUJPlfjSN/8LXnjmHAeHObONKh/+5C95/Y13efmEg2X18cuCASXcQLFx/x6joU28s0447JPGIZqcTKkJRGNQuUJaEt/3EKIgXma5JkxTDBPFhCyaj+r0PKiUaFQEiyRJioVCGIuBUahcUh4dcvmV13npH/1jnvzSOXrXR2ybJrn0EJnGyAiEx294vvxt9ejvS/i0pCBwiuKkdZG5po5u9xPA3NIF8CsnWJQti3FKCIEyhlRpUq1IjEBbFqODPVrv/Jh4eJuBZeiEOXe6A1zb0HAtSl7AaBwSGY0qBcU3zjMcXYyVFTtlLnM4fP8e5cGQpSc0GzOrZMnR+tOQakM4cwL3+EWGG+ssLR1DtHb53DOzXLy0yL37I37x6/vc2hihjY0WhjBNGcYJw5LHxrBNaizcUp2gUqZmWWxt36fUS/DnRkxdepLq5k3irTVaaZ++znmrE9L76BaPtCXNz3+D4eoptCpiyq0HIPmkIBlVdFCWLGQN8mhklr/BS7MmnVSxIQRsi+3ba2xfe5dHX3yJ8ONdWnubNJdOsnD8DGs3bzNe+5io5GPNzlKyIO5LhJZ88O7P2W9tEdRrfHDngNXmDGGUMcwVucpooElcCBo1ZqyQx/OUQaLZiyz6UYaTaWKTM1utcHquzOLiEn+lBa7nYUipezZa2GwNRqRKkWUWSZ5hpYYpbdg7GDK0DOgSnahKVfb57547z//7pwNmfIuxUniBjZ0rYq1wbBdjEoStiVKFHMZ0X3+L9sYaa0MwpkNm5VgKVmdrvPT4Kr++Ijnojak7HnOO5HMvnaXiPUe4/QYPHXP4N7/c5/ZNxctPHifVJRyGrN3d4fHVOR5/9AzvfbDOE0+u4l14iQ93UsZ3+oz7bcquIBmNEChyXOJYsXnvNmHYZ64SsHTpLBXbZ9Dro03OyupxHjr/CIPxGNsqwlCkNEd2mw8cDQodrcHYmvnHnkDcd9n81Y+4e7BDnLV56MM3+NX6u4zHOa5XYnNjh/Y4Zv3WNSzH5o3rG+x12nzx2afZ7+a0dw7I+m2SKCZRGVmWo7Q54olj24UhoGsLpppN0jRk+2CE0sW2zxYCx7ExShOUKoyiiCx30Mohy2Ncr4otNKs1l5lSCWN7WKLNez/6Mw6XV7D6Qx45fZGD6XPsyipKyM+4KPyvVyFxhGH9fQmfQoBrSbQx5EeHRhQjSdFdaYyc8ISEQcrJuDfh/+SmcF40WY7JBanJKC3NcvJP/hS5cZf+5Z8y7NxgccqnLAVK2+z2hwzjBFdAR2lqNnz99DEeO9Yk0oKWV0PUV1h/+23u3dnnoelbNGbHxFapAAtlwdmKsHFWnoR3XsOpltDdGtfWNXfurbG932N/kJPLwi1TG0iB1EB/GGMsge94lOIQbVlUwgTL9xiM2lieQ69aZ+6lP0S/9TMO5HWycER7HPPhOGXt5hWeQ3Ha/hLuiUcYq4KD5sii8AhZgPi2BGlZyAmAfsSzKkY8M/Fp+nQc1BPI6rkXn+T46gne2zhEigaDcJ3bly/z3kdXmXcEXzq3wPGaw9XdIefOPs2N6+9hWYp33/oJx0+ucvLURT7c/Qnf+3CdL5ycZtp1kZZE5zlhf8TBQZdHlueYWqiTKEH9cEDLMuwPMx6em2Nqfor27ia7t66TZimjPOWhWpXxMEU7Pr4FKzWf4zUH5kvsn5DEV3foJynusVmqxx/m1Jf/Ed7d7/PjV9+gZBzCKKXsWNSCAJOl5JbALwkq1Snao4h2KknilO++/z6UHTZaO0RRRM12qJYqHJuuMzrc4bGHT3JnN4ZwzPnVaZ460eDme1c4Ng4ZbEnu3dnDtQTnz65Qrk8x7vbZ3tygOjXPd370ERcfPk/ZRMTzC+xvDahnhr27V7DViMbUHIM4IY96uIGH7zoIq04vjVmdOg52BcwYnIBzD5/FFgXE4dgWShU3JksUetfiJl8A1loASpP5LpUnv8L4zhZBt0WYRrx35x4zroXvWLTChNZAoY3mnVubfHxvh+1ByvFGwImFOa5vrZEM94jHPZIsJUmKLklIiVI5tmVPdJYOJd9ldqpE2a0zGkUM4xjQk85L4fs+tWqdKEw5vjiHEFNMzdWZL8OSjBGDLkib2AQklWM8/OLnuP3OG7zz0dtMffIu009/Ge/CN1BWaVKgzBFJ/jOP/zxA/bfSE6QoDPN44OBnsEWBqyCtz9DiC3KjFMUGMDeTIAhTRG1po0AZlDAo7eGfe4a8P2Rh2KLZ0LR6Kde3B8S5IplsyWrSMOW6DPoRncClcWyBs+cvkFMh2zvO9ctb5LfaiMdVYR8iJ0JXNK7O2EsAx8dNMkaDQ/rJLGVpEyqNcCQOoFRBRkwzRWYgNxpbC0yeEk8AyEG/S4Uabt1jNOjgH+4SNo9x5o/+D6S//CucW+9SckN0PqJkC/xsj+DWK1SqGtl8hBwbyyrGOfuo85zgfsV/gsklXNhwcGR2dkSUM0UKiVLgCBKvRtRfJ1A5cZxiIaiLhKdPnWP50S+zMlfiVudnvP3+m0TRkH4yJtc5pB637twm14buOKadpJSNoJXEzDWrBJagWakQ+BbSKpO22pycrWNLydqwg2dbXN3Y4+QjdepehcAbo+OQ1ijiMNSUXcNKxefkbIXVpgVKk5xZ4EoX5N4Wz58/RvXCeVYeP8buXp33NvZp+IJUK3y3cL1wfAfbE3SzjHtbfXQmWT7+EN3+AZ9s7eBHdY41ZxnLLnkYYvKMVrtLabFKSQpWl5dp722zuLLED//6bfbX93lkzuXuaIztVvBMypuXb7GyNMVMpcLSsWnefm+NK7cGtDfh9/7bb3LHrWCJFv3779OwI5Q0eEGJ43PHSOMEu+ZQ8Urs37+HV3M5de4Ue7lDOXDop4qFuVmEKcTXSmlySxS0HG0wUpHLopsSxsbWFlgJPh6tKzeYZYBfEnT6cKcTc4+c6ZJHkqYoJM1qme1+jC1jFhtVFh1J3Nuh196DeITKM1CFdThWcY5syylOs9ZYUjIcDensK8z0EtPHz3IYXieOQ7QpzCYRGYNui5WGy5nlaVqtDtNOzKXlMseefxltAu68fpnWXoug7GPGNrPNORrLZ0jOv0Tr7KNE+FiJ4si0/NOuaVKkPlOnzBGe+7/QBv4dC9Wnq8VPHRmLL/yb+pBPZWyT1Bkm+rYJMVsZMyGFW4XbgJCMhhFZd8j8lMcoHTCIcuqOy9MzFZbKHr6E3OR45SpjpbnSHXGqltE8GFCmz0PLZZKNJqHtIlwPNy46DmOBUA7RIEa/+WOm7DFJFFGvu9zf6dMIPE6uHmdru0V3lDNSGbbjYiur8CIXhdlQQYpTZElMGkfElkDlOaV6leTwPiXXZ33X59k//m+p/rzB+ifv0B/u83jVZrFms7u9xioDVh5eZ3Di6/SNXxjGIXBsG3sik5EUHdXR+1pM1mKCTR1FIymEUGiTo6xZ7mxcRXQO2VxbI9OSpWrA/+bl0zx65gSHjXPoQcTnn7nEx/f26Q8PJx2dBZbNuWdf5IMfdylHPXa7CSv1EmSGXj+mVnKRJmT9MCHPc87NBay3E/YTwxOPnOK9tX1kHvHSi09y5dohJ2f6bB8mdBNNxbWoejZVz2Fhtsnx1Vl214f88O2bOHnO733+DJ7nodNtst2PePXWPQ4TxUrZIxpFCCk4nGj6mq7HVjdif5RSb0zR3tmmYkmmPA/XVYi4R0lmxI5hHI5pCQdhBGr3GtNTs+RxxJWPNLt7XXqHB8xMz7E5yHBtxcMnV7BMTNIfgquZXTnF/d4NIrvJpT/9pxz73a/xb/71FbLWDvHeFf70j8+T2IustZbY2L9DozFFreqSt+5Qr4CcPo7wKsioR9m3SbTGTsYEpTppVkh/tLEeHBdjNI4RSE0hd5EanDKDm7c4fvenlEWPPxtEDITNXMljnIWF15rlsTA/h6HCXFVzvJxhx31coVmYspjy4XAUk2qI0owjZoBWCimLDZ/RhQh7rHJGnTFPPbLKs48+w3AYsr5+u6C/WIWOxCfCMhZXrlwjjUYcCEX3tkvpo10eeeJR7Cil7Flk4QF7H/2c6vIcF37nD7k1/SzdMEGqIVpoMJ/d5n0GSP+Nx/8fHD4Fn3J+EEfpOZ/yIszkgGl9ZOfyKVHx6PcFA1ZCrrEtizCMuPf9P6cSX8edb7A0N80jpwN2r98nGXaJ05iZss9UpUESNGmWHK6vbbB1f4dolPDwo4/RqM1wcsYj8eAOA1w5jaHo8IaDIa1ff595sQmuTR7l1P0mQS0AacjGKV6e0fTLaDMmTHMc2yLPFJnOcaVVxA5pQ5YlRNEYz7YYtFt0dzS2sGkMupROP84dCU//3n9NpVnl1z//ESM15N7WkE4WcL/d4/zhZS7FBv/SN2krByzxALC0JEhhYU2ItJ9meogHNx+DKdj9QmE5DrfWdjnc2GR060OSpEiWOblYoRvFvHn3gLnKFXxrj5npOc7OVtjdLxYbllZ0ez0ePfUwp5/9Onuv/QXDUUzbt5gpOaR5jJABh90RQdllvu5QDXx2xm1uDVO+fDqgakseXl7knR/eYuyUuXh6lX56E0Ypi9MVKr6g7ljMTnk88txJ3vnxh0RhyqmVCqcXy7x/9SbD9Xts3r/PG29+REUnNGybasXDcxUr0zWiVHN585A00TSrZXb7HVzbJdQKzxj0MCFwJL4lKdfL1CslonFIlggsRzA7XWFp6TRvvfke0SBjtlbjmS88wcFrN5mtlpmverjC5WC3zc3tjJnHl/nqt77NX/7VZQ73RmzsRLT293E626S+zZvvjMj0ewy4Q275dHsWa9c3mXZjjp17lrC8yvbugKXlOrtbPUyuCHv7zE7XsWXBHfSM9UCtgC6gkdQ4eLZDNjhk/NavKK29wl485PrhGNvyaMgxaZpOOH+aM49e4MTZp7iynfD5P/4maR+2/uP/E4Z3efvNNawMEpUSZSE5CjE5C47rYnRRsCwpyDUMo5yRMOzs7PLil6rUp+rYGzbzS7PUSgHJsE/Z1ezubeEICCyHkuPS14bNrR06UY/lRg1bWMw3Z9jduMPWvVtMne3yZP8e+dQKO2qaXVGhj/xPdEqTLSCfpVYdsZv/PoXKgDC6eIOPuqvJtuJTIH/COEd/pmiZBxIQTHHgzUTdLLWAcMzqc4/jD09Szrfx8hbr29u8v7PPKMyRGL64arPyyCznv/y/4+o7Vzg1CtncXqfTSbjy3hDPsagaTbVaoywcIluidDHDT9clM1/9AmTPY2U5Sa/PcGedvL9HY7pK2N5B2R5RlOI5DmmuyDKFa1lYojC7yydtsrQluUoZjobYUmIZjUVO5+5V4k4f+1zOx16VJ1/4OtNzJ7j6i+8Rqhtsj/q4jotuJbRfvczjfcP0ky8SV2fROkdMKBIFplfcdQqcqnhuJm57SuWs3bmDDnMOWiO2O4d4MsdlhBQ5tijRim2u7ebISsSL1S6zp7/A4fp7XFwN+PCeR2swRkqLdHjIweYujr/AWENJS/Y6A8aWhe/ZaBmCBYNxTLnkcucwZmFmijuH29xY38WxBAfdEaMkxXEHrI0N+8OUpjTEUcxsvUIt8Djc7/Cj//AaegSeY7AsxbUr9+nsjujgcWX7Ch/t7HM6oDB9swRWpYy0LVqdiP1xzijJaeaa41MVZpp1LEsWIE+myNMIleWkcUwlKFHzG0RhjEo1m+s77Gy3GI4y6gF87tkzzM7VefyR0+zeXqMdj7CFw4mLF/gf/+wVWu1fcOb5x5lZXeTmu29z6JXxkZxtCobV81y/+iFShczXXGancg7ChLs9m+0BnDnzLKXyNINeH2kcXN/BdqpceOwivUH6YFFiLIHRAmEJhGsVOsUsILr+CXMbv8YZbPHmoMdBZjM9O8f2fguhcxwpiZOUUrXEwvwJ9lKfJ/7w27Qjh61f/gWLOsNvnuTO/h6fbO6QpDFgsC2LNMs5spRWOp9s9AphviUkxhhaOxv0DndoTs+wcuwYJy6coru9Sb1cYtjpEYUhltJkWCi7UHgE0qK9k7K5tUOWZ5xf7HFyrsnr99axtvY4VXUIHIeKP0P54lcZn3wapR0+c+ctStVvjHr/wI7qCKMSYpIicTTe8Rmyp5no+z5raaJ/s1iZyYsRsgiarM7Oks83ce0q6e5V3v2Lf8H9g/soCalR1IXN3GyNC195js2OwnEcHM/l9IWL7B/2SMI+4zyiHaW4qo0bpfiBQQuD0QJt++S1WcgVWmiCmSUa588z3Fjj4NZVbFllmLQplytk8RDt+0hLk2tIlSbXxaw+iTkACqtXIwQ6zdFSUbIdajJHhgeMdu9zr+Ry/twpZuf/GdsfvUvw9mvc2brHvVFIrGyit9/l5P4+yy99FWvxLFobbGEwWj0YlY/Em1oXvlVK5UghkUnG1Tdf5bDfZ/H4Kt3WLr3eLq4D5DHDUcawr1mdnebEE8fx0i32Dtu88vp1lms1hnGKW5sizQTDu1d55qVvs/PuAqp7wFBpHFdgOTlhmtMdx2hpEWV9BonGr5Z56FiTQQyKhLMrizRkTJZmXL12iEoNQdNBY3j7bpu5SoVTUz6rvs8gGWCRsbEXIfoZ040y21tj9tOImuvQilOmnBzLcej2UnwRcW1nQKw0J2o+Td/CRRH2uiSZojo9jbQli8ePEYcJh4cdDnsD6qUygSuwpYU2CXvbLZAuy80m4aCD0DG2yDi2tMTB/TU29rqsdYb0Eslh5QR/9K0/4MXZeZTK+Rd/fZ26bnEh2EPO+xxT8zzxufPIkSbc75BUZvnnP96gvniMTNpoIVCOzcZ+h8C26e/vcri7R6U2i3EkyihUrpHGgNA4noPa77D5k+9zcPdXnGsKTizNsRnlyJlpPv+5F+j+6Mf0wzGxzvFdh9PNBm5ziXMvfptBBOb9N3jU7ZOXJd2Dde7uHhKmaQHYU3i/SVkQrbM0K4JlXZdKpcLOQavAjKQkHodc/+gKxkBjZpY8d5FxSnvYZ78dgQaPgkYSmYKWNGXbLNgOuSURgcV2t4vnCWaWllhf22EYSAZzD5E89y0Oa8vkuTPhDE7gDfHptHCEU/22IvVbC9WDLsoU+NRR0TkyjmeycT0ydzvK/SsyAAsLXqUVSh+5hBbr99xY2LlFJmPW+g67/ZSLszW+/uQK/+JXN9nvJXxy9wDxP/0FywtL2OV5pucXuX3zNlPVMg+98AiXX3uTMTl6+TS5L3GFLqx8C14qjgZtCYwqMJ401zROnKPSnGfznZ/TmO/jiJwwi1FK4fmCQRwWGsA8mXitQ5ZnGKXJjaE7CJlC0qgEaGMY9w/AGKpeQC8IEA8fw8nGHHvmOZonTzP9xqt8/MFlDsMukbIYrK2zf/hXnP3it2hcfAytcoTQBSY1IcZqpRBCkKocaTRKJaw++TjXN9tM7d1l48q7qHSM64BnWViWZKpWJk9TXBliey2sao31O/eJMoWth0zXq2x126ycPcvJxQU+eevnPHXhMT569zVs20MDrThlOAqJkoTTsxVWmmVsJ+BQx0RZRm+QUS9VyEcpY1cVSwsBjuuTpSm1Zp1O3Of4YpO7u13mamWmApeO7eCWfM4+Oo+QASedAXfXNun1Qo6XXQLXJRIKrRRrvSGZ1Hz94WlWZ6pEcYpxXGzXIck0YazpDCJSAytnz1Mq75FnN0jSGN+1EcIiGoR4ls84UyhtaHdjkiSj1+2zdn2TmbKDG7jc2mpBbjNVsalXPPxSibs9xUDZ8MkveDde43NffoqLpxZ451fXuXttjxPNgFPPLtNptTg28zhK2KRZjuMGiCwhyRT2uMdr//7f8OQzT1E7+RCOVQJlkCLDWIL21Zu0X/0h5nCHqpezE1rsrnc5HEboZJsP3vw1Nddh4Pu4tqRSKYIg6osnMKmm++rPiT75OWvtTUbRmFGakMsCHhCmSFHOc3WkcQMMgesRVMpExhAbhSvAcxwefeQhBp0uTmmB6uPPcXrxLJdvXqc1ygimFxkNOhxGCWGWo5EE0kKrjLrvcGm+zDOPHyM4vsgws9n94Zt41TK9cy/Cc/8Vh0ZjVE6xSpP85px39PhNrPvvX6j4lOPwYL1omAQ+FM6V+RFLXRekTk2hZcqVIdfFc6UnlqhHwiKRoRyfLEnYvPouOuux38/YXT8kMD65jLh82GNvOOLFQcbpMyXqM7PU6iXu3r3FuccalCo245FD88IzjL0adp6jxMTyVxYkUfUA6C98R5XKcBoNTj77RdbfiMm696g0S+hegjGacuCRCUWWp9iWjVJFjL3B4OY5C66HbQxpnOC4FsdnSiwtGLzqHr2RYf+aw9L5x4hGI5he4uFvfZvm2TPcfeddOtubtIYt9sIttn/wH3g2GrPyxBMYq7CSFcKeLCKK1yx1IcCx/CpvfnCPfJSwfedjdNRDSigFJdIkRBub4SgmUYZulPPKRx3+0anz1BuaXmYYjEPmlqexk4zphVPgThP2bvGt//5P2emNuHb9MlbFY3/QR6GYKwdkSpEaxULD5Xh1lst3NtFZjMhTwqREPC46BM+2CNMQgJeWZ1hcKHFsYYrReMjxhTppu02YazyTszBfY/0gpTUa0IoSYi2oBSUSq+iE26OIrTDj82fnObMwBdJQ8kskucDxJOWqwzSC48uSrf0hu3dvEViapeky3X6ENBrbtnClheML4jyl1emi04hwlBPnkhsbHU4v1whjTRQJ5menOFi/w7vfe4WX/vSPuL0Rkx52sbOY9zd7DL7/a/phxnonpl4KqDY9VqorXHqxgjc7T5KB1jnS9whsl8792+T9Phu9+6ycO82UI0mzHONoxptt7r/xMd1bb9BL+2yPYhaqZcZpRLvXLuyQLZfDVszpx56gUt8j7B5Qf/LzXHjmdzjcbrPz3X9N94OfM0yHJEYRKU2oJLbJMLrQ75mjyWVi22FZNkJK+sMB3TAEY/A9n+PHVtC5IrYt5i8+yfxTX+Hmn/8r2uMOU1OraGGxk2wRGYvZWpWzgc8TVZ/5uQr7w5A7O12sj1qcp8zDjz3Ee80KI8fl3LNf4H1Lgcom3gXW36gof4P8edRV/Za26u9QqPRke3dUsAwaQWGcUmA5+qiLMgal5aQ4TeLgdUFUErIwKBXSwrYFvd0267/8IcnGW5TIWA5KXN4fsDXx6Vkulzg9XaJS9rFkQv/wPmrc534v4Revfsix+QV6yZCTFsTSQcqsiOTSR7HVhRWKkbKgSWhVOHCqGH9qhqkLz5N+0mNuSpCKhHjYwTUuThpiOXYR9japGgZDpnMsy6XkOjTsnM+fn+OJhxeQIiemR5iOyfoueX8Jt1lnFObEYcDcuYvMLK+wefVj1j74gP3dPUbRmPd/9gN2Nu/x5O98jVJjmlRnWDgM+jE3r3zM6vJx3EaDGx+vc3BvE3Y/RkVtqkHA4vwCaTJiqGLCJGfUiXFdgTTw9sebBP67vPDVC+xJi//42jXa/ZC6VyPujXn4i+c5szpN7fgKL3/r22SW5Pb1NyiXXfw8peZIhkmCcHxiHLKRoWIsnlqaApWAFPjVKr4tWdIeO0MwOqYX9jh+rEo0jJmWBj2OsBybcZpzfqaJBPqjIb1xSpoUwO5Gp8/idImS67AxGrJYr/Dw3CydkSYXEkOGFDYyBDnxKnc8h0cvXqQfpdz+6ANKriQuu8g8Zcr3CQxkwpDkKba0GIU5Qhr6B11sy8Kv1njyqXOMXrvNM7/zNWpzDWrCYWOrzc2PD6iFPbqZYLnuMVV3uTOIcTzJXMOwdKyJqDRIdEizXCOLQKCQtk0S5zSXFrn4pSc5fWIJLQRpmjMexLz5418wvPY+SbLLehghZEC9Ps1Xfu/3+fN//z9T8Vyq5Wlkrc7q8y9z4omneeXf/Stcx+LCy18mDOtsvfXnpDvvUK4IssQnDTMsK8UVKY7jkmQZmQSTgy0tAtchznMc1yXROcMkRhpDYNvMzR/HKk2xfPESoV3GPfsIewcD+rfeJdNQcn0O9u7hWDbl2gyPrMzzjx9bYf78Mbbv7vHhj37FtTDj+toevf6Iwfpd6kGd3V6PYONXvPT0t/lFS5Ib+WDpV8DZ4kFh+rTA/K/vAv+zCtVRBfx0ozeR0yhVjHxaoyasda2K8VCZicn8xJtKTEZISwiEyth59yrDD/8aL+xhlQQr1TKnKiUu7/d4bGGapcCiJhWNeoVqs4HvesTjAaMoZOS4jEKH8dhjczjmufZ9nMVLhSzBTDi4Rj7Ay5iwvLWkiLJGY0zO4vkztEaPotvXadYsrGqMwibfNuwPRwSWg8gN1oRZrBD40qLi2bxwdo6LyyV0FmH5Dpa28L2MvHUFS3joUxfxp09jhCSLUtKgzOoTz7N0+gIbN65y/eP3iQZt1m5/zKDX5tkvfZXZc+dItMZ1BNHObd55++d0c8VMdZ6VacOd7l0Cz+OhUyv0xwMGgx55muA4Fo3ZCtVajTCKKFc9vv/eNm/d2GdleZ4LKwt8uLlPvTZHqdZg4/4t5kcDRucXOX7mGF8r/RHbGxvowT20tInSjKrv0g0jgqCGyMeUPQ/LUnjlGrVGjWq1UviWOyPe3z0org/pMRwVYPHZSxcJkh4Nz6YRuPhWgc+EUU43jMgMjLOUUNr0D0OqrkvV87kwVWXYHRNpgy01QqgiFDrXFA7sPtJvkESCxeXjzAaCD999C6MNpaDK6skGvpVRsn0+Xtvnw5ttjtUrDHp9NnYP6cUpb1/dRvjTVL0Gx5dmeOzr38AtlfjVe/tEn7zOGW+Txy4ITkyfouw2GL7XAaU4PTXHVEWyYEX4uk00ruHXZ9DjDJ1LklTy1DMXeObCabq9PmmYsPH+Bh/9/Efc3rxCP42JdY7ONGkyxHc9rm1usHzmDPv3dkiqdT73x39M+dgxkkiTlab44h//Homu8Na//X9RbX/EzHRAreRzMIgZp31sbUMCaZ6BEORZjhGS3Agc22GuUcMThp3DfrEcsgQPnVnhzOpx7h7CqHKc0uJpQllBiBxTn8XqHzAa9Yr31K0wU23QNC5763eJLYekl3LyxDJpfcjb6xvcSMrML15k3G+T5Qe8+/bbrCoX++QfomSCFFax8f9MsfpM6fpfPP17F6ojQeFRZ3HkD64nI5/WqgCw1QSvMmAeYFKTf1+I3JBSsH3zDlnrOvOL07xwuskjZ+dI90Nee+U6qzM1zs0EOLkuku2rLmW/gskFNhmBZ/j9i8s0XMno9EUuHT/Hvf0hC5dy4gc8rqKwHi0AoMDKpJGTzaQoCJVZwtS5p1l7fZeAPRyvzKDfRWcJCki1ouq65JPMNJWnCFswXy/j2hApGyvJEHbBr0qTlFQp0t1rBM1p/KUzyDQndC1IraI7aNY48+JLnLh0kZvv/Ipbn7zP3vYm3/vzf8cX//iPOX7+MZySxee++U1e/+6fY21dJ93fY31fMVstcXJpjlE4pnvYolSqUJ1fBjKi0YBBe0wvHNHrWaycOE5JCNb3Wngm4eLJU9zrjKkfO4vjVPnSN54gFAqd5cxON3n4/LPcfG8TZI6QkkB6jMaacSnC0Rk2xQhhBKRZTPswJElT7NzGFopcSgZJEUs21BkvPPs099/5KRefOs0/feISb/7wbe7d7xNFCb1U04sTcgCtafg+s46kaksCWbi1zk9V0UqT5ynoInbKdW1s6WJ7Lp70WVo8Tej0qdUDevsjtBA89MQF3GxEkI/Y7g3ZHu+xUku5c3ObXhRhuxa9xGXUOMdL33ye6SWPNB6TZR5vvXkVp3eNc+cMrg3Hjh2nvRfzjadW8Ut1mPo8C+dOs/X+z5mebzIyPiQpOs8waUJlqsql08uE4ZDOTsjPfvATbr7/S/rjQ2ItUFlMplIEksB3UFnM9WufIL0qF770FZbOnMFuNklig4Pm87/zVZQ7xS/+3XexD69QLUkskeG5Hr1BlyiKkMKmVgpQRiCtQrIUZimxUoziiIXZCudWZolUTnc/wmCxttVme2/E/CPP4y2dIw6miAcRwjYEZ5+HzZtIK8JGUArKBKUyNzfXuHmnw0N3tllplFg51mS2UsMypykZw+NnH+bW2hrbBwNOnVngkS9/md3NEYdpqbApkuZBNfm0/fnMrPdbMv3+ToWq+NrmM0VKP7DeLf7k6H+TvzwB3PUR4M4kQktYOFJz/tFzlB5/jKZrMXzz3/L+q1e4dxAxHgx45uQcWZYzSBIQgmldplatoxEM0gOmZ5roXEG5wfQzv4OXO6SdfbTKsSZd26Q2FR7uk2KpJhvIo7RmYSQIRVAvM3v6UfpXtwjTEnOzJ9ndvYrjeGQqx5bWxDFCMVMtM18robOMvfYY0pTZ6TJax0ihsISDV66iwhG9yz/D7NzD9aoEz3wNYZyCqkFh3SnKZR774u9y/NxFNtbukCvF3OIyjppkAVaneOyr3+b6D8f0N+6CbWELRSASjO+yODNHuTHNbqtDNUhxbI3OUi6uNghqDsPBgJWFOd65lxPUpjhx4jTHumMWky1OnF+msbxE1g8Zj0bc/nifw80rNMsew7QIm6gFHs1aCc/KsW2FLPwuSLOErBchjU1mihuAa2w6oeLdtX3OLkzzuYsPc/2Dt1B2hSttH0kXqRRK5YSpph9phLaQwhBYFhfmG/R7A5anK9QrZWzXQkiNJS1sO0BogWVEkd0nNIGl8LNDPF9Su/BlSlc2qQ/WSccZa7cOePTZJxjv3qI3hpITcPJ4jUEYgbB49MJpVO041zdHnLoY88K5J4lT+NF33mR8+Tucr41485MB7VbI4+lZPv/y1+i8932SVDE120GFTbpxxuaNa8w+fgKrVEOk+6h4QHlxDiMdfv79t/jld79Pv7NGX0SFk2mW40nBTH0ahIWQHlZtitOPXuD8E08Q1BvEqSJXAgdApNhBhV995yeMb/+Y+ZKiVPIJHMmNzR77Q8hygW0XshelC58pgyZwHFzbIk5zhoMhh4cup06fYbMzQCnojCIqvoM/iDCWTRzFZKrwausetJme9dndPSCwXeYaVbrhmDjPaLglpsoejXqFZrXKVLXCdA2whqA9Xvrql4lHe9x47wrV8b/i69/6E34wKtPLLTDqM0Xpb1IR/pMo+39+oTL6U9rBb3yzSbEyk+3ehDL16bcXFExXKZBG4EoL25JYKIzJGRiXW4MpNt4/IAk7PHl8isPOEMuSjOMYbQyuV6Y/7GMR0xtGzCyeot1aJ1MOIvdIswxZmSY3CUI6yMkbMjFu+LSITtpNoyXoSTEQEqMS5k6eon+7Rt7dZ4Di2OISVb/DnYMWSINj2xitsRwbWyqGscCWiqmKT6+fIjBMT5XIpcHREc1agD2CxskztLpjfG3IpEA4FrY6GqQdlNZML64ytXiiECojyFFoFDpVTM0vsnLpS1xt7VJ2Cw/v8XCMVRZMzcwhhaIqB9gaanWb5mKJ2lQdIyWhHnJ62ebb/+hb/OI7b3Hz/hXmbYnf2mOmZzO4tsvU/KP82794k42PXsVJt3EcB5FEOJZNFOeUvJhGpUKWpOS5JssNjmPhSJs0Ldw4lY6ouRbjTDNXcjnV9Bj1W5R8wdU7O9zeH9IUKTKLqQYW4zClH8fkk9tXWRq8POfk0hSLzQpKFZbVWWbA5EUjXpidYUkLP7BoNixWjtmcXMjJyzM8863/hnH3gGuv/oQ0H3F47yoPv/g80515vsKbnDrm8eqtffYGGtvM8iff/iPO3N0navcIo4zWnuL2K/+OhrpHnAesnFjm4bOgrQHDtTvoJGY0aONtXyFKRrSThO7WFkb+kukLzzM7tUBv8zrDX33Mdy/b3Lh6lVF3n8NQk1gGXwpKpQDPcgAby62x/NBDfPkbX6JarRLGOXGaFWRfUUSw257Px59sMth8D1/m2Ch6Ycj9UHN37xCExHWdydZF4DguUVqkOAeuS5gkZBp6sSbcaFNzRkwHZVqjMdItnE33tzbIfvoLLrz8LSKRYSsXPepSDhx0mhJUy9QbVeJOSmNqhWeWDaUkRAibvXbItfttUjKW6xZB/i7bziVmRM7Xv/4cVzdTDn/9a5qrn6NfWfzNYiTEp32V+buUqL9ToTK/0aId0ROOGNRaH4HXk1xfU4xWCCZeOy65AAuwpcQRBkvYCJGhpGTn4IDOeMhi4FKyLerVGtjFxsaTFlpq+qMuvqPw/DIHu1sk2RjL7lMxfbSoFLFRWBgx8bt6AM5N+F6i2DsYJqnEVhG6UIi5LZAB/aFNd6fH1Lzm5NwMJWUYjXySLEcLCHyP7jDEEz5LtRrtwZhSVOLhRoU4GjOKcoKKg2NJjDK409OM9tuYUVSk2PjNwgJWTWQySGxHYrQuhKmf+SgNEsuR7O0d8O7772PHOReXpvBKDh9dvUutPE1nOMQzEYGVE/gO5VoJ1ysziF1sy6IfjtjeiRCvXmXl2DGe/+qzOHLAKCrxyo8/4HlvQE10mbNa3Mk6hPmIfifFdyVTro0yEYNIobuCNEyLpchkeeKgsSeuD9oYHl5uMjuIQVv40mZzcxOvVGZ7r8t4u81CxabuSDzbZXeUMshycmNwhWS1WSXwBCKNOWgbHNfDdyW2tAubG1Pwb7TW5GTkKkMam0ZzmmF/TBS2cD1N89IlVNTCl30Y7xFubvDVp6bIn/kKf/1X73BtU5BRh9Ti9OpxHn3iIo4Lg9Dhh3/+P7DSaKHGDv3OCNdZ4tLZM6w+f4b9+7s44wBDxu7GHcxYsdEzRMmI7O5H5FnMC1/8BunOFaLeJrvpmBlfsnK2yZ2DiJ1M4Dp1RrGiXK3wyPkznDx/nqWTJxDCIkmzB1teM3FTEJbDaJgR3l6jIQZYJYfAd+mHYzYPu/ieh3tkgAdYts307CxhEtLp9MGyCDNFqjXdKEEbhSkbTGYI7ABlO8RKQKnE3MocmWVAF3islIZurwgyzVSIsB2cWpWLp+s8dqrBG9/5AcO4wyjL2ejHpLniTLXKM08v4W6v8fY7Nzhz7JDlJ17kg3Pf5jCTWLpYvv1dC9Lfq1AZA1odAeh6ApzrCU9KFTwpIwps6oj0KSwsJCQhTRWR1KtkBFi2hWsLXMtCpA75xhWavdvU6z6+Y2EMbHRaCKUo+35hWZwmpCWPR7/0+9x45Uc4ps+ddkQ96bAcdRFubUJKlYXoedJJPcgdPKIrTAzsxGfGQ0tDd7/P+nuvkHa3adbKJIkFtqZSKbM6K1jf65FO/l3J8xiGimDeplKe4bDbZpOUmcDCdYt1ixX4GAEVP2DQv4oZjemsTVF55PMMjjaIk4jto7HUTN5offSGC8iznLm5KX7nj3+fN74nkFOGLOkigyrVcsBo/z5ByWLl1DFs16Y/1IxyCXmCMpAkisODIbOWw3w9oxrtYFUb/MvvvMVgr0WQjnnisQNeevbL2M0TfP+7f8Yw22WYJehcsTJVoe75BUvflighyfOcYRgyUy8Y5Hry+WdxRN0tCu8oGjAchex1R7iWISi5KGB7kNNLWrRzTT4J/6w6grMzFUZ5XJi1ZZq669LqdRFa4EqJ79i4ll1Y/7pOcZ0lcPXaGurePsOwTuZ7LBybZbhxjTvtDll/j3Bxjelqg27tJC//d/9Hjr9wyCs/f52sO+LDX7zB5/7wq4wPof3Jm/z+xYhld5l2f8DrH4/45OZVNteu8tjWYzz63Iu4T/wO3u59ZnTKnfs79Luahx57Ej3cBznm8g/+JYfdFt3URihDveRwxsmolHzskYVjN3j6uTM89cxjHDu2SK4lcZah8okMXSiKZ3KC5ZS4+ubPSW/9hMAZUvctQi3ZPRyBkAS+h8omRGBRYFOddgtLwtLiPJt7h8RZjmVbCC3QOOyPDLWgxtTqGZonH6I+s0AwO4+YPU4zG9J3PQbGw5lZpLP7LqmSTDXnSXOBZyI+ev0Kd99MqduSZqXM8XoZd7/PvcMR1WqZUqnC1FTAY88eZ37uDKWFOW4bxaEdQJJjhHpQUP5XqVR/iyD5txYqoACTJ5u8XBd0hFwZMgW5NhMy50QuA4AC4WA7iv1X/z0nV2cpPfIV+uUVhBSM7lwnu/E6/a0POGjtEUU5FxZrnJ6vYls2cQ7DJKRcrZNGMfubLdq3f02jKunogINUErVizhzsYq2sTnLviqIkj9qpo+byqM2c4ENSGBAGW1hok3Gwv0ce7uGWpxECyoHDdntIWaesLtVJcs3BMELnGt8o6p5PYHIaNYfZyiw6Sak1yrhCU8FDS5tgZgYcCzm7xMLJOt957WOO185Qml8gyyOULFwQjPnNrMPiZRZSIyEMaa6pTM/wlf/qv+bDV37KaG+P5tQco36XlWNlqvUSSWYT5g65UGRRgs4G2NKn2axj6ZBuFGHup6R5nQ+3d7m7sc+069CLUjKjGLbGfOsPX2Z5qcm/+P/+f9jcustepBnvjVDTsFB3mJoqYzLFaKzx3MIiOJtE1zuuhWVZlD0PMERpjhcEiMBBxQNqVRfHr3J9s007LRwb1OTjyBF0B2MyrakGAdK1SHRKUA1QuYZck5CTao2vbISxmD1zBr9RYmrpErfevUz//htYosyVDzNawzZbo4zVSgUxyomcBpf+2bdYPHOB5jI884Uv093dY3N3nTzW/PX/9D+Trf2MZy5VyU43mZqZ4ndfbPLyCw+zuy25dveQN37yE2ZOXmL+0RdYWl3hk/Xv0N/8EeVmgFEpN2/e5yCe9JmWwSGlRoPI1EntOk899wjPvfAk9ekKWW6IsxywEUZgROEukk+uX8tYGN/h4199gL7zFiszLqVgijhOubm2TZhp6pVKMcYIByPAdz20yNGZwbVd9vf2GA0jHCkQRuPZHonl0XBnOf3c51n+3Ev0LZcsF6TShn7O+q9+wKmvfpm0scD6/i7NahnddekMxvgNSf9wjSRKiri66QDbKHSeMUotHj11jksXj9PfuMW1K/s8fmaG6WnNbrfFUtBh224Quylk1mS+ifkNMsLRNMhvHwF/a0eVTyKujsibmZoUqlyTT/Cp39g0Co2lY6zyNMnMOboffZ/pdJ/mE3/CWxs5m6//FfTvMR6FHETgGYGrJf1+yuy0SzlwaZQCylMztNttPlnb5xdv3+Li6iqsfo6vff3ztNY32e4nTAtNbo5IqZ/aoggpP/s+/E2O2aQRlTzy5AXMpVMTHA56nS7X3/wlfgZaJjwy5/H8M9M0piocrrXZ2I0YjBWdvSHLs01sx+JuZ8Rue4xKc5q1Mn51SKYlmVvBbkyxtR/SevMyz/7u18BxIDMonZOrIhVH6weB7cBE+jD5fZYr/FLAqcef5YODFoGf4lYElpMwGFkM4hxLJNhZwjgqYrM8r0ae5UhhM4w1caa4f32Xa1sdaqUKjmXTGkSsb0Tcl1u0FoaEYp7PfeEP+fUrf8nO7h2GCq4dDmmNJA+ZjEdPLdJ1Jb1hRJgWHbYlwbOLQmWEIJ2woWcaNXaHGZbjIbHotPscjiPaaT4ZcwzSFHzAYZojhSJOHeI0Y8qtMhyHpGkRGFsu+YTRmFhYVMsux04dZ/7UKh/++h1cOeawm3A4GnL9YEA0uUaTRNC3T2Cfe5rWB+s89vQl6B9gZ11OLlY4deEL/PQHr7Oz9gvOTUsapx/hXrfNBz97j2qjyszKYzz0pT9l5Rtldj78BR/+8gfs7LbYXHmG3Y079JIBW3e22B/E9DMol0pIpXG0YrE+zeLSPJWls3z9979BqVomU7JgihuwpPVAWjY5LBglyLFwA4uNa/cZ33wDX7WJM4s8y9hpD+iMU2Ik+XhEIARz9QrlahllPKIowrIsosQwHMcEnk3dKTFKQprzS4S6xMMvvMz8488wiiUqzdBKQ9mnd+1jzMFtZtcDZpp9rmxcpp0eAB5TczXGnT2yKKZcqeMAETmBEQy7Yyqu4dmT06x+67/k3R/+JXs3tti+0WZrs8fMhWc4Gd7GdwZcN4v40xW2+prQHMVYfXogiyHntzOpfkuhMqRZTm40SkGmNGmmik5KFfSE4rsVtruObSFMsY60jKARd5mZbpB092mu/5DfufA1oi/9n3n31be4/qN/zpONEY/M1GnYBs9z0EqRjlPcis/SuTM09Cof3N4hyyQjA8cvfZ7xzBzNqRnyLEWZApYtOqe/5Yf9G6OWMQYsC61ycmOTT7he9cUlnv7GH/PBj79HX7WYKiWEHcXe/RY3ttrc2OkxVIKy7XJtb0TNl+z1IiItqdeqpAeH1KZgau44SjmsHqsxc3aKMIy49vZlGour5EmP2eXjpLkGkz0QawsKJ1BLWwWVQwgsYaHznOUTxxm98BL57h3mnB73N+8jsLDVIVkaY+wKXrnOwUGXTEksrQksQSYEcRbTz+NCxS8yTp+awy+VuHVvh83hFW5ebXFwuIfOemT5CKMEUmpiLemnhnv7Y1S2RcX3yPIiSsl1HISBJNbkFmSZJlM5jhRMV8ocDAr2vFAa6fqkeghYYAoujy8spjwL4QiyVCAcwWyzQZLEhGGM1pJUpaRK4NoecabIkVz51evc+/Bd1m/v0u6ltEcjulGGKVY01AIX5VfoT6/y3zy5xMJqhc3v/D/Yef89kqhPpTbFiaef4rSKOPZUnc2NiK07B9RnAwaWxe37hzQOrpH3/zmnX/wa8zM1Hj45xZvvXePW+g1uHO7RDxOEI4mNwMHCs2xm6gHz9QrzU4v4s/M8+82v4AY+YZQjbRdhWcXYM1E5IIpIOaUVYPADyb27PbZe+y7L7j5Os0QaxSSRpjtIkLiUhSCwoOZbXFhukiaK1KvRfPQhPvjkY7L4EMdzcazCVdP1KpQXVrnw5EvUTz3EYKyIoojcMRi7gohBDbtcWD3B6lRE0v4BX11JiZ3jvHl7j2cePsMvX/k1SkkSA/uDPvsmZjFwuXBsiTPTDQIrxL76PR4tjbn30Bn2RjG7m5vYB79mpfEO9WOLPH/pGzz00HNc20/4+aamr60jhOPBdT+p2X9rqfqtScmZKjqnXOmiUB2xzrWaeD4Xh8pIC0dKWrc+Jty4Q8UrMdPfQrke/W6b+r01lszPKOUJi9NlvNMNvvboGXbWDjnciYuQTGmBMKS2RRrFWI7Ns4+fIeu2GU/NYZqL5KnByg1aSLTShUbugaBXHlXYiXODeYABHYmqC5Jq8WdqMn3JwsCaLEywvYCnv/WPuf/ez7AOr1KbniK1LbrrXSzHR2YRmKL17UYJOQ6lso/remgpsf2A2eOLDAdjlo4dpxPlaNPnk9d+gKHGk199kUwfI1UGowr2uzwKw0BgpC4IcuIIG5RkecbyiZN8dOs6jq9p9WICmWHFMV61yUZnjMlDpstlpM4YDEdQrTBIU9I0LgTVccLYEty+d5/luSVwyvhOwnR0hyED9qNBsRkxejJ+alKjyZTNTi+hGihOzDSwhcsozSgFZeIoIVWmuJFlimqjRL3icsGd52AQ0x+HpFFI4Aq0EkSmIAC7wLzrYOcaz/Eouy6ObWFwsVNFFGWUfJ84jmnMlImjkO54TDQYEOcJlrEY5jmD3DBShlJgODdd47lHl/nexy0a7Tskr+5Qav4OsQiZmatyGNVJYsPm3XWyaMDGnTaxtHEHOyTXFYgSc7MCk7YJE4vk7k+Ijz3O7XiGj3ofszGa+IbbFlmmmKtWmSoFlCpVHMvFtlwqx47x/Ne/hvQrZFkRSGJ0QVY9ovccnSNjBEZYSN+nv3NI8sGPeGw2xLN9VKJxhGAjTpipOCx6AXmaUSt5uK7DXntAGIU88USVR1Ylz597mK3NA/71925xEKU0K2WUVaU2d47cLzGMM4QRbF9+h9njyySlOp0rH2OPN/jR+odcv+tx6fgUJWHT749RSnLrfovRcIyQPmk8Zm6xicwTBv2YW60eV3f2WSwJHl6/zcLiSZ763X9GNe7wH/7VP2dnv0Oaw6NnzjAe9fmz/9v/nSweUn3u9xg2HsHk4lOuEEVH9Ztk0P/cQjWxOzkqVJ+yzYtvYiFRtmDKTlhuODSifT7uvsmtu7fYiVMOTc4Xn7rIUy9cItzbIOzsMX/r5zxuTfN/ubrFJx/cJYo1FxfrnF4oE8eKwHNw3YBxp0+3vcd01WUYOpQfeYHU8ZBZQqZNQc3/jEaoqNKfFiatP8WAil8mwPpkH6iNRpsjTtgEH0IjkgynFFA79Qy3b33Ac/4IldvUg4CDdkjF9UGA72iMVSJURTgqlsXC7Dy+E7C0uMChO+Sjj28yM7/E9OI8/seS2vICldnjZCYjyfKiQGKwKLAzIwpdVLEgKPyLxOQC9zyXTKVEucFEkkxmBJVZMBLf9CkHAmnn2MKhUasQJgmjKCLPU4JKiWZ9BhUmSCG4t3uA5deYmllgGK3TkJoehniyCS2M+iBRhkQZyr7EDzywPNr9ARpBko7QSmM7DjrPEcYQhhnt9oA4zXF9j+4gJstzTF78jDXbmhxaTVBysW2FYzukqeawPyZXCqM1fuDiCIvEGPZbHVzbJs1CkihB5QrPtwgcm4VmiUUMJQcWyxWefnyem7nH9OYeUc+wcXnA6S9+kcj+GacrLr2hJph/mMtv32avu47tSgIjiY1CS4HvVBlGLT68tcnmTot99QnXdnsIW2KhaZQrBK5kNvARGrI8R4UjRDDN3LFlvvp7X2dsVdFZhpAF+fnoHBUuI0w2YLJInxl2MLFm49e/ZIF1PCGJ+hGuyHGEoC4lM0sznDm5xO172+wORhyMEjbaAyJlaL95l/W1NlNVn5t7HQZhitKCdihZfOoZaNSQbkCWaeJByt7Hb3Lw/mExemvFQdjh9HKTGIt/+eZVnluYo+5LXMZ8fPUqFaeELNmcmF9idaaJnQ3xThjubbV4b/2AVugBFeYuHOfWG69j9j9hfmGW/faQ6txxhKPoDEecu/Q093OP+/4yIs8B5wFt6KhI/YMlNOqBZctEs6cnkTtCYLsWfm9I9cZfc/6Ewkky3ttaZxwnJGlEmkv++rUPCMeHfPPxVQ77Q0QUYknFY5ce56ev/po4Tjg+cjGUmZurEY4SKo7NuS9+m3ubPXo3foywA5ozSxyY4iKfTBHFpmzi2yQoDMY+tZrRnxYm85sg1aeeWUfSoOJRBFIoZJZgey718y+w37qGnUVcPDlDvz1mEKdIqfGDAK1Tyr6DF0jiNELFPfrjIW++9nPK9Tmm5uZR4zb7vUMeeugSt/b6RAmF9MEUok0mYaNSTjorS0481Is47SJ3VGG5Nt1RSL1c4fTZFca9XfqxZGf/gJqVUvJKSMdB5YYkyxiNQ7KJ9nIcZvT6hfnfEXfFkyGjfouHTi0xHHVJKh73BxH5A55EMVKPc00p1ViWg+uXSLtDcqNJ4rjYqsYxRhd8p3GckGpNybdZqgVEMyW0DNBByI3NAzwpqXkevqewtOHE0gJCKrb2esTDGNuZhGJmijzNyfMioSXJRxij8R2LsudQL5eRJsfGsDDTRNqKirDpH8T8yR++zM/+h//Abn9M++r7LDx1kbSVMN69R9CoMdhV6GSIU6pRKnsMxj20VLieT5iCV6/R9HPCcUKUD/HtlKl6mbzsk8YST+csNcsc9oY4QiDcKo3jqyyePsEozcHJecCHERP7YaUf4LyZKsIWhNZ89L2/xIm7JGGPdgkyz8ZWBmVBrBV5bmgPOziupFyRLFam6e0NkK5m3O9jyDH7I+K9Hvu9EFsKtKnhNVc597kvoLwaSZZgYdj55AbJYIPUjLEnhyewLA5bA2YbEstY3G13efr0HAtTNYZJjCNsVmYWOVabo5rFzFQcqoHLyWoNUa6zOwp47Ou/y9JDVa7+9FXevbaGkQ7lUo3l02c48czTEHiUPJtzTpmf3c+5kQuw1INs0Afj3z9o9DNMDnRxlB/YkRhwHZedj2/ifPRdbvfvce+qw7curuC5Lpat0alEU2h7f3J5nfZ+i6W6x1onZc+axZp7GJMblms2J2YquI7NsNulGtSYKpeIhiNqtSoHh4ckoz7jGx9Qe+EYncxCG4VW4lNX0UmL96AzmgCW5jOF4ChH7+jvPHgceW1x9IYZMqWoVgLqz36BW6+mTA0/YdZzmW36JH1JlqWM45zFuSbLs1WUigkzgeU3aMwucfm9y+xsbWGuCOZmZsgyzfT0InmccO+9N3jkSy8XW0p5lNcnHkRqFSEQR0nTn95rLBuOnz2LGPYYxVt4js3O3iHtQZ/FpTqeYxfJIzmMxhFZrki1emBn7Loug/EYg8S2bfJRSBSNsWTMqePHqA1jonyP/XFBttVojLBIlGacKpIc9ts9hlFcBKpaNsYYpNbYtl2s3DNNpgQCi0F/SCVwwfF5rFZj67DDYZwxHmU0tUWp4mORobCwbAeRFra1cuIgMVY5capAFCRTy+RUKyUqno0gZ7pZhTSi4gqac1MQhmS9EHt3i2GUMnQEtO5x7/UfM7tS5fBqgu70GUUd2lHM8pkZjN3g4HbE4f4upVJMs14iFx5pYlPzPBoVxZRtUSrNEEeK9d4GWkryOMVFEFo1Ss0Fls+f4YnPPUemQJkcY+RvXItKGzJlyBVk2mA7Nv1uQi/JmUm6+EIQjiHpDwlERjmwqfgepWoZt1KmVquwPFtmsxORRocIxyHVGksb7nf6xNqghaAkbRKnyqnnPk/qB6RRinAc2jfX2L78M0ZZSNW1qTs2YRJTqVTojsbstvaxlSRJNdc2WpQbAd984RwikuzspIR5SqkkKZWnybKYKBWcX32Ih3bvcc7fR1jHiTObUSqxbIXIUq7fukNp6QwvfOslaqUK9z/5Nd3dLs7C0+STmzCfLVb/EHrCEfAsMFjCoKXBwSBth3g4ZuvyD3mmqvmnX3yCewObN7eHWF6FqfKIcSRRdkqmcgaZ4a/vdhHagLFZPr9AVWl8y+JU3aVZKtjejl+mGVSxPY+1d16hlUc06zWGtsu9a69xfnmR6tQZhFcmFHlhYmcURmUPVvsP6J4TETVHwJ3RBc/KfKoHNJ8dHSf8KyHkhD+WY9kejVMXiT66SxwPOT5f5/bBfTKlGMeK02dP4juKTMP9wz45Y8qezx98+w/Ya4/Y3Fhn7cY1VBSzE4+ZqTZJD+6xvXaC049cQGchAoEtJa5lFUEPViE5OhrgBRTOEyrnyedf4MNfvIaOB/hCUoqGnDw9RzXwiMIRYZQQRtmDIuJIG9t1yPME1/NxHZ8oTorO07NRuaZ1OKDRaHJq5ThBqcLlm7fZGccoAwKNsgSxNnT6YxK78L4SGlq9IVIYXAtsYbCFJss14zDGdwXSLozaci3QSciMJ7HygEjlhLHGrftIz6HfT/BcnzBKUbmmXq9j2wLHlgyHY6LMkGaaqucglaZsW5QDODY3hWcZbJPTrATYJZvAaH7xgzdpj0fYQUAUpbzz9jt8fvkP6Kgao+4hGEOlUaI6W2KnNebs2Yc5aHXo9AZ4jsbTKZkMGHkeUsL0bI1OJ8Gp1HADF5SF0gm5chGNeV745u9y5vwZhnGItIqRxkwsA7RRD6g9hWusQmIjbI+d9ducn3WQYx+MQKoEldrksY1tFCpPkMbHkhatKKFza0zHOIQaRlGE61hkOifXxQ3NnVwzQd3l2bMLyFLOmiqxefl97r31HeRgg6myZKHs0+kNifOMsNfFkjZCFM61mTbsdiKW8Hjr/T0OWz0uXnyRkmeRjPfo2SnCaIajlHh3H+GNGd//EDtss7La5JPAJVcJKk+w8oze3etc+VGfhaXjTJ04waNPPczl/YyO1jgmI5cTUz3Bg+v971WomGAkRwen+KIGYSlGYUhjYZm6bFE3ivevrrE+gPmyoVL1mc4Vm/tjMi3ROkdLTWoEFcfj/CPPc+vuGvOBxWJQwxiYLntIWebdzTZQ4+CgzSc3r/IHX/462gnZv3ebhfe/y/TMKXRwAhNUKM+t0MElLypq8YoNPFilPeBTHZEXTAH+PPB8F5N16We2D3zK60jSlJmVFfZvziP9CDkeU7UddiOFsTQfX7vB9DOX2O322O2MUdpQcu+wud8hmD3JqYcf5qFz57h1/SZ3bt9mv31AWRkqB/ukp09SK7lopbEsWaT4yiLsVRRX+4MwUjHpruxSDS1BKkVoIlaWpggqHhhBmgv6w4SS5+B5NkbbpLlG5YW0IooTRsMRYsJ8T5MUKQvqSa/XZTiKyEzMkycaNNoR1/eHZKboADJhiLKcwHZwbUBpHM8GrbBtSZrmuI6L7xW6Lsd1KFUruL6HjSRVGZ4USKMJhOLs6XkqgcNhd4DBI5ys2FWuGY2GZFmCtCS2ZeNpTaPso4yhVvFoVl1mpnymGxaeYzHoZ1h5gkFzea3N+7cOmC4F5JnCOBatKOWjd97h2ImzdLd3qVTAxBHpboc0zjBBzvPPPczN6+t0+33qAoylsW1wsgCkw+r50+ztbuG6NjoFlQeIxiLPffNlVs+dZhzFSNueXDWFs6aeQCbaTPhS2sDEI//O5TuMrv+UOafoOquej2Mc8jyjVPGoTU9xZ+By15llr/EQzdkZzI33CNbeJ473sYHADhglEQqNkJLMGGKVMRP2Sa+9hzx1nt37go23v4sabmEbmHECLAW+65MpQ6wEeZZhWRKLIpNTCyj5DtKeIREx0pG4SOq1Or6bM+j1QWn2wjG/vrnF5+/t88jyJidefokvv/wC7736a0IDcdxjd+s2h/dvsDjtMX3mIc48/xJu1eeDpMbuyMa2j1Quf4M/9J9bqIomfgI/S4GlJ7l0rkWn3aU77HI93GNtb8iNVsphFLJhFHXf5clzxxgME+JhhO0Y8szCtiyevLhM+/417l+/wUmRsjscE2cSIS0Wpjz8qQbvbva4v3YHjMW+XeeRSo2Ljy9jC4E3Xkf1t3Er87TDLu7iE+TSRmX5xHOqKDPyqJ08ktQI8RnjvqP3xkzId5MiNSHfFfXL4BiNZaeUjj3O+idreMawPF2mG8aApFz26EeK/X7KODVIy3Bnq41lDzHbe9y84hOUKzz/0kvMLB3ncG+Lna1ttm9dZ+HMKebOnSLPioJRjFNFi3cUuz1pBYsRS9p8cvkD9PgQrT2yLGRmaoZUafb3W/SHI4R0cFwbz5MgPDIl6I8GRUagtAj8gCROSJMEx3UmcWbFD2yyIcpWLAR1nliqMYpiNoYZykiU0cRJhvEchJFUKxXCtE+eJWiVI6VEZTlK5gSujZSiKFKOy3gckudpQfbNYpqB5KHFOrbI6WeK0TCiXq+jNQwHw8kSwSbNMvJMUws8lmYqWGhsFEHg0Kx6TDU8qtWALIkZjPocjjQ/utIiTFJqnkRbHq7jYDkWd+/dZ+P+Lg1LYkkfo3MwI6TUOCWH1VOLXLz4LX75y3fY3rqHkilSgS8FWSCZOhGQxQl11yG0LMJgnktf+iIXHr9EnKQIWz7AQQuFxqf+/UeRcUJKAs/nyru3OXjzR6zWW3i2z3iYkfZHVHxBnivWvWPc3q3zcS8gLs9hjTKcbsrq2W/wX3zjdxn/639P+/KP8KOUJLNIZV60EpP0pG7U4ScfvMsZ5xib7/6cvL+OrTSanIOhLuy6VY6QFlKCK50C+phYMtlCYNVOEM40qYUHVMIWy1M1aoHAt33sKtSnZ7lQCrj/l3/NfqVKo36MG995jS/97/+QWEdcfvUyZAmDQZ9ISfa6AxrtEfutQ9q7LV74o9/nWv0x7sRQCPXB/MM6qkkI5iRu3Mgcxy5x68Y6/Xu3aFoJO91DDuMERzr40qIVxoySjGP9MSeWZjE7u7RHCVpoXnz6FCeX6nz/lU948lSDS36JucAnV4paKcDkGacWl7h8sI9TD3jumS/ywbUbLF08x0yakYoMoQv9mYhCphPFILFxVh5m6DiEKVhCgymKkhDFGlRO9HVFwfrUw/2oYglzNGIdtewFXmKRobXH2vYh/XsHLM2V2OiMEZbkeKPOyaUaQVmxbed4rkYpTaoFWZggrQQpI4ajLj/74XepNac4ceoMz3/zKW7e3KJ9f4NzD53EmhA8pdR0Ox0ajSoPtEB8imsPuoaPX/0Zc02Yml1m7+YBWdYly+WEGOqS5jlRnhCPBVmisG2XZnOKcDQmTnIsCY5bOJeqyVIEI1C6eA+MFuwNxli2xfF6Ca0itkYpmYBYG4RlEccJtoRG2SXJJL3+YBKsKibOow725OD2JnffLFNY0kYCtaCEyDVW4NNsePR72wz6fVzXZWa6Rq87wHF8cmWQMiPJDZ3BmMWaS8WXlF1DrRqQxzmjeIhMU66uh1zfGdBOcmquXWSwCFA6I5cWCsnd1oCZwOMkFnYOjqOxpcJkKVG/S+AJnnlqmVIAO1s9tFbkKmWqPsONTz4hH7ZYrNdwyseZf+oLPPrc46RJipDFvIEQaKUnM8iEvqMNQmlcx+BaAesf3ye+8nPmvQOiIcSDHrbSeEIzDhVKBvy7Kx+xlXpFh2YEslTGm5qmd30OLj7F57/0TTpuhe6HP2eU3Me1qiTUaC6scvL8KYbhgJm5Ze7ffJ/BzhWMSpFYWGhClSIpZGy2ZWF0wYk8MhAwRlMJ6pyYmua5Z5/lnhSo/hbhOKfi1ImjBGFZqDyj6c/w5KlVTn7zj8hFg1/8j/9Xrn/3Z8w9dJHUslitV5mdn2NfuIxii5IVMR4n3Lm/Tf4v/w2nn1pj6uEvc2jNTLqif5CExuDYEluCNjlC+Ny9cZc7b/2KgJyFqWkG2zbCRCitsGwLRxgyrelnOXOWYHVpBrPdIk4l6WDIntb8n/773+PCksX1H3xMe2+A7VhYlk2lVuX6WDOz+hCluTlqsysMfv0qW8MTiG7KTAWCisd0tYLRCenwHv39Fvc+ucKxS0/jHj9FKFyM0kXnx6QD1ADyAd4mHoDpR2Pfp+OfNsWom2noDw3r775Of+MVVMnl8p0dLK0JtSbrDKhWXKaEAnIkBedMaTER7BZjl23ZRXstJO+//TZ7m1s05pcxSjPq5TSnfJSK6HQzXvnJL/jDf/QNjAw+8xkU27fhcIAwbTx3CSEks4tLZHGffDzB54yi7NuEScZwFIGQlCyXwAhUXgSpetIiVyHaFBso64gOMeFo2EYQZ4rhMKJZq9L0LMbKpRvHRMbQGgzxZUA5sKlVfJzYQqVVBJogsGjUqkjHIooiwtGYNMuwjWYcG0bDBE8Yyp6NxGB5AY5l4Xk+aZxQrzapVkscHvY47I1xPIHvSFxJgYPZgpJnszxbo15xGaQxThDQ2sy5sdlDI5lxbcoVD+kWazetc3SeFjwyreiOIxxjmKOMb2y0pYhGIYebKcmgy8ziMp/73FNcfn+HMApRaQRxDOmAKDdk5TkqJ87y2PNPkmcJgsI9FooRRk+2yFqrgtpjSUQYs/P6L2nHFtvXbzDj97DsHDeQlK0SZQeSMEJKn1bu0clCtAuWJVGpQUch2faIvNzmRuDiuYa5809Qr0D/e3+FsOY596Uvc/rp51EEbFy5zv2bb3Lv2hugYqxJUrJCgxL4tkXgeRPqkQKtMJObszaCsi+Zn/bZvfYRa1trPLQ4hzIh/X4Lx0hK1QaOBKek+MqLz2BOnuRXr9zmXrvD1mGOe22LYarZZUglcDg1P8WJpx9lmDrc291j6ivnGS1d4qqtyBILykdymn9ARyWEwLUnd3zj8cnlj7jxxk9o1muoJKOz18WxHWpBiVGcgC78cMI04bAz4ESzgckU040qB4dDrt455MRcQnLrLn/5iz3eutri1FSFpcBmlGrubaTc91NmT9VIxjHvv/1rAtth42CD3XZOdLhPybKYqZepBTZxlNANDU4wyxm/RzldZTz3BGHzGKCwspx04qX0aQclCorDBGg3D4oUD4ijRliEgx4fvfkWw911svGYdu8QCcwEZUQcEaUpm60uiZhhlEo830MLG5MU8g9puXTHI2zHQVqCKBxjCcPu5h0OW7tUqhscbt7n/Oe/SHVmjrf/+i9xdI6LIVMW0tKFH7dlkcQ5b/z8x9hpl3RQYk9oqrZDHsfUpj2ELhMOI7JMk6caIYrNngWMwgiFIMtzslwhpMSyneLO6rqkaVpwzoRASUGmDanWuEJzaqlGOVJ8uJ4S5opBCmEqybUgzTKELjhWAGXXQauMUTTGdl3yNKPkucRxwn67U7hrSItIG4yx6Pf71CsVyr6LyBV5mpHnBV4SOJLF+QYz9TJ7Owf4FpRsm2q5glXy6SYJrl9hEGs+ut0i1zaWZQg8BxtBkqQFnqQFgeUQlANmBzHDMKMThUjb0KRM2S385vNMEMeS/nCDUbbDKIFS4NOYm2IcG2SYoFwXNXeCx55/fgKYF9fOgy3yJGatGPd0sdkyOTrwuLOfMO5vEdiHVJzCILBR8RBxjJdrgrJA2hYH3ZyEorPXtvsgDl0rRRSG7K9d5Y2DFk8//hRfeOI5AqdJWzRYfvJpNjd32b3yJoc3X2P77mXsLGLaL6G1YqRThLEQUuIIQa5ybNtBmQKZ1UdJwUIwzjM2dvdp7e9zolHGUYqSLyn7LqPBiHtrd2lfjfncyUXmTpxEXb3OKXmX86dnuHn3kHGcM85ShGMTbh5wajTkzAmHcw8/RmvYYOr8V9nTJewsIxOTdJ4jzszfv1BNDOjQxGlCo27ze//kv+TyOx/RvfEO0pbY0iJL0wfcpcD1kQa6o4i9zoDl6TJGG+qNgMxoepnLe61pfvHeB5gs48xcGVPy2cgtPupHLC2vEg27NEo2+9vrLJx/hNHaxxyfmeZwd4dEQb8dUbIdHNtBaQt33KKiLWbju9y5csDs8qPsRhmm6mOtXiRL9YM34miUekBpgE9HP4qfQVoWjUaVP/gnf8SvPtnlh//x3zKOe1gqIiNnxi9RVik6y1HCZRSllAOHxlSdbqdbJMJYDiXfRWuFylLGgy5GQC4hj0cYFGne5c0fHhCUZhn113n4wtNgORiTFiTxCSfM8yTPP3+J93454OP71xmOQyqlCjOBRTMeMDdTwnYcoijEaIPnOHieh9KKPMuJk6xYkecZ0rKKJCClieK4SL2REtexiNOMMFEErluM475PpeIwHmXcOugRY2gNx1RsTbnUpF5xyOMIhI2xCg5aUAomFKwiqn2vO2IUGUYaRmh2O0N2pms0ajAeGSwhcG2baDQmjsd4jmB2KkDmMbu7o2KjJW1sLUjiMf2eS6s9Yq+1RXcc04tz0lzjGMiMIc8Ke2YchzwrCsfi4gLpOCRVfWINozTHjlJMrvH9wngujsAa5ER5juN5aCJi38OuzLHTiphdOctTL75IY36WKMkK9cBneXuGB9bbR7c+K9d4QR1v5WHcK+tUXRcVhkjfxpeSctVnZaaBR4pddhlvSUqbiljKQqwsBMZoLNsqch5zzXh4wO31ezx7bgG9cpqp2gJ3P7lN++Yn7Nx8he72NVyTU3FsZitldns9DAYpJA4SR1oTrW6CUjnC6MkYqKmXA2rlClSWmdc+D9Xh1FxAxU6xHEnP9TDuFNeu3eWN69s8ZmJ2rtwAPeaZJ57gzvbrkBbUlnGmSA2oTkz5l3dZvLKDe+IS5URDICAHebTg+js8fmuunzWxSil5glPnTqKdKsn7G5BrjJsThWOyvAjUtCkCM6UxqDzn7m4LX8J0xQGjqNV8qnPH2TQ1hpmhZDS9KKcbDfi4FSIaTeZSw9Mvfpkrl9/g1KXP0WltkPTb9HSOLSSWAIeiXY3zFNvy8Wyb9Z0B793toZOQr7gxteYJdkcBuVIoaZFnTBQ2BoMFJp/cGSfEUCMfJO5YJsexPd5fi/jpK28T6YTM9kjSiPujAQeZxYlyBTeHTuuQRrWGxrB/cFC4SSiNShI8xyPLs+KCsCTCWLjCJjcJUueFZ5eKUPEeTn2FuVNn0LaLiWO0FBhjY1uScQjuwknEKcWx5dNE29dQWcLp1RUO71zl/uY2rmPhYCgHHsKyMRSxSWmWoXKFAhBWAeyKwpZGa0OaKWxLIG2Ja/Iid04rskyz2xpy5swSx2o+h23JMNf0c0MnzVmMQvzyFKln4zoSnCLSCiGwPJcsg+3DPu2RohMpWlmCwhAYw9buITO1BYTWYEkq1QBLGZQlGI1DbFtiaUh0VvDLLENtuoa04PZmh63dDpbtkKqJFTYKbQqirBAS13NZWJwnTTPyPKHTblGq+lTTCDFMydKMyLKwhCEcZTTLLo4jCyqB0sg4wUiB5fq0dzZpVFwufe6LLJw4wThOi4Mvrd/0Z3vAm+LBOGh5Ve6u7ZLefZ8ZEeO4Hv00JOxHJHGGY6DsG46vTGE1p9m/d4BlWfieR5jmkw7TQ5schCbPx1j4tPbu8pN3KtjHz8KdTaJbH3Hvo1fIws5kiyaplqocDsd0lEJJSQULS0ps1yFLE7IsK06CKBYf5IrZRo1IKWbKGi8zeEQ4aGKlCVyHhWMVVh9a4na3A6UmtXPnee+VnzHsj9gR28S5QBlD1Q3wSyWiJGScw/V2wo6y+fIXzjO1f5WDk08y0BJHJpijfbzkb3381q1f8USCtjBC0j4ckscjZGBjTI7jOLi2Q27AsiWebVMSZeJum14Uc3O3xenZOuSGznhMHoxJR3dAZ9TLAfeGIfujHOOVqeSaeNDn8q9/gWXbnHruZQ6//68YDyPyMMWRAmMklpDkaQZSIojRbpn1Q0M/zjk1ZRHomPBwjXrzDOs376BWVrGCCiZLwehJiy4nxFBBkT2WTwitVkE8dDw+vHWFJO9gCYUwAikdjM6IlWJrNGLKcbm0uMTe3i6jwRBX2kSmAFhzpbCkQhtDKfCxpKHkOviWzTgDv1Jn8fgZpN+kNx7TWHmM84+eR2UZWvoorXFEjpQWb753i3ZniF8u0b57D9XbYXt/k6i7T9WBXj+i4tk0Sy5TtQqZ1gyGBYCujCDRYEuwreJ16TxHAKkwxELg2YUwe3Z2Gsu22dtvobTBcQRCGJIkpuLbkBgOMsX+OOdYmFFLYhqNMo5dEFmETNHCZjDO2G+H7HWG9McR/cnd1SAINfRGGbt7I04enyWP+0jLwi8HBXs7FugsxwgLG5guu1TqAfuDiL2tAUrmhZNHmiPEpEOQCi0Mnuvg+S71eo1Ot4fneSRxgjEKy5LUqxVsmTIYjeiHEd0kZbpaRfVzRg40yw6etFCm8ELzVUzgCpZrDnNygCUknnIQZCgxcYplYig5yRI4ShG3Ms3OJ+9w5/WrpP1rtOMxahwy0jk6d7h4rsJizUHVYFiq8ubrt3n3RptRX+PNLeCWAwSiSJ3SeiL8stBKE0Uh73/wLs2DQ6aqTc6dW+X+LQdCjS0Kf7i9QQ+jDWMUAqjZNq5jEyVFyvRRIyKAPE6xpKTVH7ByfJXhzl0CW7KwMkOz4dHqdKgEHo1mE785yzcfWWL6uS8xtk+yEgsWR9d4a6/HeDgmsCXNRp3OcESqNI1qGVtqjBJ0uj062zuIXofgwkvk2i7oT7JoH/7ezHQoLi41ES0l2uGtX7xKWUW0ojE5RdqvRbHiF5aFkAUm5FkumYLOOEGaPovlGtVKjSTNOdi9StmS9FWGiWGm3iDT4FsurutwYr7JlRt3yNKY3uEAWxZ3ecEkQ1BpbMspUjeMQ9sMce0AR9rshzb//s1NwlwT2+sIfwUaczTOP8rsyVXqtQB0Rp4bhLBQKgNAWgbbEgjpkxifrc2IQb+NbQfYjSVsv0EyHKCTPo7J0TqiF48ZpTnDKGaq0SQZR0RZRjp5rRjDdK2ELUEIxVTNo+K6jHIXUaoRBCXu7+5hew5xPKaTWkwFZfJoWPi1EyFEBZVbxP0OZSdFjfY5bO8ziiL2WgcMpCZLcpQxuI5N07JwHRs7SViZX+L22n36Ycpco4RRGbaUYFlF7JURaNfgeT4mTwlHIxzPw7ELKcvC3Cytgz5hnFH2XVzbotMfkCNxK1UWF5pkWUScKkqlEo522O/G7HQjNjpj9gYRNoZMFIpGKBJ3O5lmoz3CKzvM110qro8VeIgswyQWxpEkmUFbYIRh4yBE5ZqnHl/k+vU9MiPIc02eqwJ3syTaGFKVk45z4iQhmVjFaJVTLvlUKkFhT2MJamWfhJT2MMO1xjQCF1lqYupNomRI1OvSFC5JmJKlOdOzJ4m27hKMz5OXV8jzCTcQgckLTamajH3F5g86Ycb7P/0h1rDNME9I4hTfF5yenqHh2HzlsRlOfeFJ1i/f58++9wkbrYg7+20SfPJ+Ga/RmHDLJuoCIRHCejBiiiSme+8W8uQZDtIaT778+7z7kz+HYQcXWWRcCnAorMA920bpnDTLcIR8gMlaCHzLwbgSY5cwWRlXxDxx8XFmyimWlbK4dAzLRCBtPCfi2BMr5OmA0HcYHCbMmCFPrc5z+5MWIxXSi8ZorSn7ZRxLcGK6SXlmCdsJ2Esd+tKjZgVILbCsdEKy1v/pAvR3K1Rm4uRYSAFEMubJ585y+Yc/pSwt6itN9rd3ioNpO+R5Tp6rAsh1XGyVkxlFJ0lYmraZnXL55N4WM3OL9DqHtEcdHGwqSYpbKWEHAf1+n1gtMDPb5N7Vt6jIhNgyhFnB99F5ATg6EyAQnSFywTjtU/dKpKlDOIzxAw+pNCK+Rz7epW9C+q19aseXmVteZmvtLvWKz/KZFXJdIkkkW/t9bm/cY/ewS2oMSljY5SpG+xinTqm5gs56qNGAvLdFGOd8ePsuvq2xbJssCQvXyxwq5QDXMlQ9B0xKtVKi5Ht020PcSolkGLEzWsdyJdNBmWj/Gm//MOalr/0O1UaDPIkQskIYa5y8w/xCk/buLkk6JgyHCKMLLyhpoaQiEZLOOKQelSh5HtKy2d3dpd0boY0gzXJsNEHgY9sWeV4IgFOjSLOYarmEoPDsNsJQr5XJk4j1rUP8IEBSgMSOhFAr1npjlqIGTd+nXnHwHIcozTm42ybPBVXbwqmXWFloEqWKq9uH9JK00DN6FjvjmGT9kGimytkVl6ZQYGuqjRJpkuKlGbI+zYd39xmEOX/08iMk+ZhIKUbjIlFFWgJNkcRtWRaO6xCGEVGcoA34vosUkigq1vJe4OI4FkLCgi2YKzvUaxUSA7u7LfxSjeXlE4xnVwjKUyydOkl9Z4fRWHHx5W/SWr9N49FjDIYdao5PiIsWptioCTmxbFZIKRmMc7DLpOxijGJhOuDREzMgBLf3RvzlaxssXO1za7vF+iiinWQMVQ75mKx/WHSBno/WhZeVUYW8SE/8UbQs+FDt9Xu4fsCZkyuce/pLXH/tr/FMhiMtUqMIjMBxLFSWoLSeUPMMjrTQwiCRRCrHywSrx49x8vgiz64onPCAcSehD9xvDWiUcmpincyxOPvIKmpqFWnBjdvv8GFnl6XFhErVp98ekUU5HoaVRoWv/5PfY3Bnh/FoTDJOOPnyn7DhVtBJjGdbCGFNkCrxtzIU/g42L6ooVv8/0v77V9M0P+/EPnd40ptPPpWrOlX3TM90T9JwAme4FCmJkkhpVxIlrSTIWKyNNWDDf4H/Af9kwIBt2IB35bC71u5qRYmiSJGUxCEnD2emc6xcdU6d9OYn3sk/3G8NZwHvUCAPUF1dfdCVzvPc9zdc1+fyDp0lrFawOH/A9Ylgoh3TYBFSI5SkbaP1IgkenWhUG83L20XGi4fbzOanXNoaMpoUrCqNWEmSRNPhMVUDsmX34BJ5PsBVj+iqY4Z7e8yffvBMG4/UCd57WtOhpUQgSXWCcx6Hp20rWufInEbpjCY4hKm5uP8jdHWKb6d064ZZEy0gx+uUN967w9n5nHJd4n2L9y1t29C1LQKLaztkmsYWx1nQGS6dIMcJ1fwJVbOmbucMVJwD5HmK9I48S9nZHoOPL+hssSbNM+qyRMiWJG3Z271Cv69oVlPKpePDN/fY3b/C2QffJbQN2BYxv0fdSdpKcHF6hN0Mb2eLBamOlUpjHFYLTs/mXNrbRQTJ3naPZVkxry39PEPjf5JTGELAEmg7g8xyzlYNqQj0VAxYqE3H3dOWk9Jwq5eDlDjb0FeSlfG8f7Kkajr+9s+/ymDQZ7lec//RGYN+yo3JiH4vRsUjPYnU3Lw04qN7p+zvjDi8ssf3fnSXqms4XqwZLjIube+xqFusg9pC1Xg+vHfKg9M1t7cLHj09497RjJ7UCKmom440T+gPCrI8AyRVVaGFpBOOzjpCYxj2Moo0wVgDbUDKnPFwRNuWdHVHsAbvHGlwtOfHTO0pWTZgfnwfc/YuZWkQpuTeN8+49OqnePzdf8+6Lkm2LrH/4ueQBnzoCF5gfdwoS53x+MM7DNOGrRu77A0HjIuAtw3//R99xNJpvO3gyQVohdBw4/IYIQRvP55yVi2wIiFm0kR6hgixvfVR8MezxbUzHfOLCy72dhnt3+TaK19keu+P6coK6QV9GdOjXbAxXF3KZzAkpAevoQ2evsrpF31Uu2J6f472jkwn4Du2VGzLjkrDBx+ec3rnlJufq3laLPi5r36d//G/+2+5uPOEROlounYOoTx1PUOszknzIQ8f3OHF5z5ByHJC1yGlRgmJ3EhkAv7PcVAFME7gvSQQqBc1j777W1zr1Ugn0M7QS3OaFCrfbZKSPcmmVfPBI7Vi3hm+8/F9bl8Z8+VXrnE6XXHPd/gQMM5graAoUjSe7Z1tdvaucXY8RQnJ7PgJQcjIzXYxd05riXEtSHDB0bTRRlB1XSzHpaTqDJ3zdCKgdUrAM3v8gIt5hZivuXr7FSpv+cFv/jMuao+VCa4pcXUN0m1awkgzkBoEDluW4Gyc8WiJIMdlRRxyBo8JEuEse+OcBM+g0BxdzBn3cmzb8nResTcS8QGQhquXt9Cq4/TJOaZrOZsfcbVds/YOIToen89ZO6Beg3V0KKp2ReNDRNk6z9J0KB1hacYIUlkjOSdPFG2ruXq4RT4rwXp0GmO72s7QGUOWpWyPh5RdZFqP+jnadxRFxqPpktnKkCUaJRJMWyGVRScBYeLg+tIgoyvX3FvM6RUp1y6Nsd6hVEzD7ozDI7CmY9jX3Lq+xeH2mCLTXBlIrt26xbrqmF0sqEXClZtXUDbhd7/zNj+6d8K88eQIhv0UdIoXCi0DeabQeZ+6LgHFcDji5PQMAmRpQpACMJgO2saQPiORBklZ1jjnwDmUUDSNQQbL7jBlpyeZ5CnHp6fgE8x6weH2mKACiw/fw7ZrzNZVLmYJX/zcL9NKcJlE1zmWBikDQmhWK+ivjvni5/eQ3Zr7H5xz70nFRSuZ1Z4uNGip4sBeCDIRGEtJpRTGhxhS0q6xoY2GbZERlEL4DiEVHomQyaZlstSrGY8fPeL5519i+/mXKVLDRz/+LmkQpDpFEuh8iDBGxMa1sZFXCMFk0ONwa4sXr+zwylbgsOiRDjJynaKdw7WS0d4Wp23HO3d+m+N8m+3G8k//3T/j137tbzHIC1brJUpF9lImQaiUixX80e9+h9c+/TraBx6+8V32guCFl7/EkyqghCTIGAzj/zytnw8h3kzeE4Tgne99F9msKbau4NcVVdOhZM7e/pCPH937iV2nbdu48ny2tg3wZFHSKxR7kylnp+es5zXjLOPmlT1Ozma4rkPlgUcP79Ih6N24Ta8Y8OGPv4PFUwiNlJHI4J0DHbc0SiuMjbOX1thomHYOJzwJcZPUtDWWhLQ34KXPvczrX/kahRjwO7/7W+yGFRdlhQkFIWi8DOBjVJNU8YYUzuO7Du/iENpZG3tqCSLNCaWiC4Ym+AiBs45Le33WxjK/WJEgaKuKrnMQBG3TcHBpwmK2oqrPCVIzrSzzsmGweIJOFSrro9KE9nxKP0k5XZbYIOjnfXpKMVstaEPc5hkbbyNjBbbyCG25kiic8Qz6PVKlWZYlTdPRtQaUIssz8kQz7o/QXU2SwsHeNhcXU6RQ2FZggb1+gnWWLJEInXNcl6QSPn15zGdv7JP4mNJ7fHRBmm6oCGmCC46yjpHztVUsqybOzsSKUa/lYHdEoRz7l7ZptgrSLFBWnunFKYPRFjN7So1gICWZVpiuQesU41oaY0n7fYZigNaaxWKJtTEmXkrQIZArTUtUXkf1vSeRks50OFeTSAnOoGTgYGdC6BpyBet5iUOxffkafeX4+l/5GsuyplqcURxcw+Q3+dStV1gbAyGB+QlquI10GbmC1sPpWz+i1zzk4Z0pW7nmM5+7xpvvP+UPvn0XncYNdNOZTRCJoguC2dMFp41h1TqCTqKzwjlcUMhEIkyFM54QNKgElYi4GVYQuhpXl6zWKz559TnIBWePH7A+OyXgcd6hlaJfFHR1DSGgpMQqRZEkfPXFQz5z+zY390ZktkGGiv5QsPOF10ncHqtHZ/D0I7ZDyc997Yu8/Et/g/v3npL+8BHN+oRVY3De03UdEEiSaKy+tDVi2BthTEXW7/Ojd9/i8sVTfuXmhCt7r/LDWTw0pRAbTdefFZwHGO8gBLwLbF095PqXPkvSK7h444c8/P7vkw+2yHoF17qSJ2fnrBuPcw5r7U/Wt9EvKHlwUfPy7W2ssAyyls46TGPIkzSmGUtDdXHKmRH4leXw5quYZrEJHVUkQdFZi1ICgse0HY2LyAhjfFSWGwtKYnzA2qjGdWnC5NIlvvDlL/JzX/0yd+4e8dvf/gYnixkP5x2r2iKEQaqAShXIeFN514J3tNYgvI2sJBlvjeAiVtd5AWi09mz1MkZpgfCGtnasqjYie02HSjUHqeZwt0/XCoyF6cIgZWBvf8jT1QVCRKbT4fAyuVKkeUsySumsZDIouKhqZNcghWSSakQXKOOXJy4agLn1+EVLIiXXhynL8wV7l/fI0oT7x6c4JemnauMndNT1CiVgUuSM+pqTc4v2jsvjlLyGBE8vh95wxKOzJcJLXtsd8qVbB2gZqJuAQ5DlKat1y9F8znBcAIrpsqZsDGeLhkVj0SIw3cq5tD0kkZ7OJhRJQaZhdr7gzr37PD5fszUZUhBoEAwSTSqh6SzjUUGooyauKjt2d7Zo24bxaMh6tQYkTddFgiuBNBHUXuDKSMf0LjAejenqCuNiFTno9VgsSwZZirOOPEu4vp3T+hJfe9743vd57sXPodQeogvk/Y6Pf/xHtEHz0me/yv0//B1u/8JXSOQ13v/ud7j38T2mxx9Rnn7MTpFyY79PFywn5w0uGSBDzXDQZ7ZcYI1FI1lbz0nV0ZCg+jsUW3vIbBc9OuDg9Z+jv3uIqS9Y3H2Pi7f/GHfyIV44hM4JKHzTYdZrFssZRt8k7Q359Kc/zR//4Tei1m8jZK7bDiU0MjhaBHv7PX7xxStsqcDd99/myfuBVIKQgV4Brzw948Vf/Eusu5oPvvltnn/lkK///Cd4OD+F0fN8cXfCZb3e+Pwl1gWElDjv2S/63Bzv8Ornv8b+6y/ww3/1r6lRPJku+NZ/+X/h8ue/ws3P/RWe+m06XSDcn2eYHuKWLXiPRHD55ku0IdpLihe+SPPWm4xSR7+wHOxmTOcJq6r9iUEzy3K89xjTIbWidYFueJnetSukT38HISWz+YosSZgMh/SGQ3RecP3aVWblksxMMc7TyxK8bWg2QgIl4kEhN6C1Z9hhKSUuSvGw3mGDp9fr88Vf+Bpf/vrXeO6ll/idf/Nv+fb3/pjaKy5Kz7xsCUTGkbMbnyDgXEdwHRC3Os+2JDE9Jv4erIkzDhE8lyc9Xru+x4MHJ6yNIZSBpjUMhiOsN/RHfQrpkMqT9QoeHE3pjGc0yDg9fsqVrR79axOCSyjyAdVqTqIVxnR0TjLIM1wIlOsa4x1ZmjJJBbSWxjnsRikt8SwtfDArUXguC8HZ0SnDQY9UQJJpBkWK9JGNLkQgT1MKpVlOa6qVJXjBznaBzBKE0OztjVmWNVqm3NqDr736HL5cQhAoIVmtKopBjyAMR7OSnbTA1SWtcSRpipTdT3hgTed48HSKEoLdUQ9vL8hTTyIF+6M+VRNJC+NEUZn4YgmVYhtLYzvyTDEaFejGUDdrpEroOkOaJKzLKiJViL67ZwPjgGNd1+RakAhPlmqatqOfJYzylNZ7uqZhsLuDDo4XD3L0lUN+8IcP2Tk8ZGkdL375l3n87hvo6Zq8g/TgEN/vcXpySvkb/xVTu8ODB09ou47p9JydnqCnIPcwmzd8dLYiS2u8EXG+JCPo0RrDyhgMCcloi3RyCLqHDaCDpzp+QtdaJjduceOvfJbrv/S3+fif/xPm7/4xtlmBaSE32FJSzQacTGfc2N5mdPk5PvnqBe/++A3wMoqZnQcZlxAJ8MrePhOd8PEHjyO5Q2mM62hwvNCTzOVD3pj+fyjXkqd1xQf/9k0+Oz3n5l//h3z08Uc0y1PefW+FCCYO+kP0jFpjmamWJ+en3Hj0Y2595pDJtS0m93ZYVxL3ydc57lLk/buomztIiDrDP88w3frwE9V2Z230zrlAp0Zc1BW2WrPd36cpWwgWpeTG4BqwNuo1gogHSCoCPhmSbm2T93qItkJlGuUDMnhSlXKwt89rV3c5LPZ48/GSb+mMrBe4tDWhdYbz2ZymbuKanQjfUkLEttBDcI7GGoxzFOMJn/nqV/g7/+gf8OD+A37jX/w2773/IcY7jqdLjlYeLyVSxu0meITbbDhD9EE9w8CEDccqEGcIAkEwLcG0EAKPpzWz1WPwkAVHZ+oIA6wr2qbBB48eZKzXDVVnMa3FGEOXCnZHOXv9jHlVMh5f2ohQDVVV4WzAeYOUgkvb2yzzmifTGV3bkkrFJNGsRKByHgsbNbOgcoK3pg0L47i51Uf1M/qJIE9SAhKloJenqDSm7h5NO84uzrmxP2TU73G8bkApJltblCZQN45RGri0MyEXJU5Da6HrOnQiaVqHFZImSD4+nrGVREGlFIpBr6BuGnpp3LI9vViyblrqoOiC4tp2SpIqdoYZk61DrJUs65Zp1dF5x7oxHG4P6dZLGmMpBgW67VBasFiVnM/mDPsFSksgaux8EGSJYm9UkOcFF7MFWmnSVGO8I1GKXgLD3HMw7JMIz952ivaGK9ozvLXL7/7eh9x54z0+88U+7/7b/5Hx1i6Tlz5N9WRNvneZpBgzOLzB7MF3cZnl0pXnsGdv8nwvj2LS1rNsW65f2+Hv/8Jf4p/8v/8195aPEL4miBiI21pLB5DmyP4Yr/PoZgmWZnaEWR4TQsHizRHD52+z++pXGN78DDLp4c2K+uwCs1ri2yXN/IKnJ4+4fPh5wvgaz38q8ODBA6rzGYp4qVy9cpn/+G/+CnZ1D8opvWHBX3vxMr1MsEgnfHi/5vd/+w8wSZ/E5LRvXTBdB0RPozvJ4/fP0eE3uP21X+V/XAROPn4AuNhyC4H0UWu+tA0P14HBBx/g//kJt7/0Oc4+/xrn259FvvIappMIzEYX+VPJPH+2g0oQhe4xNPMZl8oGRfnkDj3TUQwnLBtJlg1JdYkSNrYhm9NRa40KkrIpybVgdvSU/bHF+kAvK5iMBpi6JtjAQCrG/TibSeWK1w4Uv7c94fjiKdg5W8MeVy5dous6pqdntJtEHHycI7lnGYQE+pMJL3/mc/z8X/4rvPfhPd5+800ePnnMuut4PKs5Xne4zWI08tU1QkIILnoBN0EE4plPMERCgE4UtukwTYvvalIVhZPGeuY2Cu6sjC1TwBFstEDUbUeXSZwPLNYVRZIgheNwK+NwlPPkokKkI4KArisJwWx4RgJk9I211RpvLcMiJXgP3qGCJ9OatfFU1tF4AIf3UAfBnUXDtLG86gOX+yneBRLl6fUTijRlVZYEqVmXDWqj3D9ftTROI2RgtpijgmeiFduHO0jf0qw7utYi0wyZCEwTmFYVi9Zgg6A1BhIBQjMrO8q6iSgZIpq3V6Qs245HyxIEfOrmPqYuEVoz6Sc0dcv13REPZiXGB1rvyFLN1qjHrFxhrKHo9/BS0ljoD3NwAZmn8W6xFpVneOGQwbNe1wyKHICyqhAicLg14NrekKt7PRJvkb7joKfpy5TtSwPavkCkmmR7n4vpKV4YyqMFx/fe5/IrnyfPXkJlBbvXnmOXJ+wOB1zbl6zPdjg/XXH/vOWk9rx754LjuiG8f8TR6RIRQAWJ0IrSG+rg6JAIlSNFDjbgsXHwrZ6RQkuqeUn3xpTy6BFdW4J1yKwgmewyvvUcmZBUT4+4eHzM/dE9Xrx5g4Xa4pOf/zLf//e/g2kNPkC1nBKO7nJzVONyRVJoyuWUVZMhxvt0LtBlOVO/w+f/wf+Kj37nn3Hxze/T24xYFsuOp/fPYPgeZd2QJAprYmUuQiBNE6x3aJFinOOsDjx80HLuPyJ9+efI9i9HHVoAgYouCe//VGj6n2qh0c/g6+LZFAQsKcf33iFPFaooWJ4c42WDtZ5BkrM2LSY4hI+COLHZuqS9gqs7O8yf3kOGOETrmoZUSyZ9wV+4PORTX/sC4trLXPzRP2PSzfnlX/97/OZ//d9QLs85Op8zaBsu7W4xmYw5O49mV+uiPsTHI4beaMwv/PJf5vbrn+H7P3yDdVVxevyYVVVxXsNpGQ8AKWIwotjEGAXngSjWDMGBDwS5qdZkLGu9sbi2RVjDsFcwGeY8ebD8CXvd4+k8OJXQdh6hBWkSyY8ditmqYpJrtnsJzgWu7w0IuiBvEvqjIUJE/HOeSKrgCN4hJOAjC31pOhIZyPIM6yVbeUZVtahgyEPAyoBTmoVxND5gQ+CitfzoaMF80uPGOGW/r1GbijQrCu49mlJkilvXxjhguQ5kmUa7hkGesDfsoZ3DWke1dkzLliRJKKTAtQbjBcfziifLGiE1NyYD8hAicaCJgZhKJwyKDKU0uTTsDTLuLDusd1RVQyIEXW0wKpBpuH5pyPPrmpOLkrQosAQG/RypBVXZ4pTi46crer2clyZ9mqqhURrzLCZdSbI0pVCKxhjKsgYg0QmXdgdc2Rkw6SeMhj1yoJ1NGUnB/t4AM+jx9P6CL7+8x6d+6VP4wQEf/va/IN1XdE8yTt/7NrcuHWCbC8Zn32O019HMjunqHDkYc//tpzz/6Rcwjyu2FoLT83MWVYXFkwtNSATGAVLReYcJkMhny6eA1Bv4Xghxs+fBS3C+oTq/j/cyYnXaFWYeaOcJo8M9Dm7ucn4keHTvA8ZZSj/T7F65xkuvvs7q9A5D5RjrLR7cuc+90xP0IMIAamfxKHTyISfLjq7y5OGIH/7zf8rO8CrrbIumuuCw16cnAqtO8vqnv0r+b75NWa/weLSUSCEJ3pMojfDghOTpuiI4yQvX91HFiC5JwW88jCFsUpf4SZDxn+2gEsTB9ebQ8kETgsc5QzKY8Op/8ve5f/cIYwRPnryJC54sTei8I6Bo2g7nLQmCvXGfm1f2KbpT9q9OWJ9ppO/oZ3Bja8zNQcZeZpFna3xeke3d4MNv/nte+cKKtz/5Km/88FtgahaLFabuKLIM4VVkK4koi5BCMphsc/u117j+ym1+8PabPH70JG4tvacTGefrBY2xG6EZscxG/EkFJUQE8G1aQe/jgyK8xZkG7w2+bdACtrd2WczPQelNu2vxSKxQVB4GMsHZDmUtEsHJrCRPJYUWTIYDwGCDYroypL1xjL4O0NQNSWJJUo1OVAwqNYLKeqrGsDfMEcGRiADOIUUgz5INh10wLAou6orz2lD6ONxcmsBHF1VUzneK57OUPNEo6dnbLkg1HB5sMVtWjIOj10sY9QbgHaZpsT5QNg3GB3qDHK80RmcsbMfD0zlFkvLJ6xMeHV8gnCcpctIcemlUkbfGMMiix7BIFLkqWNqEsuk4nZfc2M0Bh3GSNC+QpmIkPW2R4IPESkU/FQxljjeWbJBwe3DAfBqN2Fol9HNohKezEfaXy4SAIE8lMu/RNoY8SyIQr21wheTsfEkz73hyNudoZ8StfIvZ2mNPHjGhY3n3fa597Tn2Lz3H6Tvv8NxXfg29/xxPP36Hiw/+a3Z3JSa/ytVf/gpPfvgt6tO7vHF/xTI5Y+fgGlujGotk8fgpSZB0nSEgaENs+9wmxDe4DrxFBAMiiUEdJr68QskNTS3a2ELw4AzO2oiaWZeEOeT1E17t7/FO5Xj49BGv3bzKfHbB3/i1v8mufoj96C5v3W35V2+9zXpZ0k8En7yywz/8z/4WvX5KSHs8urdk9vSc9YOPmQwCp+U9jgOIkLF1+QZ5WFNenHH25h/y6ktX+aNvn8UW1gSkVoCD4NjqDamahtobztqS3v17fO7TrzG3njJIRLA4Fy1HETv0LIzlz3hQPYOg/QmTHBJneP6zn8VKz9XXrvGj99+ja2PfXxQ9lnWNsQaVSpq24/JoyJc+cYPp8Qlh+YjpEupyRS4lz1/d5tVLA1bTio+PL3hQ/SafMo/JtndZpTucv3GX2wcTjq6+gFudM784pzUteSrZPxhgpyvm6xovFYfXb3DthZe4cuMmP3zzXabzCwiOpqnwQnHv6YJ5LZCJhhDbWaREKPlTA3MHViA9kRpqmyhLcC2u64hBoZKsl/P0+DGD4QgfM2MYbe3z3Ke/jLeOk3sfU50fIbDRwO0jind7MKaXKVb1ms5YjtcdedHnYDvmFHbWUJUNk22Fw6FV1LDNbRf1TkIiQhyGKiVo2hbvAkoopAj0ioxLe9ukS0miVsxLhxGS0jk64KSEREqKZcOL4z4H+/sc2o48L1iXFb5zjFOFbUpa1+JspBN4qQg6bkQrJMvacvL4KRezhtY6dsZw42CMt4HT5QW2jdaMVCZU9ZLBYESRpwTv6IKjbBsO8sCp83z8dI4QY67v9qEzOGNIZeDVa3s8mpesmoZ5peg6xTiD/d0xs3XHtd2EbZGCknQq0DYdSkQr1DAf0HUNZdvgXSDTmizVSHz0u3Was9OKzlg+XtS8Ne9I1YoXjlb89S/cRj1aMU8D0/UDdPYd8huv8eG/fYuL73yHV76es3/9Fb7xW7/L7N0TEnuPl/74DNfNqNsZ81bwb75zh2HvMQdbfU6nJVopCjxOeMrOsAbqEDP/xEZrFpoSLQUiSLyNUEMh5Kay2ii4rSHYFhkECk8v89y6tIvvWl4YS25sWb6kM3qi5ZPPdZwf9Tmsznjn3oyVu8Td6j46JNz6xKfJ04SD5WOW773J8KWXcTInaTy3P/fzNJ/8Aov3v0l7cUYQS6zU2CtXMIs508fH7J++zyuvvcY3vvVDtAwMBjnIBC+iV1LnGQMlSU3U7J1PnzJ98DH745s89DHb0AZJsB77zP3yM86iP7X1i2vs8CcrcBeT2YwxJBJWtmQ9u6D1Hi1ANzVZlrJsG7yTpCpld9QnrNbkqcZ5z2oVtzOdtZw8XTCwNeNxzmScYkTK8MarLJZzLv/iX+bh3pcIZw+41vsRR9/79wyEpFyu6E8SxuOM03WDlTUHh/tcff4FkuGEh8dPqZYrQghUqxKpBPPOsnYyvuheELQiLfKfcIVSrUGA6QzeNljTEJoS367BW7SSjIYDirygKAp0Er2Grffs7F6irdYkvRHZ9ovs7VzhCz//N6iWT/jev/2XnN55D+lqNFC2Hcb3cLYlH/SYzjuG4xQlPUWWMV8YPJ669qRKsz3OWK9KcuWZek+RSBSBRKRxYdF1IGIQayoEZdlwniyRacYkqTjYSSiKAXfPF5ysG7zzPFk0zFvDj04qivQJv/TaNX7utX047VjMJfP5kl6/oLaOznp6eYrzcTZZ2Y67p0seny8jKVOkDDONcYLVqmKcB4p8m16ScXFxwapy4CWDflSHz9cdQgv6vYzbNw95694pD44u+PjxlPGwz6WtDNdUrNuOUa65ut1H9nd5eLJg3hiKpGAkJb1UYWvH9iBh3bQE4WiDJdUpRR6oqxI8tMZRJAmTXg8noLWOxksez1ZcLA3Gep66wP4k51dePeTrr17loztnPFnW7A0KhDWsL4544bnn+Np//g/4+N//Eb2dXd76vd/j3vExupfw6es9Pv3ZlMHWi3z/ew/ZXzzFCYk3jtV6jdYahGa1LqOhWurIotcJCR5NZFELWyIrSJFkfcUgE4xyzVamGWcFh8McKRS9wRa5ziI1dgAA3XJJREFU7cjNit1ccGM4op9laGqmC8vzf+1rLL73+zz83d9i6xNfoj15wMX776I/8Vn86pzn9wcoW/LoZMU9u+bKu0fc++CIpdc8nK4Y57/DlRc/w9d/9a9xf/HP8EHhheGj734Tl2m2Mwn1kp5oyYuMg62MK6MRJ7OOtU/Z3jtAakV5ehwP1AzGky3eefOHfCmfsPXaDo9DghR+kxgdY/n+zBXVT0ce/AkgbLNdw1PbhKff/AZbHCOKFG8te1sTCu+ZrWJQJcFx5+ERD0TK4ZUDvvCpr/LoW99gJxO8vDNhP025slPQG2l6vQkyKeDsMWo2R97cx6qM82SL3c9+jemyYf3Gb7F7OKRq19AldCFje/eQm7dfZvfwMiezeaykOosSEpWktM4yW3d0LhI/RarJi4K2jS+uENB0DXiDb2pctcLVFcJb8lyztbXD1mSbJNlYGjYJzTLNoknad7ie5nRZ8e63fwvbgsTzyutf4K/8g/8d9957l+/89j9Bl3MUgXJdsrszZNUYio1cQMuImLHW0XZt/OIoiZQJeZZTkmLn5wyJ1VnTtljnEEJuorUgUQpLYLlY4KTi0ihhWGiuHY4ZDzO+88ETauORQjCvLXVpyZUkTzT1akHXWnSakPZ7eKkj3TUDLwTLsuNi1XDvaM5i1aGk59bhHk8vVqyNpSclRZYy7ues24pJL2e7t8e6digBu/tDpouSRLfIRDHKU2wbK1StFaNhj8cnM0aDA4okQyjFoqlQWpO2gq1hBrJjWq5IkoJeojm7mFP3NINcY4LHW8dy1eClQ+ocaxxaKIJQnNcdi6ZjUXbcvnGLYliwLWtWpuLXX7vGze0Us+z4nd97l/W6YdzvM6s7Oi1AB9YP3+LS9U8w+LVfY37acu2W5qtfvcm995+AkLz37imvf3bAF3/pF5mZ73KtWtCtLD6Al5E4qoRHCUue53zwtGTqNPvjHuWqoWlB6pRrw5yxTjBtw6VBxu3dnHFS40yJyPocrz2dqTjMFfPVMeu54/6ThM6tefHyFt//8Cnrq3tkTc63H16QnP8urRdUTvOjf/5PmQVQiSBTmtJ6Wqn5wdMVUnqaTrIyYAYlX7r9HEb3EJNrJO4DAmtG/RwpJI+tQa0F5oMHrNqWQSdwtmNvO6U678jTlJ39bV79yl/g7OEj5usZs2XF9SuX+M4f/Qt+YSw5v/0rtKWLTH4fk3r+zBUVwE9COkMMHHAOEArvPfMnT3DH30cNEi73h7iuo5clICSHWxMuFmtaD53XdCFwNl+SbV9jNBzyqX3LS3nEBu8Mc4a7RdwmrkpYPCAdXaJbLPGXGrzQVLZj79Uv8fR7/5LVck4YFngyRrs7XL58iZ0r11iuG6bTCzwG27UkSlF2LbPWM1t2IBUikeTDHmZd4uYrfIjhBCEEbLci1ItoxUgSdvb3mUzG0ci7SUmxzhI2mXc+jraYNR2t0ZQUhG6FaWtUt+aNbzzl6NE9/s5/9l9w6er/nj/6zf+B9uzHZEUgJAnrdcvueIgSRAqA9azXJdZaEi1RWUJTNzg0x/OaPE8YptB0cWwvhIjGXM+m349LBS2j8rlpJMMsQeApVGCnnzFfN6RpgugsnbFMithSIDXGecra0FpJXcVfT6YJ56ua+0+XnM5qWge7vZQrw4w8GEaF5qPzmjzRZIkkyxKC7GGMx9tAlmucabg4PwOVcnV3wHJdkig22htPb2MgX/vA/eM51/ZG9LKEYpRi2oa6KhE6YX9cUBaR097f2aWsWlQmGfzkJhZRpa+gM4Z124EXTFc1J3VHZQN7RcIH9x7TL1JePuhzefsyy/MlD06hmIy4e1FxadijMp7aGUI/wwVF+/Qcufo+Oy9CXezw6P5dvvTpMa/fKPjGjy/4g+884PHdp7z2+QXnyxXv3HlEuaywDREs6C2pjCb1SZESEsHeIOEwrWlHnrYOLKY1Hz41BJ1zupphLDzfL+in0EsVSkLQOUfLNYMkRSjJbL1ib2eParXkcdPwZD7j0X/7X5JnBR/PDFstzCoDIdBXCY2AlQEtU3YGCQOZILOcxfIi2qWMpSjGjCZDPnzzDT74+ANS33F4aRfhO944P6U0cK/0rD46wuKZLQN/MDundoEdnbLXf8K154fcvHmJMD1ha+s59r3npLXcX3re+vFb7OW3eLz7ItYHXAD3J2zLP9tBxcYG4/yfJGoEBN7B+dE9nvsLXyEfHHD6/ttUD95GCccwExxs9ViVJdZJtIAklWAcwQRe3u3zvG54dLpiLQS/uFWglCYkGcO0oGlbqnGfs7NzwrUZQhVIl9EsT+klElF3zGea3iRjNNlm78oB57M5XRfoqoYgDN4ZREjonOF8ZeicQAiFRNGuStrlBVQ1rlvy7K8oeEeaxQpqMt6iVxSkaUoILg60fSDVHmOjN2m+apjXgVpEyYL4ibhW4kVK8B3nR3f4/d/8Df7m3/97/JW/8/f55j/3mPYOi2VJkfVRWtEZT2/YZ7VYUlfxIMlSjZYapWNVsNvLMV2NjutSnPP0sqg/qlpLtW7QicJbS5Jr8iyat4O1NCZwvm7pFRnBOpJUgwy03nNpawhe0Bqomw4pNFpEGsCd4wVzJ1gtG7TWjHoJhMBF2fLC/hgRPL3EkSjY35vQ6yVRFb6xXHVBUi7LmPuXapQQeFvRK3KyosB3HVp4FIFMZ6zLNcfna/Is5drBiNrUMYggQGcarHfsDHvsJBPyIufa8wfcvDaiWjS46ZpuXiIUuCBZNx3Hq5apcbTGk2rJXirp4ZGJIEkEj2clHz2dsm5atooe+ZNlZIxLhXXR4rI0hmbVUrcG10JycYfJruLt96fc+/CYG7e3uH55wEf3FU/Ljum3P8CNJuwUBc2qpPaG4B0+wNo7juqOerrAA+M0ZZClZDJwMMjYm2hSFN95fEZpHAbPY9NQCEEWBJlSQCStBh9okKxDoFgfMcFz0dT0VIoLll4a+Pzr19jdGvOt79+ha0001xtD2QVK48jrNYejHon0tFrj0QwuX2V4ZcLv/+vf4MnDU7qm4uoX/xq9g2v86Lf+K/r9HrnKaGtDX+RsjSTDfk4mBevOoIND2jmjNJDsHjJrNdXynF4xRF7+JFc///fp1hec1S0uCOzGH+z9///j5z/4oHoGAovfx1s8BIeQgZe/8CW8ikTHrd4epw8fIFkxwBJMpDNqJdFS4qxj0C+4ZX7MF35uRHsGH5zVbF8asv/JA6gdWdKn6hTV/fucPniL9x5bBjufgFufxlUdZ9/4bfayLdJXnue5qy+y98LLiCbw4Zu/SVeXtHVLlqjozM4zlusVi05S1tHR7oXAtG0kIKhnWg4PIqKUh6MxB/uXGI0nBB9IdIJ/ZtlBkKYJxjZUTcei9pSAERrfdWBN/OYswtuNQFTiQsfD++/y8MOPefETt3jxi7/M7O425dEP6YcY6Gi6lrbLma/XBOnJdAwjtdZtBqqBUQqNj4PKfhH1bd7GWPhESRIZyBOFSKOBu7+5vXu5RiWRUbU7SFDO42XKlvAxD1GlfPBwyrJqePHKJfppzdHxGVpKjtaWp4uWa+MeLY7dLMUGy6IxfHQy43B7iJSCIk/ZnozpbJQaGAvOOdIs3fDbFc5Gg7CSElev6ePI8oxhkXM6K6mTTWXrFO88OME7x6WdiAsqioQMTddZmqpiXBRsT3JePLzCD3/0HvNSUK/XaF2gUsvpvOZoVjPrPJ0UjFPNrZ0hXVVTd56mbOiqGqXjokIhaKwjCOgnaSTWikgBUFrw9KTGa49uHXq+YO95yeGNGxzff8yDRw4fSsZ96EzCYl1ycbGisRufnrKRpaZ0fIZUivOa2hoWzjMtG7z3PFp2vFKm3L4+5Oa64P6FwYdI4RylObmIViyhJOOioG0s+Ojje/nqVbrzM4J36Fzz3rzhhZ7iS79wne99+xFNbem8QWYpSgiUt7TWI/Ie5KMowC62KK7e5vIXfwHpK05++/9F8I9IJ1d57i//p/zwv/m/Ms4Fx6Xl/vkZVefQSHpK01eSa0XB9a0R25MxdbPmm9/5Pr7YZ3J5i/ZhifMenRbUXuHCgDbpR3CBj/gg5/mZJdWfXlFtxI4R4Sx+0l4IGQmHIUDdtOS7e1x/9ec5u/sNDB1aaoq8wIUOawx5mvFr/9Fn+NRzgfv3T/no/RVH85YXX71EnQ/Y2oZwNmUw3ubmK89RH1nyOw+YvftdJldfoVkvufXlL5BP/iJytAMyRRVDTt/7Mev5EmHrTU6fxbaW1nV4IVmWDUGqTRRW7IN1WuCMQyhIkz7QoyhyDvf3SHQC3pOnKcBGoyUAh3dQm4SzqqVuJSGVWBNbtuAc3jYI1xGC5VlKs3SOtip5/OgRL75yi09+6kX0z32CH/3WIed//D9gVUDnmuOzM8rVmq3xkLaucJta2LmYDhK828gpfHTES4GV8QD1zjIoMoqiYF1VJErST+KcTGlJL49DW5GmaBlpnluDjCQzPLqYspsf8IkXbtFXsOoaMiUpq4ZZ1TLOJUI4pusOs+64ujNmkgWmZY1aKQaJop+lpBJW65rz6Zq2MRzsbUVnggDrfVxSeAiKyG0PktA6iqxH5y84L0t0gCKP28KPH08xYcDtg4TWGNJMkG0CPQiWEAyuqVAy5869JzTec143OAdtZ2mdJ1eBvVxzdZKTKM05AmRAhbgk0lqBdyRSInC4zWKlc1FLJ4SkcfDu3RO67RHjcUFvblm/dQeNwBuJsylCeQ52xpycLklTgSst61WH1AnGQmUMpbe0MiMpttDFEOUN/VST2gZXr8gxDPoJd2eWx4sGSUxDclJyaixFCJEFZgzeGBxR+X+QpORdhRMWFWBlPCHNSAY7/MEfHvHx4xm3v/wZpicnHD085tLBNuOqpXKKbOd5bv6FX2B0eBmT93C9Posuw2Zb5F/+u6QnJ0w++QWa82Oap3f46OiMRecRXpIJsMFTekODoK0srTVcrmq2ipTGwbd/73e4eesFeqNtsiLFrk8ZTK5x5mzEdcu40QzPAh5+xsd/ADgvbKqDWFUhfiq/U0S6gCcOo8PeZWY/akgGoPMBaR1QdYMqEm5e2kfXC77xB+ecTmvmq5ZGwWyx5q3f+xGJNIyKjHXzMadTx+MLGTdEVYs7+ph8/znC1oDSeoRpyHRHZ2vOHr1Nrhoa00V3boiizTRL6Cx01oHKQIISEi8kwRpolmBKdL/g8uElBoMCfGRmx/ADg1KKLIs6JmMNaxt4NK1pOqICflGigosVmm0R3qK1RKoE56LuPctzdJpQlysg0HUNQUsqk2B9Rtc5OmeYzVYM82gH8i663eumQSmNEII8zwi+QZOQppq2aZEC8jyHQtDUXcyiM47h7ha5cnFm2C/wwZOoaDdKtEKpwP7+Fsm8ZDiQfO3TLzDKc0xdUpUVi9LwZGpIkLx4MGGoJZe3Mt59coQNBuc8M+dZTlf0tYIkY1a12K6lbOMLY6xFbeabzkcMT1NVP6mwtFL4RLNsOlZtxyTLSFWgrxTbwz75pRHvPnpMJhIORhlpgEQrhC6wHoQPGNPgXEdtWh5WHeeVJ5WegZQcTnqMEsEoi2zzVVPjgo/KcC3iIRokSaLQUpLrqHlz3m38CJ48zxBJwtNZTa46Gl1gjlvs+UPq0tO6hmoFg4HGNxZvHcMiI12aCF60EVtdA+sATmVIUrA5SvUovUanWyT5JRIpWOApV1O6LEWrltR2eNvgMSAFBkWQGQbogmMgNbI/YukTbDJhb3uPBZKBhzCZcLf2cDhg/xOf4MHTY57/zEt86i98gd//F99g+NxLpJ/6y7jeHnMbCA5EHdDU+EYgd27AJ34Z9dwtfvhbv0WVSOqQUkhLEB4ldBwBAUJI8l7BCnh/vuRKk7Hf6/OUkkXzDq9/4hXmi5LDW5or60dchH06o/Aq+mzhGXbmz3hQhUDkO20OrRjfs6HxwZ/gQ4MH1xD6Q1AanMVZS7kqyRKFCZZ+mjM9O8PUDcYGhFYE6zmeCWYBjh6d8NL+iK2dq7xzPOPJyQleweHeIW52hN69GbGsoUXJEPUmtiE0azSGRCusNQgZUAKU1nSdQegoDNVpipAa11nM6gLdldy8fpWtnW0SpfEB6qqMGzThCdaTJQmNqcjzlLq1nK88VefxdYM3zQbDYRBCMBr2uXLlObJUg/OsqzU+eFKhqK3k6OkxR0/O2DvcwVrHrU/c5Ftv92mWZ1RmTSoCOiuYr9YkQmFCRF/08pS6aenlOT7RWO/xzpNmCcZYuq6N+BPbUiQZ2+M+tmsh14yGfWwQJEnCZFSw7hRZqhgOcvJen57UjIc9xtsFUnrKdcnRvONH9y8QeZ+bO5IEQe0CH59f0Lae07LFCdgb5NStJ08T1lXD2x8+oJen5IlCI9gKHi01EkG78d7prEdZ1zRdTZCKoAxPZiUmBFbWsPCWylosgcwZGuP54eMZl3oJh+OMrUHCaJBTAW0HuZPoJKE36FOvGrSEnpQcDnvcvDSkLiucCSwrS9kakkQx6OUIGWiNwnkLIiE4S2kdqRSkuY6Vq1AoJbEhYo5qBytjaGbrGBKiEnQmOV+WWJExUpLD3QGPpxXbkxHH84Z561gH6Ag4r1BBE7xDUuNDgfQS5xP8RgAq0gJ9cBVtK3xT0XpDt5gil0e0rkQojertQm+AEA6vC07zXlS5J577XRTWWgvnfsWLl1Je2t1jsVrx6//4HzGe5JxXJVsvPcfnv/LLfLfdobMWiSRsPK1+gymuupbR5/8j3HJJLRyNFeRKEUQgQWA3koJExKTjQTrCyRaXaKamI2kavIxynDff+5DPv/YZ3v7G73Pp6rt8+et/i7fFIce1RyiPEwoZup/povkPYKYT46Xwz8LvNi3gn8DYJQJPQugW9ISjbWqauiLRGqkk/WLMzZvPY04/wtkaLzJOpgvqpuNi+RiZCNrWcWbnZAvoX30Z0Vls3XDn7lNeeGlJTxiC6GJ4pRBooogvyfoRpieIzHYRQxisg6A05JCTEkRUSDvTkYSWV164xXi0hQsbBbp1jAYDVqsFiUwQUtO0DVIKFuua42XDbAW2LaEpCa7Bh0Ca5ly5coVLlw8JPvKqmqpiMEhJEs266ljWa9ZnT/jn/8Nv8Tf/47/K5Wt77OwfICdXKefnLFvHXj+hUILaCqwNlF2NkvFWDgQSrehNRizXFWVdxRxB3yFFDJjMsgypFRLJoJ8zHqTYtmFVlmwPC8aTAeWsJSkSdg73MVhGacru1gCZJrSm5s75gj/86DEQuJIGlk3L/arDBMe9RUNfCMrKcHVrxKev7vLo6ZSqbbm0N6I/GvDxg2OWQjDMUtIkJUsVXWOwHqqmozWWqmtACrxf46xHkTDYpA13zkOa8GTd4JZrrg2GVDrwznnFxbLhi7e2GQwFOs05vlixco4kS7i+V3C2zugaQeotV/ZH9PsabxOmZYWQIqKGfGQlpXnK+nyGJyDbFi8CNgjyXkaeZySJolyX9PKMk9kU0YVIdWg7Wis3lI6OEDxdU7IMFj1OoswkqSlXSzrhabynC+BFAOEhtAibEWQGiSPIeEhIIaNo2Fps2Cx3VIJIUrKDHrbo087uEZo5lAtkCMgkobQCaUEPBog0wTQtKIUksKhbyjbj8PASL710E6ckIumxM0z4B//wb/PwuMHUkW8lfgKt8zyL4w3e4bViOZ3RLs+YnjxEK0Bqgo3py4gQgYT4mJVY7HEw3OFw3DE7foJ3gWldMZ8vuTg/gTzhjR+/xeup56/+rX/E7z4Zc3+pQHos+Z+joiJC754Jsf4n329yxwjx4FBqwNO732YQDBaP0in7+1ssVwtuXrtKolqenl8w7g94++ExjxcVAkW/SNlVKSLJeeOiYn12xGEt+exLV3DGM3u6osgUWjwzPka/ayIsSdKnP96hnCoEFi0hL3LazhDs5veoFV3ZxlbVeaTvuHrlgIPdCXVVxzkFgiRVrKo1RR6JiNYagpS0VctFY1jZ2E9LY8BV+NCRZj2ee+4WW5MJXVORJ5quaxlMBtTrFatVzWnlWIcU71tm02O+9Ud/xK//+l9HJgV7h9c5PblLknXcvrpN5hz4mgawwaKFwBhLr1eQ5zneGobDHmVT4ZxjNBrhumfmZU/dtazXLcEP2N3eJdUZRT9jkCc4nbJYTxmMJyxNQ56m9HSCVoFFXVNOS969f8Gg6PHizoBBlvCDOyvuLJoN/UJhcbx4/ZBe8Gjt2D8c0zaWofSMJ0POL+bcnZYk2lO3HUXai9uyAAGJkJokzcE5TPDsj/rcvHyNb775DtYHcpVijKHamFSLfspAB6arNgp2u8CkVzDe3WPtBd/90XssjKL2sZK+Ok7RXrM3KVCpoBJNzKaUsd179tgulyWdcUglGA0y6s7StdEjKKXAOUe/348HkotG94tyTW+YkklB20U6rReKfpZwPF/S+B5B9hgOtzh79JDjTtLlPQgSbINwLcHVhE4hRYJUGkQKIs4hpZIxPsy38cVLIK0rSCzJaESQt7Dzh/hySlhXeDUgqASf9HA4Brv7EAK2cSAjP262qnlydMbh7jYPHz/i9ksvMO4XXBlMuHpli9EicGFjlk5AbN7rZ11SHPv0lMeuTulrifEwGQ9Yzpa0jYu2nhCQSjMJNf/RK1e5/eW/xc3X9/nW7/0ee3mfdVNycvyEe9//EXpnj8p5nrz9IfPH/wde/Uu/ih59mg+qEcr9bF/yn8Kj4k9y7579p2eHFUROlZQEIVhdnDK7+w67+5ew0xmDQpIPcsq6RAtLKC/oupayv8V4OGbVQdd5TGs4x6OSjKt7YxCeWXXG8lSwu7PH5MUrMQJKK9oOpIxdrRaSVAvy0ZhVSEiT6IsKzpEmGudBBIcpW+gszrbQNqRKcmX/eZQ3ZAo625GlGVVV0s9zvA+RK24twnvmznGxNhgkoesIxhICpGmfGzduMZmMCd6SKUHXrBkM+qxWc1xQzFxBIwFhCbSo1DGdHnF2dMb+5at84S9+jbcTwfLoQ5L8nHo9x6mE4+mcuuu4OhoQRAQRChmhZEWRMxmPKMuSRGkcFp1IdJD0U83+sE+vSMgQZL2M4C06ERyfz3FGML1YkU80k/4Bo0yQpvDgyYxvvXmPet1xa2dA2TXMlnM6IuUmU4GBEuggKITCdJbaS5x3pAoaD4WDnVHB0braCEoNee5xATauaoyNbbLWSczrC475aspkWJDohPlqzRKDaDytgOm8YpJqXtkac1KtuHu65PLugE9sNUwGI27fus5vffs9nlQVnzgcMMnS+KKFjkT0CCbq0VKZsL29xbrqmC+W4B251gglWDcx9xAf6DpDZz2T4YAsTXG2I9EJ1hpq77FIeirFKAsutuB5nqKV5nzZIJUkyxSPbE433iXt76CLbYo0UJ68j1me0rYtQayRShGShCA1QqYoHX2JzniC8Wix4vIgMEgVZXfOclhw6g/pKHDlU4JdghNIGwmrjS5IipwgJKiAIOG86nh0sWD73kOss5RlR7mqqTvDredv8drBhG88bOPYfuM+iWdPfMcdKWaxpqsb8JAnCbvbE8rFmg2qPy6NnGcrT7h+WaLDfd7/wZrqacd3H77DJ1//HK9/7jOcv/cWD5sGcXgL+9InmQa4+PFd0lsFyeQ1jPjZwX7/AVu/n/0RNhWV6Na8/Eu/wv7N67TzOQ9/8G0Wj97HWc9quaaZrgl5ytWXXsA+fEzrA08v5tStY15ZjOxYdw2ffuEWO5M+vURg1ufMz0548njBy4MdJgc36LomqrC1RkvPeHuLEyHj2ttvfIl2A6gJDrUB4ouuxVYreqOMcRJ5WcrBMM2p6ppUy1ie4/AWujbymC6aBhsUobWEdg2hJkkV12/eYmt7F2ujKdi1Nf1eRlmWeCF5OCup5DBC/YRE6pSuW3N2ann8+JjDyztIBZ/55S9jVz/PN//wDzifvcHFk/dxNm6dGgeZENjOINclwXtyEw3ZWqpNXFigaztUokh0ghaSPM2oug6hE1IhODo+56R2LGpBWZe8fuMak2GGdi1Hj8753lvHnFYVpvUEW7M9zNgfjrAqMEoMO1qR9jPOViUPnl5wbW+C9Q7pQWYJy/kSvxBc3dvhZF5idEKuYb4o0UJiXGA87jGRfVbrivWqZDIa4k3Dk+mcZWs4yFKev7xDL0/48LTk7ccn1Mbwycu7lOWanhSU1vPd954iguPLn99l/2CXV2/tos9mHOwOSUNclFjT4XVKqhS9XooSKVIE+kXB+XSGcI4s05FGaSM7XoiA8LCYV+RJgtKCLFXsjEcsVRlj3pYril4/fq5QLJYrPJDmOdXplPsWzpqWeXKAKsaReBAahvu32b58mYff/1269ghcjWsKpHaI1KGzFJn28V2NkAKkITiD6Sy6VzDRGRMBvbTHY6WoRMBVJz9JIvLeYbsWncVNNT4OuJ1QPDmdMhKefpFxeNBiTMW165f54Q9+zOuf/wrvFp6z6hlx7hlxJULVlTVc3HmTHppGJYDn4cMj2q4DoX9SfbngeLyo+Fe/9xHXbzkOD2/w4+99l+P5jIfHD/n1X/0s40lOGg4Z/9I/Ziq3aY0EUUUaCT7SPH5GSfWzjzERUyvET6H3fvrfN80h4Nk6PKB/eIN1o1DblymTHabTGcpZnh6fczwvWRvFH//wbbYPr3Bw+ZDLh4domZAKifCORdvyR+99xB9+fMx37hzx8emco9mKrlqwfu8dzPwRqYxD7kSDDJ7BaEKSj/HBo6TYDPgDUgWyVJAoiQsOhyMER79XUGSSRAm0FARnYvqylti2JjhDZxq8t1RdS9cFvGnx1TneLFAabty6xf7BHolWZGnEtYg0ZVGukDLh0bTGpCNkWiCQyI08IkoWWk5OH4F32MYSjGU46XH55lXGl27QqYKVF5x08N50xUlpYj7ifI3pHLhAKgSpUkR1enwIx4MBRZ4gMs1qvaato49yvaqQSc75vONotuLa1V1u7U/Q3QVnT0/58XuP0MHxtVuHXOlpkAm5LlibwKNZGRN1VMLjacV567ioKtZlQ7l2VM7hhEToGM91sDvhpUtbjLRi1JvQdDH8M9GSvZ0Jg35KbT29Xs5k2CfolMW6Zl43zJqWNFEsa8PxbEmmJQHHollzUq3J8oTbl/dwwI/vTjlarFk2NXm/x/XLBxSjIXm/z2DQZzQa4kIALREikOioZpfSMujn0afpHN5GyYezUcPV6+W44Fiu1xEImKZx8ZBqlBIsy5rzZUkQcWGilKZzGzik0xwtaqauR0iHUTcVAr6ueHLnQ9LhPvn+KwhVRDqHXUNXEUyLsw3BdxudYkBIh/eKPOvFpBgUSMWlnubFg4zR1gDVOySQ4swaXBfbxmDhGUXNB7yNOq3FqqQsS+7cucNqtebHb/wYrSUnTz7m5ctD5LP5s4jb/Xi5QvvgA4r5G+S5j2lHAbzdQCM3ImiBRwJl3VA7yeL0DLOe8enPvM7rX/wkq67ld/71d5m1LU2zIskGGO9QoQEEQsW8yET97MPoT62oxIae+dPzqZ8+rJQAGQLCObQCQYtzimp+jghQ5BrTGDJSlsuW0qxZffeP+at/++9y785HHJ2dID1cHQwYDHKMt6xby72zksdLC7JjJ6tp+CZX1qe89hf/Jj6PfbkKgdFkiyzvg9VRWOgNzjlUotFS4m2EyMVIL02e5aiNJ47g0SriM5z3ZFlC07bxCyYlTd3QNg7fVgRXoZXi1o3rXDm8HNsxEcmgRa6pqpq0GHA8b+nSISHrwSZ0IYioihdOEYJjNp3RtSIGTLqOquko1w2m6ui6jrppsFIzc45Vs2an0hwOCoQy9LOEtq7xBMLmJk1lwLaQFSlFppCJIs1yPj7uSGTHaKgotOALL+/z0sE28wfHXCwr7l+0eDQvXd3GNTU39iacrGsa2/FkuqR2hoFTXJiO1nsmScKnbl7l5HzO/fMZw0JzqCSdcQx7KUF4Lh3u82R+j+lqjnCBynf0ck/X1SzXLaZuuHXrMoM042yxwnnQWrGuGu6cLliua2ZVixdgUDxeNDjrGfYkk17C7iRjVlr+4Icf8NlXbzPZnuCrkuAFuq9JfYvyhqarWXctgyzDuQhTTFNFJgUdUcsVNiEHRZ6TFxmmbkjShP5wiHWOtusoipwkKcm8x7ees+mSopczyqNg2BEj5YSWmFbgekOkTpE6JbgWgsd3K04e3mN842UWTz6C1WO8XyE6CWUAoQg6RSZR+R+SFLP2PLk4Y3BlG4jiY61gT0nUwTYfh5R5CIT6nNCtUaaPN5EkIdSzYieh8Z6qbtFY1usSHy7T2YK6asi0oFcck6kRlYvvut9IxIPxzD58l8u3PsNOLjh5+03Oz06ivEMQt+6AtTFE5bXrV/jk4RaiyLF1yfb2JT7zK3+Di8U/QY4STp7cIxUNu8dvM9t7DY9EExd1UsYFhfwZLOKfWVEJYkpElCbwk2/PfqyVRCqB1hKR6Bh9IxTLixXm6F2cqWnblr6OlMan6zWLtmK+nPO7//bfcXjtCpcu75MpwaSXc2tvm1evH/Cpy2M+dWmbIZ7CSpSFp2cPWT65x/vf/PckJvr4hBCxqhlsIWScFRR5b4Ok8Wgf0CGSB4VKUFlOMcjpuhZCJCjGipHNbCPeLM46qq5h1jiCBWEsErh6+SrP3biBaxuwHU1dIgjMZhcoJZmXLQuvcDKn1+8TzIbCEEJkCimFtyX37n7Ab/zL3+b+/RNQe8yXjnI6xVRLXNeQihhF5p2lAY4ry51ZxdnaUNUdxlmSNEGEQL/XI08zhI4YmRDiS/ho3nF3uqY/HDDoaT5985DrewXL+Ql3FzV/+HDF6crS1jWtB5IhicqY9AcURYHd0F0lklGqmUjJC/s7XBn1SVSgbGvmq5r5siO4yMOa1zUtgdF4iLWe4aCPin+5LMuGk7M5N6/sxFSZYKltR+sDtXG0KI5mFZcPD8jTlM4H5q3louno9QpG/S2SXsqkl5ALy4OHM775/XdZlw39PAUhcImCNGdrNEJLx9a4IEs1Sa4ZDIqoc+oX6M0zm2cSrdkkCLe0ztBaw3Q+pzUbQ7EQqFTTmjivKqua46cz5ouOunUYB23n4nY2CJAFQidxpqjUJkFcsDp6BN7Q27uBVCkEi+vmuPUFvqpxXYtOY+JMPhiQDge0yZAH5zNkUHRVg8FTt4atTHH7UsHu/hayf0jAYspTbLtCK4HS0YwvkwyPwomYaBOC497d+5jOM5uteXx0gVtO0ekm3s67aDMTMXJu7+f/Kvbrf5/R1/8uvcPn4nsuAmkSZ4wheETwXN8e8MlLWxRZjx5w/eplRBqYPb7HZz/7CjvjSzz383+Lyd/83zKznr7oyBNFnqT0soR+ntLPo4j5f+7jTxV8ip86zYLYaKo227dnbeHG+B9zzWTC9J1vkbsVrZZkPU0iPWJVxdSNVFM7x6P7d6g/+Ry9TJOkGeeLklGWcfv2DZyJt9B2keK8Z9QfMOgPYitwdId3/uDfcOO1z5HvHpL2CyaXbjE7+xhsG20FLtA2FdpqxplkWfloiZGS8aAPAYyJPHTnAjqJ8wqMixibAG1QVE2L6xw4y3jQ56XnrmObGq0CdV3T7w2YL1cMe31K0zFrHI1RpH1F17RYYyN3PTiEyhGqj2lPCWrB2ZMPeKOtePedN3HtGi4+wHULQuhwIWKftYTOe1wQzI2lnVtWTcflYcJuZximChViDE3nPCo4RmmCEIq2XPO1l/Z47uqIbNhjelYym005nnd8+/6Sdd0yTjWJktx9OuXa3jZaerLEM53VGOvY6eV0xuJEIGhJbRxH0xmp1vSShEXVUp9ecGNnGOcaKqKOJ8Mh9y9WFHmUKXjgdFZCCIx6BWXdIJPI429tYG09y65kqBRYQ19CE7GyNDZWjqM0DuO7TiCCYHuYMb+YcydJuPn8ZVxwmLLBK9jOYnUyFFE3F7xg2MtZztdIpSM7SQi0itNj66Az3ab9iVd023ZUVU2WRv+iMQ6nG9JhwsP5lEVTMeoXBKGonaMNnrgHeyaHDkid4EyI0p6u5eL4PlvXbtCc3ENUDcEbAi3ex+fEdC1KCbqmQyQKn49Ztp6LsmG3p+nKCp2kuGCYFJrndgcEa5l2Ob4tsaspiIykXyC0QiiF9BlOuKjm37glHtx/QJ5nOGfZu3wF0pjBKYTayI8i28wXGaa1LLM+XRgAgTTRWBNFsZ117KYJt7bGtE1DXdcEkbBoP+a5Vz6B9J6bN19gdvw29san6NhG54dICT218bIqUJuiQ/2MiupnH1SCGIUTNuT0zc8jNqKwZ6mrAoEEgjTMji+o7nyXQero6YJcW/qZpjGayaBH7aHsWrTtePjRh3jT0AW4fes2zeKcDz98gDMtGs8wVdguYOuS0nYE0zIZ1YSuZnX6mJ/71V8nnUzYv/4CF2//Pol3NG1DV3c4AsJ79vuKk7WgLg06eMZFHyFtpBF6H8nmEQmBlBKdaGywrGuPq9tI0FSeF597Ieq2ckVZVeh+j+VqyaBf0KxLDIrKaQQJ3lmkj1RG6ywkMeXGmwq6msbFpObp0UeMdvZQpuLm0DPsKcTugCcXa8ouRB48G9KqhNrDo8rztGnpz1q2s4T9fsZWT5AmKqb11hWDQvDFVw95UnrS8R4yLOkVCd6P+NbDp5xXhu1MoUKgs4GT5Zp5U/P8/j6pyphVCw4GGV//9HN85407nNSG0hieXEzpuh49nZERc+LOypLztWRv3aNsDW3TkkqJNZbpsqKXSDofOF2sefnyPtVqhcr6ONfhfKDtLIRAqhSZVsyrmA5jjKULDmsDx2uHPl1ijKOXJPQGA/bHBXWd8eBiyYufeA4hYDZbQaEoW8PR6YLt4YhcCnxnkELRH+QsFyVFllJ3Bi0i2BGhI3hQQZ4l0YAeNulGCJRUZElG01kq22Gc5GRe8XQZjeDWGNato3OK4CrwGSEkhGgmjWt8HbDLKVVviNq+gmnOwRtkIkkzHTfoQeBMvHh2rhxw0Z5gzYjzdsE4i3yyqNEbUDUtIy955foWb5uK5WmHaCosqzhzy1JUlqFEoLUOmUqCNwigrirSLKXqLEH3MM5Gu9bGV/osGyEEQSoF5YNTzp98SK/XJxjDrF3ivGSgcy6PcvqJY2tYEGTGdLGg6+C99x/wy1/8Fc4bi0rgetrQhpaV6pOqQKYgJyBlFNYixM9s/f5UcF709cVLQsR/oMSmkmIT+BACyMhJ+uiPv00mPOmll2kWc0ZJxXgY8DrBBMm9s3XEGQfNvccnTMYFo36f8/WK2zdf4uT+++yOR4zGQ5rOMVutWa5qBODbiul5jZ6fMRrv8IPf+P/yytd/hVt/4XPcPbyJPX6f4B1ZkjIocoQD1bSMs4p6GS03xrb08xQnXRSuuhiTJZXiWe3Ytl3kcndtLNcHGYf7ewjvcMaQKKjqlqLQNG0FKlCtapzLEAnYro2cK0QMsbEdtl3SLU7BNmQKikQyr9c8PVqTC4luNM/vDdju5/jOcryo8db/5HKICbex3DYIZl1g2bU8XjckKub0aQSDRDAsEvSjjvuzlpfvT/mrn75EJiUn6wbhA586HGGbjmEvYl8cgap1vP/k/CdJyvvDgraJ2XlPHhyjhAQUxsfIskEvYzfLqE3LdN2wKlu2t3Kssexs9UkTwapqcGlC5Sy1C4yGQ5rpKU0TSDQsW0PpHeMsZWvQQwSLJ+qWkiwhCRrpPeNhxkVZ4QiMhwOcN5zP19HmhGN2esbnX7vNW/XHzFY146DYH+TUtmNrK0emCcYIbObw1tN1Dtd5pNLxALIOKSPW2hpHv5fRNCXrqsG7OUI49vb7OGexDj58tCAtMsbDEQ+eXnBWOdY+YIQlMTVSbG/eF1BK44IFn+Cdo5weo3tDRD6BqsGZjq6qSIoROtOY2kXNH3GGabygBCo0qQBNwDZ13FoSKKzl5sE2d4xlPT0htDNE6MAX8dlGEPIcoePLrnTAekHnHJd392gHV1ieKaRwIARh44eNc54E1lOWf/BP6ctjUt2LOCEUFYGX9nJCa3i6Vgx7FVniubp/QOdqlrMLvvvf/J+5fPs644HnW//0/8gv/cP/gnd5idpZEiki70yKn5rj/s+fRX8qOA/57MASPMu80z/1E4oQLSdeChZnF/QKxWf+xn/KcO86dx48Yvnt3+CgaBg0glQasrTBCUWwmuACL127xHI94wcfPeJiPue1mzfoFYF2FaPQR4M+F/mcdVlG3VXn8a5hMX+Ks47v/HfHXDx5h6tb2xydJZTB4yTQtjHbr/Nc2u4zXS4JLs60gnMbkX2IquANIdN6g7MeYwVtU4NvQAS2RtukWmA7h3cWJRXetvR6OW3VobOC2nR4FMI6ZJqACARnCG2FqypsswRrSJXk6u6AXEvWXUdnY9tQGVg1FoUhVYqDYZ+RcSyblsoGvIxZgrlOaEwUo8abT0KIL1kHzL3nrLY0viEIwcOzOb/5g5adQcF03WBay7ifYkRGriWHe9ssm5a6W3HeBLLEc7A1xDnPx0dzQDIsUhpjkRuty6KpGA17BGvpEzjygfPlmueuXabZhDnU1qO1j+2VEQwSRZEq2iRDe8f5uuVkXZNJyShRaCEoW8uqanE2Pk8Ez5XtIV/95A0+PD7jvaM5RQoPzyqaznBlu0BlGT/+4BGX9wqu7Y64OL9gIQt2+wUTEUjzlCzXNK3DtAYx7NG0Bh0kXnuEVEg8zpg424lRPCidsFg3HJ3FanR7nFOkgrTXwyro9xKGowROBW2QdCEasIM1CO8IwoNOQAYEkiDtpgVcILIOnQ9wZoywc4S5wFd9uixDao1OU+q2oTfuxWeuLZitS5LcoVRC6FpSJZE6oXWOQa65cfWQe66hXCyQJupMgxQIEUW0OklRIkN5SaY0SV6wu7/PUk7iBSwlYJ+VHngEKkhmx48ZbCU4dUCzqKjaFUkx5B/+2q9w/sZbfHznHdIsxTlB4yvmfojowIaWDz/8kD9+9y2+8vkXef3akLf/+3/C5V/7X3KS3STBYYX6ExveswPyz3ZQRbhZ2DgGxcaQLIUA4Tebhc0x5h1bW2P2f/EXcUgu2orRwSFnZCxnF7Q+Yzjq0asqWtfhhKeylvunF3RNSXCei9mctxPB1z9xlXVT07kW5QK7W9vsjYc8PDnHuo5+mlCHjqfTY8byjLf+9SPGu7uMt0Y4G6sY4wxeCkQq2JKK3UHBynuckJHOudFXQfjJrM17Fw2zOkVGhxYCxcHOLokIuI3vy7sodBS2o9CS41VFiUIogdaaoAukMnRPj/GrGS4YVAikUjIpEg4nI6rVmlxCRWyvdYiCQxUzu0hVIFESLRJC1cYyXEt6iSJxBiE3+YlAngq0TFFSUDUGEpgax9LB/rjP7as7vH/3nJNVDd5EP5gXFHlO08xpnGPetbTAQChM2yKlYlE2pIliMuhzMY/WjuAdremom/iiTHoZpbA8WVY8ODrlbL7GNBlnVUeWJ0y0ousa8lSSJo4kU1RLw9G8QkjJ9d0xo1TRmEBZg5KSwWSAsR6JYzjs0zQG03Z446htR97LebKusSvHXuYY9HPeevsBX/3889y+vsNqUYH3VG1AZYI8S8kSSUlFXbYEa8kLhfHxhewlCtXXZEWfk6dTgvcb9nqEFM6qivtnFa2AJkypvUBetMgHM4xnE/4ao2Jc1yK7DlEUm05EomSsQoMHmpq0mwOKLh1Q5Jah8BRiwaOpxQ53yJTEthahIN/u0U0N83LJdpaRCwnSsqga8iJuHZXUXNnq0XUH3G1qfNsRnEa4JFZJQZEkGmcCWZ5GpIq3ZJN97i8agtIIHyBIvNyYgwU4HKOXP4V+7jkORMvs+7/PR9/5HSaDhPrhPT588IDSwBUJIVgyLWE1ZdXEQNxsvMN7dx6hv3/ES1/9EvL2Ph/+4A/Z/rktfDJAhlhJeR+isvjPjiKOldSzAWGcb26GheGZQflPdFpK63izOEilxlhDRc5S7tG/8RLNe++imTLpTfDG0lnD45MFXVNRtRYtFSfHFzzZG3LjyiEff/yQ47WjG11hko/JC8fJ/AkHu2PGocDaNZ231G3H6sGCxWKLNO+R9QoMgSATQqoo247D7TH7O2MkDiUTOv8nGzJrDUpGR3+iYDxKuHRpl5NziW0N25MtcA4lJFJHDLBWkqZtaKxmWgdCWlD0h/jN9iTUJVRLcgyOgBaCFIl2jrOTC4KPCdDLzpEpSZ7q6GOUAhkkjkjgVAj6Km5ikjQBCVkqN213tHuIEKuV0aBgvorGau0D1bzl4dmSm+MBmVaR5hkE/TRlZTwnswVaJzgi+uTLt3bxTvLkZB79b1qjkXF4XmQEH1uDxEVNjdaardGAfmd58+iMR2cx/TlTnsYHLuY1p4uGnhRsT/okSrEuWz6eLpnWLS9fPeTm/oSyrAjrlkG/R2cMeaLIdEo/1ygBd57OuVi0OA9vPZmihWKvSNjKBTrVdLXldB14/+P7XNsdcv3SEITmnXcek/c0iZT0en1aJUm1xGjFqiwRIkoUtIzBGucnZ3gn8SLQ2Vj1LTqHEVB7T+l83IZutt8hBmtvVuHxgnTWIEyLTA14BSieLbOEgEIZ9noJKhtwdHLOzu41mrMjlusZzpfgBY2pYK0p+mPSrQHZ9pB1W/NgvuD6VkKOBZlhrCXPMoq8wFjD3niAvH6du/cf0jkHziGEJ0vS+ExslkYByc7eHvmlV6iOBeBAKlwQwLNxQ4DQEDroVMZFPqLWu0xGY7qm5Pe+9T1yLTicpFwapOSFQoiEyahPv+9pveBg95CPFxb/8hfRv/Sf0QJbbR15K8HjcOBizF0Qf85wByHiqFxsJAlsEBgg4ufEs6MsDrJSAV4FvAjoQvPi17/OSCku33qJp3NDbzplulxRKEXwjvmqjFN/tbF7iIR3H5xy7WCH3cmQJ1XL9itf4LM/90X+6Df+O+RFidQpo0HGbgOtaZiWFZWHbjbD+Rl5nnPl0hWMbcj7EfqW4WitIdfbpElO11g8MaBSSrkJm4hJOwrY391GZzkX52cUWbphTG1YXJsYeaEk1iVUUpH2ejTLEmE7JJZmdoLwLYrAIEmiQFAKslSzqlpypamcQUixqTYUvSSJ2hQT0S82CDrvNivhuBpGCHq9nLpuQcU04K4zGK9ouxhXVpmO0sUHzljLg4uKVAQyLUhUgpQxG08h0c6jCextjbg+GXG6rNkeFNSdoes6hBCs6woIZFkejdghRABhkdEb9ZkIOF83nK+XjPIUmaZc35IsK0OuYhyaFJ67D074+KTkaW3YGRY8t7+FaeOG0VpLIkFnCW3bEIIk1z100efx+Tll2RFkVOtL7ZnonEVlcKVhJ0toJMyXnptXemzt7bCqWnb2xrTNmgTHdFVRd5a6bKJwERhmWcRVtw2ljQbdNFGsjeNo1TCrAx0RqeIRUe+0QcUIER1ybDIhxbOJrncEZzY66Dj7DFLE0gdBnmToXCKlY3e7x/HTc+p1g6cm+BqMQdU5ZDldZ7HW0t/ZIptsYReBi9UFV0cFAUmmY/CqEhIvFf1UM7p6Ge89dx8+xW+oClLE7MuYLytJVcblFz/Jk6bAC4PYfD78lI0lhIAISRR3ErFG1XqJlopl15FKKFRCYys6CpbrmiTxGNtSOtjaucTh9VvcOA7svPwC3szQrocRG4CB9QgiV8tvyqA/c67fs5tDys0s6qc+IZ4Fk8ZfYpNSIxBSIbxH+oDwge29QxKZUhpDPrmG4XsE4RE6IUHSCwl1a8nTjLrxCA3zdccP3ntIimOxrPnjb36Tl17/DF/9e/8LQr5Ne/d95osZ16/tRh5202KDQgVD5yyrdcnyzscMUs1ka8JwZ4c0S5H5mCJNqZoatyk1o64+Km6tF1RtS90ZVnXDqqw43NkiTSRhc/JronHVmij7n9YtqphEcoOStKsSvzzBd2sSETACchEPP09gXsV4Ky2jNEIJKJQgVVEt760lIgk3X4Ag6GUpk2Gfi+Ua4eMQ8uD6dZ48fszWsCDVGmPi/9eGzUvvBPu5YjgYUDU1IksY9gY417Eua5yN094gIUtTrl3dY910lG3FoJeilWLZdAQhETqlqUuksmRptO+0G2WylKCV4PLOkGlVsbaexcmMK8M+As/e7j46WFrveHS+4knV0s8Ur17ZRWuYzjtmy1VEhiQJQimM1dR1Q6UEtTFMV2uklFzam/DycMB3PnzAqm4Z9xKS4NgZpTyZlZROkRZRGDkZj5j2FvTHe0zPFywXTUyGQWJFnLMaU+OdiqRUFzBCcraqOV23LKzHI1FCMFYJzkMTHB2RwWS953/i+RDQ6/UQCJq2RvQiLjioiLCOlAuD8w4dBME5emnG/vaIE+9xPqEul8hQE5oG12pCVyPWM7Ad2c4E4cfUsxUgcc5hnMUYg91ctoPhEO8tn/n0J/BCc/fRRcx8TBVSJZsmSDHe3mNw5RPcmRukCjgXt30x2zL+mQKbqlHEYxgvEHiqqsTZCAAoTcPBeIhSCcPJLovZBUmSk6RDeldeQu71yBLDVz57m4de8HjRRqQMiiAVNoDD44PcDPL/rAfV5kuhNlop+ez12TC1Y4W4GRZuVrFRDCpAKoKP6GIbDKGTLI8eYpo1vTSncy1t16KlJEsSgo8GUuMso/4Wj2ctUkErPG7xiN/4v//f+LX//L/gl/7RP+bs0RM++Na/486b32d7a8zuvuDe0RMGeUERYrLFuipZlTWzqqJ/PkVlfYrxiEGhybXYANIkXdthfaBqGhrjWdQVi7Ki7RyZ1ty6fDmil4m3qDU2btikpOoa1k6TDPqAwKgOQSR9BnycX0gQ1pJv5nwmKKR0eKKPb1jkjDNBP83QiaRzBq0Vwzxntqqih9Fa1us1EiiyhPGwz+zshEJLMgI9LcnyPl2w3J96docjXnvxCu/deYQhweWasrM8Opui1YYTpSIhMgSYlxXHT8+4NhwSvGDtOhIvqdsGVzWMBn0G/T7ex1tZCMFkPGLYL+jqJoL5guWgyHmwXNPPNMuyZWUM1aNjbkx6DMc9FkZQFJpXruygpWBZliRpwu7uNsvl+ie0x+A9eZbTLwoWswVb/YIQFD0lGAlLTymWxuIby0RpagejIqGXprjO0JUVb91/zG/84BE390ZMckERLN74jeRDQkiY1o7aGCpvuahalq2nchH5IoIgl55hpulryap1bGUpXgbWDpZNvBDC5qUmEL2XxOGwCBap8p+EwnrnN8ngLQkpPnh0oiBV2K0tXJpxdOf9GECKR3qH9hA6TzPNSSYj9LCHt0NW5TmDXp+mrVFSYo1hOBpRVSXj8YRgOl5+8QWenC1ARNoIIZAkGUFkHL7wIhemHwfZP0VB4dnh9NPvv4wz00QJLl17jnsf96Bc0nhHKjzbOkGKSJRQaUrZWia9kt3tEYqbKPsd/vX/4//E3/lf/29Qcpu70w6pNhkMgAvxAie4P09c1rPhedRWCDYq7k3L94xNRQgI9YyyIH5CAkXK2H8Gz9nRI/zZh2z3NKsm4KQiSVOE96SZpOlaVJLQ1QFvY4pMh0Uqibct6/PHfPP/+V/y+q/+Ktsv3OYTv/zXeXT5Fkfv/YjZ8glpvmZvq0fqW4TSLMuClbXcPT3jvC0pfUl+foatLri0M0amGRaFCRFqb43HbsSevbxgZ2vCzihnmOcRb7wZpCdZQte00S/WWaxOSZIMb2PeoUp7hKTANBEbIoLYMIkg4JAykPP/o+2/nnXLz/tO7PNLK7x555P7nM5ooBs5EyQIkBRJURqFsUYztstVvrBv7PKf4Oup8o0v7HI5TLBKNTO2RyWJI1EiAQaQABEINGLnPjnsfXZ68wq/5Ivf2vscQDIbksZv164+O77rDetZz/N9viEkomupMVpRZIrC5KyrNcYYbNsQbcK1AiFl6vkk6xkWGRd3dlgtliglGQ4GaePXBEReMm/nXOwXFDFlFR5NF2msDZKqTf1jaXwyPnMebQzaGE4WNXk0VB6OFkuubW4wKUuaEGhdS08V2NaBUmgl6WU5RirW9RqpExywMx6QKcWwr8E6bs0rcp1z9cIuDw5PGGWGy6MhE1MgMkNwntZWZCY/P1FcF0AqdcpNnIx7jHoZj09rTuYVtqoptCA6T1tLDoRlbmcMlebxukUYTd5b88037nOwdDyaH5GryFYm0VrQuEDtIk2ItEEk9nknpzrvYgnkQnCxn/OR61sMcsM33z0gj5DlGl8FrJEsvUdLSfTJ57axDchEXIzOQpdqHEJAZZpyMCKwwAaHkpKqXkEEIywnxzMQEQNIleMRBC8QWYlA49YVMYJSBq1zNIF+WWKtxXtHW69RShPaBh8DW7uX2dndYHp0yiBTKa0oRkbDEVuXn+HN1iBV4rCFzlsuPtVoyA6XljGATFjhfD6jbiJC59SVZ2ekmXvLmBLqdaIaZDmv33zIift9PvGlObvjlm//5Vv8wf/hf8/Lv/sP2Lr0WY6bSIyy87lL9/PXjX2/XKHq+A2StJ06w6XSLZ5fTtIkFc9+KbWRISCJRFHw6J23wK3ob+6iVytWdct05mi9Y2NY0DpLY5PZe9OpyDOZQiu1STIGXRi+/40/5xWhGe/tceGFF7n84vNcub/P29/7C6qDe5we3qI0mjzP6BuD7vcwHtZVBQQOpmuwDXsjTRsEjTc4oWhagSpyJnlOiwQt0UpQNRWF6VbWQnZIXCpKJ1WDE31kcPgQEmNfGXQxxjZLRGeAFGSk7XznFWn7ZxRc3hoyXaxAagZlwb3ZEtF6+kVKQ94cjaito6rqNKZ5j3Oe/f19gnP0BiXrKl1Vc2V4//Ex/SxnNBjw+HRF6yNRCnIhaGrBVj8jk5FpHemVGYvlCtFhDW3jeO/olEikUJJl0/Dy9UtMFzNO5iuc9wnoJyZZihSE6NNGGJWKPJ4iE9x6PCczEus8Nja8ff8xvV7JMHeoEHFAZj3eeYJ16XOtkk10AK08SskkGJciebFXFaVSzLxDdYuIEJPVjJCSJkQW84b9Nx4RBWz0etwYGR4sanpRYttAayPWp3gmJVLadEtAi7PAdHl+Yd4wkguDjM0yw7YWGQLLJhJaS+3SRdtIwcTAeKPPaRuZraok0g6OWB8TbR9dlkipkUKQD3u06x6r9Smjfp589olkStLTmnUU3QYx0h9PWK/WBETSAApBtBVNY/FSkhtNcJbgLEVeUDdrinKAc0kGY3BMRhtU8+TnJoTCC8WNF57lwaND9PaVhA3HmCyaZTxfvImzcz0mcrcKjjt/+i2Wr/9TimBpQmSrV3BjpMiMQIlInmXoIscKhSpLvvnGPU72/3s+85nn+OqvfZL3Vht87y+/x3NfGSEGH0cEhyflHUbA/4fSE1THGFWSzqb3aaQqIjp9GeKJc0F3gUpiZiLVasn+nZu8+pkvsPXMx/jZN/416vSARd3g1w2rdY2QBqMkSiQ+ymQyYTgc8vjwEKkzrj3/YX7lH/ynrGuXbHqtx4dAKyJ7Vy5z9bn/KavTx9z63p9x/N7bHD9+SB0cRmqGZdqMLFcrXryyzQu7hseLOY/3a+btCo9kuW6wPqbNJYImRqRKIPeoyBn1e2xvbVAUBqVSqo7MyiQEFTHhD9YTXfK+SkRZQ4g2rX5Jr7yPkTbCbNUwKkvqNpCpkJwnc0lpJIVOL00MAWzNsJenuPcm4NuKojT0tyfUTeJh9fOMLCuYuTmfeuYay+kRU+9Zx0j0gn6vR9VWPLtdcO3SBt99+yE2REQvw/pkFYJMoL1UIm12bMXBbIYJgX5mmK4aTJaRlxkbG+MUi5RJ3DowXdasFisKo5FSsLSWQmiM1jQRGiJivWJQ5rTeI7uYeh8cRZHjnEOoZFnceofMNLnKyAmE4NivPfMARkh8GzB5RohA8PSGJUVhKAvF6emak8UKCWzmkceLhi0d6eUgg8B6lxYg4Ux7qVmtUweC1CgpCd7SyxQ7/YJ+rnl8NEtbOxcpjCYEn1jmPhIi7A1Lnr+0xcxF3rx9zGnT4ERAVCfoZgxlD2kUWEe1qohRpsjzhKnQuIgUgjJLE0bTeGLwrBYzvHeJdpLpZAWjAe9xYYHKNCp0Rn/BYaQk2AayLCUVDYZIERn1DNpoosgYjCdUrefO3Zs8s/cxKqeI2KQ+QXROnwlPE4hkOGgkYT1lwz5Eloq2WnFpc8JrWwM2xZqjWc3Mtqxaz6bKaGgYFjmZyrg98/C9h4w+/RyD3/mH2Lrm8WKOLUFIDwHiBxi4/FKFSiLItDrnHZ1tLc8aNrq1Ip3wN3b9YxRJzprSawTerfjib32ZncsXiWrMi5/9Cq9/4/fZyUvW1YoGgRaS0FH8o4D1akW9ruj1euxdvYHoD6mFpFUS6dMgLZXoCqQnhgyVT2h7I668+jIXFhdYNjW37z7i8PiI2nm0CjR2zcks59Fx5J3TNbUXKKGxTqQk2+iQWuOtT3pA51m7SF1VLJYLnnv2GTKjCBF0PiDaiGtT4rJvW4Rt8e0ydaGqQKCTaV905yTTNggqGzk4muFjZCvPCdEzGhRcnpTYxrJqE1s6BUt4pM7oFQatJEWRERH4uqENilkrODo6ZqPIyJWj2BxTNzVZZSlCslrWKjKejKhWFcM8x8bEfQPFcr0mhKSIR0CmRPI+OjhmWBZMeiUi1vgQaLxjsV7TM7qz1YmJP1OWKBEppGKUZwx6JblWnK6XjDK4trPNbN1SL5ZY68jLnEKQzOqsY920ND5gXSKWOp8kHTPb8nhV0QrJg9DQ0xrjPNo5JJH1WqRYe5sz6Re0jWVZOx6crKmjYtIzZAakTxtQSef9TZJYjYwGKREqMZvb1rM7GZAl0ILWpd8zXSxY3TY452lJvv25khwfnXDUeIJrUgiFiGwWCidqFiLxzYJzmCxnYV3qHKNHEgkhoLUik4F+v0fjHPgWb5sktLYtRkSU0SACWVHglp7WNiiSRs47izGaSCBEh1YFLni8bdgeDyBEVK+gNxzz+PiUjX7OuCc5aVMsmBCJWiGFQAp5LmuRAlSQmPFFjq+9wEs3rvP21/4FH35hhy//9m/xvX/2LzHV+2xHSVlkDCd9VqZg48Vdlu/e5db79/Gf+g30F/8By7oB0ceM+wQVEUElsvUZaeuv7ac+iJ4guuQPIkIKJOGcof70LYYzbVD3edc/xpBIoePxiDgaUFuBdAs2L+2ydfkq/XbOcb1m5ZKdrhAyBS10EFfwjvV6SSElq/mUxaN9yu29xLjtNApSSJRUqXUVkVDVWNbMqwVEuLK7xaWLOzjnOTqdcrJcIG1kbytHacn96ZpF3aBU4sh4IrZNAlVBKrouegqp2dvbQUuJa1tCFJ3DQKCta7wDESOuXhBclZ4jYVCmTCCx9x2mlxT5DoEjBQx4lzALQUxuBrVjtmpQQqK1BBGxtkXqhOW11qY3rtbMpkuaRUNAcHnQYzpfEM7sS7RmY2eT249PKYucZeUJbUueFRjAaENuPSG4FHzRWXwsl0u0lvQHgxT/5Vo2ioIHsyVNyFiu1mwOBx05VrK3kaxIonc8ms05tZb5NKXzmqKkmdZsb6QudNTvEaM/d/v0IbCsGqLURJK7qhaK02XFOgTW1uMRKVEXaJ2l5yVbmUlC2xiZt5FF0yJUQ5kbvIXGeqSUZFkaK9eNxWiTuGcxWTcnHp1E6cQlyrSml+VkCmQknaxKsW4igzIjNyZRRXJBrCqWjWPlAs56TlZtSrNR6ViFDYTVAj9sybI+TbVCyEgxHrN6PCUEgTES4yEGT5FpBj4yXyus59ylhAjeJjlXBHp5hiBtiRPUEigLQ2ZyrPcUecZgNGBrc4OeUWTR4gVkWcFwuMHDB4/45EdfhIHhzqxNet1uIyCkQIszV5E05mMsOrZsvfAqj994m/W64ns/eoO33/gpe0ozLkFqaF3EtpLnPvVr/Nnb73BgA9c+/kVGr32BlW+J0aCIOGnAWyClrQfRpbD/B2FUQnTK5njuV/7zJUomU0zRcUk6ZtuZz3oQgkCKjQpRokMgRkWMFl9F5k2FkYpCxkSLDMnlIBITEJ8YdLz33ptk5QaP3n2Lly5dxtXJGE8K2d1nxDtH0SvR5YDQWLw9xigIWoIPSAI7mxN2draQIflKX7wY2LWe2kaq1uJDGoOapj6nX2h9FhiRCnXs1tJaKVyIaK3xPiTJAoHQrJCdnzZaEpVO4ae+5YwoG4XHRsnadxHsSrFaVyzXNcoJvIs4L8jyDOdarAgomYSzSNDaEIRiulyhypwLwzHz6QmLpmFVJ793bRQDkxEWKx7N1khjWK8rdiZDtPS0IaKNYbPX69jm6c0jhcaFyGq9ZpgHXrlxEaUUjx4dMyoNp41DZZp13VJkmmF/TJ5n+Lamcp7p6YpNk6MlSVisFSI66mrNaNhHqrRxXa0rtFBUVUvrU/euRGJxO5dSYZoYMUJghEB2eI7WkqFSjMqCddtgI7TeoWMiDIc2gPMMc83eKOfjL+7xk5v7zJrAZqEQBKLwqPSC4bwjWE9mDP28oK5TpqIUpE2dShyjQWnIdOpqnPC8vD3i7lHDbLlmt6fpFTmVTXCI9455Y3GhBmdT0ZOK7Y0J+/MZjSpYtY6BFgx7eQq+8IFMwaBXcNoka6AYU+HGWZrlElPkLKoVI6FTETamC+9MmGlZFEBge2ODYD1Yi8zAlD229y7QNh7pHBvjAbOYUsOVlIkj2HVTSiS/KdUZ2YWgEEITjk558Gf/Eunn3J1NGSEoN0tyaZAOesMhp7Mpf/VX3+ZDn/sCOhNM1yVFf5t51EQZk90MKaYsxNSxnkUbxPjX91Qf0FElh0whOq5UqknnRezcCP4chYtPfZpm7yDSavY8szmCNiW90R6P144zdjuAMQapVOcMGVFS42Og9i2qbbDTOVoJPB4tRQfun30k244bL32Imz9+HaEyoMFojRBpw+WDRzmRNnhSs6xbhARpJMOsTyQJlfNc4b3rOkXZeZYLtNIE19mv+ogQmqI/YLVYnPsPyaxHiCDzAlX2iN4jvUGYHt5WnPle1THSCkshBDZEqqalbj1DY6hbS+MCZZEnwqDzaCMZlD1WqxVSwGLdMF+1KG1p8BgRiCEFUJyt+VfrCick0zawWK/oaQkmo68hSo30kcW6YjZfknWR60JKSmNQvZJCaQqjaKzHysjGuKQ6WaKFPvfL9yHgbIO1DXW14sKwQA1GfOf9OzgXuTEc8cyFLU6nM/LtEVVV0bQpp661nqqxWO+hdRglcDiaEBiUOXnjkZ1n/KAwCAGjYY++UdgmYIOkqhyXBjnSZBxPF+wO+4jYMhxkjPsljx+fclolY7vMJLjchRQcS4yURZZUCVKxNRlzcpISiHWeXDACSTibG40IAS0VVe0ZTCS7PcFiBas2bWanrUVFcU6SxGTEIGgbiywLTk5PqNZrAoalqzFWkAmd5DoyvWeGNrLShtY2aUJwNb5aEonEIkshFVmE7jUIZ7kFPlGBJpMNlNGczmYUZcn2RsnGxgZaG9azNZPxkCxLmZd0zATdjb0yCrRIy4Qk/4komRHmM27+wf+TrLoNhaa/1Oz1c5Rv0TInzzKE8GxfvIzrXWBv1Kfe2eb0gaM2Gdg0bYV45g6a6sM5iB5JTIF/X8KnIKJVTLsQASGe8S3kk584A9fPpDVnNSyeJaA+VdzkGbEoUNsVs2aVCpTWSTAqJCG0ED1EybA/onWWWb3Ay5b7t29x9d13ufT8S1S+JVnxSpQEYnJB2L1wmUd37rGa3UM6gQhgjKYs826LAtFGWusRQndvqpiuSh3Lnpi6GgDV6ffEuXeVwTuL8462blh7TYwSlRlAojeB1hIzk5xEV3NC2yJln6gh2HXqNkm12xFZrB0+OGwdmGSaiMITqG1DL8tQStHLSoKAaVORo8nLAUXb8MLFbXq54Wi6ZF23rBuHs4mt3O8XOMDPq5Qd5yKnq5pWS2y7xmTqHCOQUpJrjRCJftDPe/QyzdJGapvGh4HJGectwuRdV1STZRlFpinyHvP5msermp6Di/0RRRbY6ee0bYvJPKv1jBhkWqPHFODZ+sSbymJECuj1SibKcDKvoMubE0qQ5xnOOtbLhjWBUks2+wWbk5LLmxPeenjCqYVyVVEozUAH2mbNrJFslxl9XTDIBG1dI0Qg+nRC5kZTFD2WszltVaUTVSnGwyHVaoEQkkwHcpN4gV5IxNoy7PW5uDEkyxRHhxXOBbIoCSLBB+nMTMGrSmra9QqcTKEj0tBGQ65lSuzuOhi8p2dyRoMhx9OWGAUxtoR6lU5m16C0xA1il9Dc9QddDzAcDCmKEqUNRwcHDAYD8jJnONqkrhtsW/PhDz9HG+FwsUIoierE1NCl9Yju/RAT7bixjpt/9vsU9h7zPODa5N/mXYtXsG4sRT6iqj2zh8c887mP8sqnvsBf/cm3yBuJXp7SlNvJ6y0hJZzVpFS8Oogo/ods/TozK9ldIWJXsJ5wHtIWsNtpnd9+gUN2TmmQUeKkZ71as37wI0ql8CKioqAWBhdajFEImVO3nqat0CZDR4kNgdPVCd/4/X/Gq1/4Es9//GPJVZRAPGPNx4hWGZeeucbho7eoqxlZEJ2vUKDs5UQhqCrBcp1SXCQidUkibTliSP9WWhNCeELo86kNb60lxoAyClkHbNMSvUNqT4wCXQyQPfDedk75MpHmlEKpXmeSdiYakNjoOVqvyZq0+emXA6p1SG4M3hKDpm0Dh+2CLMsweY+H0xkrV7HTyxEhEF1KmukLTT/PsK0hCljVFp1l7OWG7X6KQxfO4aQmLwu0UTRNS9O2iEZw5eJFsCmVpMgMZZEzW8zS8xAky6alzDTrpiF0I9pstqCtGpSE2kdWLXzpI9e59+iAXhY5WjQczGu2RgVV5ZPjRGuZLdasbaBta0YmwyiJFZGLe1vE4JkvVqylQytJrnOUlFigcY5CK5RKqdLbmwNsCNw6XRAkmNygQmRvc4u6WeG8QHlQWpIbBcERgkcicc7inGOxWCTg3Lb0B71ErYnp4qFVjhABrQxCJwrK9mRAbzRibCwvbEPhIw9OHKftiqA0zgeMECjv0hJFRbRJmF81mxFipI2aYBtUZlDS4FubdIc6UBQaYzJs05LE/w0iZMmvPAS8L2hD4mkZbSB6Nje3KHs9MlOgpIEY6PcUWzvbWO9oradf5lzZ3aLpX2K5BCUjnA86sUNcOyglhjSO+4YXfv1vUsrf4uSHX+enf/KvaG3NRiYo8h4bGxOEUPTzgo3JFtNbf8Uf/ZePGGSRKpyyevPbyE/8LhZPiOLn8KhUqETX1PwHjH50p1MQXWsmRJpczvhTHbP1fAPY3Xv8xQ86jhESrSQP3/0p9ckDJuM+RW6YV57j1RFSdfcYBEoKqqqiJwRaplGs8Q0bZWQwznHBkpE6ojPKhIjgnOXajevcee8y0+UJIQZ865FSJHtiBaWBcmNIrjNWbctsugBSF6WUSrhFjDjnknsEJG8fLzuTvYg2yR6EoJP9SWe+F4DQ2b7KkPR9QagUdmlylNpAtFUy3482JTSHNWsbGQ8Mykgqu8Y5j5WGGC3OpYCH2kXIC5YNOO+ppKVp/ZMIL5lTB58y46JHyPTGG/cK6ght3RAC+CCoW0spEtlRGcOqaVg1DRfHA6y1FEWW4s5rxWxesWoshckZ5AXBV2AMAU9jPbFt6RWGVVMhQuDdB8fcPDhmZ2PMfLZmMhxgZMAHx7xas388w4XESdsbDykE1K0DKckzQ7W0AOn5lxlaSVSM9DKN1pJMafJcoZVO0qa2JQTBVj9nMiw5mdbcOzhle1TSOHg0XRFMui8pFLmUmDxiVboYtzZFTmVZSpK2bZscvaOg9S5dIIymX2Q0TeB0tuTBccvgQsnWWFBXlkUFcgmEkCQtQqG8Q9o5o9GzLFdJlxoiCGUIwVHbFUoZgmuQ0iC7qaA0hkFZMrWWEGQiXboaRJnSoE3i2REhM4rdnT20zhOILyWr1RqtNOONMQLJdD5HRHj++RtEU3BSZTQ2WRudJ6E/vQjrtvUATutEPtUT5m6bXBoyEelLEL6lqSpMBmWuePU3f503Xn+Tr/3RH6CD49e+9Byxf8TDsGIZeghh8f5sOxm6BidRyT+IpvCBherJXHmGfYTzGVPETuh4PvXF858jdb7dA040ySgjoXXcffNnmPE2o2df4vD+XYxcMOknUWmU4az+EWPEWsdgMEJIQ9M27G5t8ZHXPsphlTAk2a3IRQcGxhCJQjLa2OX0tibJSgW29WRZikRPc3laj8bIucNnCGkblR536qV8SAEORnWCVNHdX4xkRAiW2KnwEU+6NyEiMfonL4hMGyZUBjagM0lQCu8hNhERKvo6gZnDUZ/6VBBQhJjIj0VpmAxyausZ7Q1Z1Q1r23KyXiOlZrpMCwBCYGcyol8WWFmzqhwxSsZ5Rr1aEE1HAxEKlWnC2nYBmJqjkyl74wFtW6M0ZJkmxoDJMmgDdWuTt7WWtG2doqSWFevlmt4krcEfzU74zs1bSASzxjIwknFwrNYudWG05HnOJMuZZAZai1QCFyV5blguV2AjTW0JUtHGiJCaQklGRYYwhtPTKbnRxOipqppcKHoaXOuwIbkELOuWZTUnV4JxkWGRHJ/MGGSGYZmju4TsGCMyT9vAzKSsyDLrYduA7cioe7sTtsajJIFp5hgdWUxXHJeagWqAJPw1SOqQzgEffdpozY+7bAGFtQ2mzLC1w0VYB09mAyZLQaehC17VwO7WJnXrWTeJwBlDin+b9Aq2Bn2MlkzGA7Y3xigtaVuHzgqss6zqNZPJmMFwyMHjQ6RU5AquX74Eg20eHUMkXTwD4vx8jU+dw3RlJEHLEvC443tcKSWtLNntKTaHJVIa9HBEsbvLez+7zcVLV/iNX/8c//V//w3+8mfHfOwf/idUIscHReAM901Aekh4Uio0H0Cn+oAA0pgOVMQOpH2ylYshdox1gTzbBp4Xs6fnT7oHnTqu2XxGuTnmC1/6TYrNy9SrBT/7g3+MdAuWS4/FY5RG0I0/IfmYe+uZlAXL01N+/IMf8uyrn6JyTZeKcdY+po7INg3Pv/AyD9/+EX59kIptlDStRaiz1a9EaYlWiqzbiCml0xtXSqxrUd0WM4aIFx147JLsQGUKHZJE1cezji4mUDMJ4tKViYjQGpzDOYspSpx22KYmSoVUGePhkJ084zMvTpjkOW8+mvPwUUPrAje2BuyOSqL3vHx9D28tq2XL2geOVhXeJo5brgpGZclyXbNYL6lrjQ+WRR04bVpe3b3GM9kWq6pi1O/hXWAVIj7TTGdrdJZT1Q0n0wWZCuA9VbUmAo1tiTFSt46T5Yq2rtgYj8nxGCKDsiC2aaspYsK7RsaQCc/OpM+69pRaoaSh8ZatwYhRkbGen0IUzOYNOi87Q0NN2cspy5zpqsF5x8liRSwytnc3WSyXlEZ3cqYMIQWzxYrt0rCsAo8OpwzLnMIoVG4opCCqgK0jg16Ptq04XVuG2jAsC5y3aJNGLUmHl+UGbz3jUZ/KefLcpLSiKBiNBqyqJSI4pqua4ciQ64Y8E/Qzw6JtUUJihCRD0q7X1PMputfDuZasXyBEi6/qzrq4RYiMGD1FluF9osUIYxgNx1S+RghJrgIXd8fsTQr6ZYHzDucj0/mSXpETo8TFFqNzxuMxk81NDh4f0DQtQmleuHGDS7u7vBcHHFXp4kqHDRHj+aQUzzbTsWOqB3Ba0Vu16OUxtatRuaIoMprKojJFWDfIVctzn3qelz//WX74Tz2b195l5/prPLC7HKMh1IQzq2BIfMufqzU/H3T871SoImDD0wXoSRGKIXYOgqBiOknpjMjOYLH4FLaVAh4jvf6Az37lN/ECluuGg4MFs6OKYVaQ6RkxGvpZWmMfz6dUTYtra3wUFJOCybjgu1//11TzFa987vM0ZzYbHXfChwDOUfZKPvTxz/HDv/gfKHKNjIEQItGDMclPqe4sg7Mso6pqnPPdY0zbv+DPAHWdCrVLwRFSSqyNqA54dl3U0JMxGBCaEBJ+pbQmqlQhozCIYoxwkmBXhLal8pJ8WDC3Oe88POFn96fMbCR4j5nVPLfTQ4ohj6cVVd2kOHIpyJWi9gEbkgB6sV6zM+6TGcXjZUWUkrLMOXHwzr19bmxPUkpPCJSZItjIEsi1OQf3GxeI3rM5NCBgczLBGI2YrljVlofzFRpYHs547uIGo75EBsnSRdZVTSY1C+vxoeWl7TFXN8csqhV5OWBVWY5mS6hhvZhTGMV8sSIqMKFiqMqEA/qGgGfSy9FK4kNyUUDrJH5VmqqpycoeTWuxUTLJc3yzJJocbQz9PIWOyhBY1pZV5VBAWebUtiWXkdY6jFYE70EHyqJgPBmxt7PN4eOH+LbhwfEiUSSUoHYtTdOQm4xYtThvKYoSHQxl5jBKkZs+hepRZppeP+dkvUKuK1S/xGUFvvXEQqPNEDdbkRmX5EM2Obu66MkyhcpzhqXh8XSBMYbNYc5mIWjXK+bR07Ytq2pNpjRb4wlZlqF6mmG/x8Zkk+PjY9qmwVtHJgQ3Lu+x8BlvnwScgIhP3U14UpjO/hMxFRKIyBjpTU948Md/xN1bPySEliIvwC/ZUJpelOSscYcP+cnX/hlxdodqaXnx+otMXvgs9/JdYnC40Gn6zlaNP1dlPgCg+sBCFVNm2dkDedItdRYWnTeP71pGSfKtObv79DdSEUlOywKhdALUugIT6pbB5Zewd37AeJgzW0PV1Git6RUlrXVY22J0wf7JCTYGpJe88Zd/Rl1bXv3yr+O9S4UlnmFoIHzkyo0XOXj0SY7u/BRFk5jUUoI8c0+I+JA2h0LK5IduMpxLGFWKhk8v6Bn/7szcxnkY5JpivaYKRQoZFSKFRnSvgw8dfpRJhMnO535pcmIEVWd4u6LyNT+9P+XN+1Nc6DA90ghrZUYxHLMhI0jolyN+/P5D2jbFUS2rCo2kaiNT5xgMhpRFzth5jpY1lVuhouewikzv7ienBQm50mRl8jzKixyHJLiW/cfHjAcFWxsblKXCe8uw16OuLYOiJcs0o36fTCt+/OAxo2GBqFr21zWXhz0+eW2Pm4eHTMZ9aBtqZ9ke9WkDtDKypw1FlhNU4HSxYOlTZ36pP6RXZoTgaZsWYzJKkyGix7pA5SUn0xleKlarOsXJ28CjR0cYrRgUhnFpWFlPcI7+xgYDY3hw/JjGtin4SwlWjWXdeoSPqBApC02WJV6SyRSubfnBX/0keaS3iXIR+n28a6nWq+TrJLu1lRBIIzFFQRNAlhOev/ocz770ES5dvcD2zmX+H//F/43bb73Oxvo6/WeeY7n2uNaR9wqCyUGGjjaRpS5Rq85RRCOiRcU68chiFypiNPViSZGl8IhyUCK0JO+XjLa2uXr5GifHpyyXS6bTKTFKrl7YoT8cMc+2U/I3XaMRXDfynRWqs613RMQEhzi75vT1r2MffoeMmGyxbUVVCPYmhjyTiAx0kbNaLvnBd37ClVducHHgOHp0F7H1HC5KgpBdrTg7QZ+uNGdF7OdZmr90oQox0tj0YNLo9wQ7ijH1Sym1olMw/kL79sTBKq2efVc5zw4rOM/25V16G1v85M5tMrOi1JbGt7TWdn5H4tzrqW3h8HjGYNBnc7TFaGeMixHXBoRWSJWKpw8Q0v6ZT/zKb/Lo0rP87PU/QttFkkEKgRQKIQXepT2H0RLnBE3TJEFs9LQ2dBuvmFwSO/tf55M2baAyLgw0q9NU8GJHDkUIok9Me2EGKTWXblw0GUJJrMpxZo1sFdSKaCWtq88ZyaklD5yulnz9J7f5tZevcmFzwHrdUof03BdSMLxwgSgChydLqumcd+4fsD0oGZeG3VHJ2hp2+4r95YrTpqVyyZ9dSYupLSOt6W9kLNqGACxbi24Mj06WDPsJ9DVaJ9yvnyMjjAYlKEFpJA8P51zrj5iUYCSMBxlXGbM56aGc4+7xgoPT5EBamIQJrmvHdLFEGENZZLRNzXy+wreOXIFRgu3JgNmiZVnVnYumQjqJbRyVsxgtOTg8wqHIu2VLlkmubE5YLJsU2Nnr4R4HJkWP2kei9ESlqReOxjpaLfFrSxEMQgQaqxBAVkrmq4p2XROFxJGwySQEbokh8dpC0NRNQMYcyiEvfuijfP53fiddrLzkn/zTP+fh6SFKZ8zvP0BubBOFIYY0jgWpsd6iVR+tckCC1Bip8DFS5hkXNsdEINeQaU2ms8Rv1JLReMBoMGTY73Pl2jUG401OHh+zv3/A46PH+BjolT2uXrtCKDd457il9S0R2WHN8qmllzg7udPFlNTJRjlk8qW/i9rYZP2t/4F+NeNaJhllka1hTraxRb65x+P7D1FZTrm5y5f/3n/Gn/1//hWLR/tsHr3DeusVfLTE0E0VZ9SBp1H8D7h9YEfV2q4hjF2EUCA9yK5FlJ27AuIMhOu6hrQvTN9HJLM8njiBBh8TgBgD+WBE+czLtG8es+QUKSXOBwigpab1CXBUSuO9xTrHhWeu8PInPsGjefJVhyQ8lTIB7K6z4KiD4+LzL5NtlPzsW3+EWM5RMollbAdeEgNFnuG8x7sUPJm6rtBZuCp8ZyrmiUlaLgW2bplIQ9+0zFyOjB6ETj2XElCUyCwdmym6wtgmyUXe7yO0wHUWOl4k7kpw65978XyMPJi3/Ksf3uLyuMeoZ8iyjIsXJoRmTVWvWVcNOxsb1FVNW7c01nHsLCrL6ZuC1bpht1+y2yuobeDRbMHcekyRkfV7DPMSomDqqlQUpORoOuV4li4pZa7ZHo8AhRCOsmc4OJ3TF5F8PGCxrrAhcKdywDHTqmazdVzLMmarlluz5Bo6KjRHK0tPWka5QWYZ49GA+XxG8I4i0/QyQ1maFGYgBV4KTtae2lqW3nNpULAzTCNiIysIERsFo16PybAkH/XTBlTDbPqY3WFJVVmMdgz6JZd2J6zqlh+/uY9SEhEjTWPJtWG1qKnEml6/wFpHlhXUsWG1XDHMNbZt6BpbjNI4F1iFEZs7z/C3/qPfYpmN8EqBlPzlX7zFm3dfx2yMid4SgiPGjqRpHdU0OWUELTFGE3xAZzk+pLxDax1lZtiejNKSxtkU55YZssywMRpx+dIeG5tb9HoDQpQ8Pjxidjrj6OiQGCN5nrO9vcXu7i7RDLi76LZsT412Zy3FGYZ8Btv4Dt0W1NSNol2uGJc5BkNBpFekc8F7z3xesXHtOu+89TZO3uJr//f/nOlccX//mPLgbS78zv+Wu3F0XjeeGk/OD0E8jV/9uxeqlAkWOeuoupGPQOxauMQPk502Lp47gYpOxCw7pqsUoM6Yad3fcZHEaQmSbLKD15r+cMTy5JhIahOVFAgf8G26SrZR4mzg3s1bXL/7gLBxAddxlqRMXCghE4YTRCBEj4+O8eZFfuVv/mf89LvfZHr3DYx0GNUivaK1CVAti5K2SYXQqAypVZdb+OT5SHIiSQgB6z19rbk2znn7xOJQIJK1qlYGCESdXCVCiMTWpggsBNb6JFnQJhXE4BO5IbR4H0GE8/sVBIyQtE3Ds8/uYpRm/3AJOrXw6+WaQVkgY9JmZiZl5B1Nl8yVoraO6CUhREyu2O7nTEIk6oxVW9POAyIKMqFoQ4ItvPcpOFqk8rx/dESvLNFEpss18+Wa4aCkbmDBms3hkOO6opcVlEZx52BG7A9pXRrtHi3WrGqFUoYiVzx/achsURG8Q0hJIU2XBORYLC3rusGhebxqmdYukQQbeOniBn2j8CGS9TU9DQ9Oaga9jLI0tI1lOB5hvWBlPaXyDAaaAoUC7j86pGo9OjMoKdCJf5wWNhLa4HEhMOj1cLZFRJjPa/pFj9J0Cxup6BcFbFziniypp4bnshEi74Nt2b+/5ht/8seoPYGWY6JMm1KRZ8lLP0ZcaxFe4vOSiKIo+lhv0wQhJcbkaJ2w0dY5JD2kUvT7Pba2Nrl25RJGa+qmZbFe473g4OAx89mMokhRYYPxiBs3nmVVtRyv0nOGSNSVJ7duGjpHk1Opkh1Wa0VER5jsbFPchpM5vPSlV9ndfI7b3/sjru1OmMs+GMGrn/0Mb99+j8Xpgr/83i1+71dfopaK9v53OLz8W6ykJ3nk+q5g/nLd1AcXKsCGlLPmQyCcAWJnLNLujgShk7FEJLJTY3euoDFxv7UURBk6j6ZuKxjAR0Vwger4MbVbY7Ii2Y50mXZGKUYmY1nVSJMhhMbawPxkyvf/6Gt89Hf/LpS9zjOI86xBFVMXFxC40BJJItzXvvgVbk0m3PzJdxgYTW4iskknTK9USDFkuVrjQ0wjYjfu5ZmhtS3Bi07QmuKWMDAhsqEth20kSoMxyd3gTBwcIwTnie5JNJB3FikTuVQImbSNUiFVjxBWgOUMZJQCMpKesaobLlwZUTcNDw+XCKGYjEbkRidZEYlhninBqN+jspZx2SPThkeLhsV6xYcubnNh0sOGyL1Zxe3jBfPaJiwuCqgtRW7wvqHQEmsdVgjqdsGwP2R9OMfIyOULYx48OqWXSaSrGSrD4WJBYRQRxdw3XOgXjMcjbh5NmRSS3Y0x9aqmP+whtOD9e8e0QbFzcZembpivG4KAtfWsVjWN85Sdp/1WnpFJhVeaxjvefTjDWc9GodFacbRfU5iSSxcGPJid8JNHx/S14gs3Nqlax3LVgkqWwU1bc7yq6RWKDIlvavJMU5YF89mSoigpiozpqmJp4Xhl2RlqgotYFONLz3G7HXDlQx/jzte+zs2f/ZStT34OoUb8xbf+lKq9RxGv4KsV+WBAPhiAkOk9n3lEtAgtWBEAhfUOKTVKqSSbCpF+r0drW4wxDAdDev0eg34fIaGuVhyv12idY4oep6cLDh8fdpY9kvFkzO6FPWxbM7lwle+eSrQKuE6BcT79iO41f+qcP1ueeRHIVMa2nTN76z3uP9jn0WKB/P4bbPT3kW1NODxkvCOIriSKnL/3v/zf8KM/+zrrv3qHH37nR7z6yQ9zdP8N2PsVgi6TY8cverOfHc9fU7c+ePTzqUi58ERxfuaRfl6oxJMOSogETssOXFedl1WCsETXhcUO9wKioF6tOLx7k4FSOCRG58SqSaBetyEoygIbz0ZQaOqGo7vv881/+t/z4V/7CpO9K1TRoUT3AzJ1fE4kQ7Sm8XgPLkiuvfxJjM54/0ffZJQF8qJHU6+RwTHspTfoummomw6kd54YQ5JxOEcIicWsc4MNHoXjxmaPdhqZ2rT99F2Ue7ApXisE/0TVKJJXFzEJWGOMSJWiw4MEKc/ivlNL3FMwKXICkfmqpm4qLl6a8PBoSeNC6r4ExOAILhK8QmiTRMDLFTvjgjIztNYRGsVitSbTnmG/x8WxYWdwgdNly0m15sHplOOmxnhHHpOkY3MyYrauqBpP1bZEAjPrWN4+wq4tg7FhmOXcO6khama2ZmJynru8zZWdPo+PTmgrw0s39nDOcWu+ZN20BGHI8z5tVbOqGpbLKo09BFZ1BUHTV4YmOIRUFFLwYP8YXeb0+n3yrOCoXtFUjjvLGZWHiamYVku2tsZcGw5ooufdwzWLRcVGmWN0oPWeTAmckDyeJXF0riPGOtato1fmzBdrrr18nagV9989YHF8Su0HXLx0lenhAXdv7iOvf4YXX/0IV4qSqJMU5ubtY967/Z1kxe0jvm1p4gKlDKYcoEwPXZISlXHMVinotCw1vrFpiy4leZbT7/fJs4zJZEJR5gDU6xV1XQExdePOMT86YrWqKcq08RxPJgwnE5q6YfPSHnJ8kcWxxQdLjGnEOpOOCZ5s6Z/c0jtVVi3Zu19D3/suJ+/f5c68wuQZWWu5PDxl78oEvbHHYdWyqo4Zbb5Es3zM7PY9ymLM6eUbvDn4CG40wnYeVwKfsLGn7jMVq7+uEv0yHZVPGjcXwXf41FnpO2OkS85mzLOuqsOjRAoxoPO7iYjz6KAQ01ZLCkvlImoyZKCus7cz4Tt/8a0uSEF0FryRuqnTdlFqpM5Ye0sMFWL/Jj/6/VMmz32ED33x84hcp64uBmLHpPcxgEoAN6KlEZ6Lz38E6xruvfVdsi5OSYXEdcq0Rigoi5KqriHTKAS9sqR1ltVqRYjdEy8VmdH0leLVQcZ3b550rN9ElgzubGMYUbpTjceIFJG2i4yPIVkgC6URZSSExFKO0ZNpxatXd1mvKmzbEpznweMFm4OGK7slDx4vCShaZxkN+ywWFS7CoqoYDQRFrjmerxiOhgxHPZbrNckHwjBdVGiVrFCUrOljeWVvg3vzFY9WjpUPNPM11qfjiCGwWNYUecbR0tKEmkwqxqtI3Vg28gyjNSubs1rXlJkhOpc2rd7zcP+YQKTXz1muKxqrmS8rysGAB49P0oZZCKTRBCeIEhApQixDIHwkaM3jkxXiNImzixjJZM7WuKDsJedRBeAiRjSM+iWlUgTbpL8vJXXddd/Ck+U5y3WL0BotA1pppNDUtuX49BgZHTuTAQ9P5hxVisINOVrcYnJxF1P2yIo+7uWXETgaCz/98fdp2zolCtsGgcYuVswrSzmp0f0BWa/Ae4Fva2JvjDc1Wqvzs84YAzIVkDzPqZuG1XpJ0zTJc91olDZo7WjaluVqjcpyil7JcLxBr9+jWtcMhj3K8Q7vn0Scb4lKEGzotvQ/f54neOeJYFhEaJ3HhoZl5Tn1gdIIrg8zcix3T1tmLnBRD3jpE1+gfPE69dGMuLYEFM/8zj9kdfHjnIjiCS4VSEEO3XIi1YunsbJ/30IVI633uM6+9d/szuI5d0h0+FOy66DDp57uuM5AddGNiqLjUwjyYc5X/uN/wKMffxf78KcMCpjXEY3Bep+y0jonB6TE+pZgHbQC2de89LEXuPKJT+O1wQsD4ez+ngD8McZz8qiUkbaVPPPqpxhv7PD263+CtysQCjSE0NAryjRWDXqAoG0aiqJAKEWRG1arFU3TdN0j9LLAxXFJU094ff8YGw0xGoRWnZ86IAVaaNqmTQ6hQiQlaEwOoRKQyoDOEN4TYk2/b3BKcme2ZHdYsLExwrWW5bqlJdArM0xWsLU14fDxCc45nHUEH6nr9LxVNuIri5KwsTFhOV90L5/GZCV5qRhJDc4z3ijJFWz24J2jU9YODpaOURbxeFYukgUotGAzH3K4WjGvJdFENnd7lMJTxj5eSN7ZP6RUknXVMqscC68R0rEzlkxrxeHjU7IsZ7ZYdh5Rgtb5ZMsTRSdcdtgQUSJSRwkuMg+exnkKaRj1SwbDjEGuyWUSkSf3zcBka8h2v09GRDjLorFYIRAuYKTClDl14wiZQMXAoOxhJNQ+5dwtK8/FzQFXwhLFkP54RHX0kNNGcHzvAT37FvP5V/HSokNAZj0eLw4QWYaoPO26xRQ9QtMgW0sjwVpL1iuTIFhluFqyqizjIuPMkDcF4oL1jtnjxzif+H3O2W4BFemXPYxWKG3oD0b4CDu7Fyh7fY6ODtE6YzzeoLj8Cvcf+G4hlpjm4dzU8uwsTlu40DHGz4kC/Qnq1d+h/8xH6f+z/zP9k0dsZilPqbKeal5T3XtEKL/PV7746zwIKyY7PUbf+QGHu8+z0mO0W4LQT42av1Rd+ncrVEC36qczuTqvTekmuurb7fJS1lk6DknK9uNs1xc7oFuQ2OrxLHPeoIKjahVOlZw8eEQpNZtFH+cgxJYYzugDKR5IaoU2Eh89iJztZ15CDrZwtUUjQDkE+qmNwpO+0guJChBxtBVsXLzOR/t/m9f/4l+hmlM0LnVLIQAeLwRKpgDQpqqJRAZlj15epOckhOSFlWmiD7x0YcIyRN58cEqQihjB5DpdQa0FY7pkDzB5hnMdToAmNA1pRZ0TjAcLs4Xn+6uHKASXL25RGKhbwf2p472jKc9uDbk+7uHbZPJvjKLMM9qmhZgkIVcuXmS5rphOZ3iXMJFVZZHR03qHDz3KXHP1yh5H01NC8FwY5AzVhEfzNSsbWLaOdUh4WSECu0ODMgoVevTyHB8sd0+WyODJkNTes/YO57rHJj3SVyBTks7xfA0BGt+kjZgEG5NTghaRTEiilDRBMo+eLEbmjSUpChR9JZEuIHygWtW068DmsMegZxgUmkmvpMgUi6rl3tEps0WFj55+kTMZlBR5QZlrciORwjNdVKhixKxtee/WAcEFrA1c2tng5eevkt05ZO0tM1djurQVe3LE0Z177Dx3lVxH9h8d0bgl471LnNoHRA16kKOrPq6dE5s66fZ8gzCqIxKnaLZ10eG5AtYdCdn5NcvlKkHcokvyVsm2yDpPnhf0+wP6wxHD0YTluubNn73F1uYGw60JV69d48j3WQVH6LbRTxQT3Tx0RvT8hSYkAiJ62iDpjZ9hsLlN3x1TakmvEFwqSuZOUjvH6eERf/h/+s+58pkvcXpviLmwh87KZLynzgriGewjfoFD9T9CoYrduBe6YnU2V5678XX/P8vGEzGiJMRzO2LxhDfx1FOQflYkC48zZ4UQqERG7+UvoY4e4W+9ReNa6iZ5OCltfn77KAW1syAi8wf77Dz7Kl4E6FjlHcDD2WtzHpQaSJ7WIaK9wDpHf7LFJ3/ld/nhd/8Yv7zfxb1HorfojupgjKGuaqq6IpJSgpVKGr+yLBLZ1TuGPcWnrm1gm5Z3DxvQ8txhAlJcfPBnGF1CymWXYBtCxLfJjlnIlIocvCc6z/ZGxs6oz+vvP+B4URNDYNwvWdU1dVWh84xCKxZti8kMg96AxbxiXjXo3CewXSW7krpxzFdrLm5tsKwqrI/kQNkruTEe4uoV7apmllU43zC2gqaX8WjdMG89VbDMqsiGSozpYT8nOMV2zHg8XTAaKDYGfebzOQsXOVg0NC6y3cuY1w0PjlIyjpZp6RIQtDbBCqNegRGglGK+WkOEvV7BZr/HZqkIwbOuPKobCXOdUeSCEBz9QUmzWmKrAEoxXVnuHM5Y1hYbPLqT8RiTE4OnLAzb4z6T4YAqBL72/fe4dbDA+siwMCij+cbrN9nb6rM1GXC8tLx5PMN6zbDQYBfc+tnPuPqhF9DScefOLZzzuFCxcWGH/mhIbTtDyGlDbEie500EKwnSElznRNFYpDJorYjAcrnqdKOiCw5J8IRzlhAj1loGwyF7u3vk/SEP9/c5PjpGa8Xm1g7Dss+Fa8/yw3uBENt0jsYzc4DYnd/nLdX5uBQ5A9oTbpTnGe3+A9r9I7YKSa+IZEZ0ZOAewlrq2lNkFe9+609AjXj201/mYTtFFz1CUJ2+rzsHxVONznmd+eDK9QEY1bn6pys1T8Dws/sKUZz/rOi4QIjY+S8/+UjVgidkUSm7gwRIJ+ml688hP/QycVbzg/k/plzvI9drbLXChUDoeFeBSJGXaS43cP/9nzK6/Azj6y+yahsMsSuQnM/HIX0pWdbEFFwrgkc4QUukN5rw0c/9Bj/59tdxx7coMoEXCiFTorOUkrJXorPkqiiVOjctQwicd2TaYFtHbjSff3GHEA959yjN+UIZlE65bsSYLI792dbPoHXE5V19tXTCbAlY8GuWS8+3fnyTxoHRgUk/oy+hX+b0jKStlmgZUFpzuqzYGA0xWYZuPQePH7O7vcHGcEjwDcO8oNy8wGsff40f//B1FvN5ItgqzXw6p5SWvFD0Qo9+ZomuIXjLh7YGWB+5M685rFoGw4wtE9gZ9ziazlivGxrbomWPa3sbZBeGrELg7vGcewcnKBfYLHo8Wq5Zi3QCn5nMiQg9KcE5VJYRQmDcLyi0YlwUtN6Rh5beuKBZrhP5MQe6cX5Z1RxMl0gEk0Gf24enzNYNXmi0UESZshnn65Z17djql0wrx8HyhAfTA07rhvmyxsRI30hGwyHON0TlWFYty2h548ERdVTsln2GhcLS8uDmD6lnv8L2hUvcvXMT16ywoaW1LXuTLa5f2+O9B3eZRoddtzjbEkJAeIcLHuEbTN+jsxLrOpC/tUSSbtXkOTHGcxJznvcYDgu2Nyds7+zhPdy6fZvlekXRy8nzgqIwXL64x2kYMWsrguxGvnDWVKQz+NxL7ik1yROOlUAqMHfe4f6//n+Rt4ds7I7ZMJ5eZrAiZzjoc+3KK4hsxc++92NaJ9i+pPn6f/N/5eXPfBb78u/xXpwkl5Hz21mxik8K5S/RYn3A6JdW7GfF6hdny/SY4lM/LboTj6dsTeWTw+icBOJ5d5YKX7Ic7pwJFhVlOeHia1/k+PU/QptTaGR6U8tkfSwlSBRa5sxXc6brmsXX/jmvfelvsPPsC9gz1m13x90EmrynYkR4wROCVMcLw5EPN3j1C7/NG9/9OqujmxRK0FqHVqnzAlBao0lXhyiSp5FS6b6cSOLOXAh6ZcanX7hAbfd5uGgJPmBDotGFGLvlgzhvi4OQKJMhSGECEQFSIY3AO0EGlAoGWpNrQ6lhZ1JwcXuDplqTlYn1vrVTcjKtWK89dZ2cUoOAxWrFoJ8zXQcuPnON3QsX+PE77/LsSy9z+Og+x4cHvHt7n4PDE0ZDw+7mBr4J1DZ1qL08R4VIbiSXBgVGBfanpxwLwf3pkhjBOUFlHdOV4fF8xcXtIauTGdGCEYaTpqENFUpEJlJjMtNhhrBhBJdGffJCp045SpxPIL1tlmyPB/SNYVW1jAcDekVO69ZECXVr0VmBq1L3PVtWxOhovGDZVORAMciSLMV6Mi2pnGV2VHPrdMmpTcnJW0pyYXPA1sYmcxeITWQy2uDB8Zz9+wdo1ePy5g22ruxysV+wni45fnzMOz/4LuPf+D2ODvZRfU8IGfVywZs//QnmnbcZbG+ji5KoFNJmuNrim4pgG8Z5ZFJo8rxHoEIbgxQS0+Utuq6YK63ZGI8Z5RnXrhTMlprHB4+pWkvb1OSZodcrGQzHyMywfXGXN6eKENV5tua/PTa9W3Z1/46RLiYLtAs0q0Muby744jMvMlQtqm2RwiCLCY3ucfEjn0D0R9x674Sju+9gHxxw66jinX/5NZ7NXkBf+/TPlal/39sHbv263IbzVWa6dXOuiOdjoADoRMpSJj+p826KjjcVk/tMJOW3dXUqgd8IZEhZcUu5QI+3sEEzKHNOl/PEEFdpbPFRYgNIH5mulhTZEHmyz3f/8J9z4ZWP8+EvfAGkTi/KGW2CbjzlCVck+kgIAhVT0KcNDSob8OEv/hZvfvePqQ/eTpIFoGkrsixjtV7TK0uaqqLf7+O9R2uJQOKcxxiNrRu8NmS+5ZXdkoDiqErCYUIaO2MXw33W9oaYirvQGmkyMIGiN8TXNbY9oa8Fo1yRK5ki4b1ChIz5fIkNns1BwWhYEmLNpe0+798+xsdA6x0BqFrLxuaAx/stP/n+T7hx6RHOexaLNa+9cJXVasrd/SNmrefgYc3j05bd8YCsLBkZjQyRRVXxYL6kto69YZ8rE8Pt4yWPlomxPcgNwSgO55blW/d5p6+pGkvdpGI3LBQbvYJBnqdOlEAIHucshSnIMazrGpFrFouG2kta69nrlYQoeefRCcLDZDxAKUlf92ndGhsTKC61IYZwLjaWSqZ1uJJYD1pGNsqCTEscibjpREYmWi7kmt1RzpVrF2miJs4bsr7m4HjK8XRNnvXIig12X/ksf/Pv/QbKOXzwNMenTGdz6sUScsnq9JjR9mUaYyBGWtdy8vARIsvQWYZQGqUyyAMm1Fzd6bNVSrRKhNeyzNBSUdc1dZ06VCLkWrN0lnfu3CFc2+HTX/gyMWjuH5+wuTGhKArQOnXGscVsXeHeu/b8/RXjE1O8J9Xq6ZOXjqydKlUQHmsU289+giuLnzLZXSKmNUW/x+mqxuAwEdZ3fsjSD3jm+efRvRyZD5nmD1k9eIcXtnJ+kBxi/poacz6r/bUY+wfYvHQj09OPpvtG5Ez7J3/u5884GiliSz4FZHdR2V3rd+YFRCdsRqZCEoUmuBRUUa/njAZbDOYrbNughGDU73O6XIFwKKHJVZ7AWBd45fkbvPybX+akiuf2MvLMWP0X2s/QzeOBmLAhJ5AioJVFK82LH/913vpuS5w9wog1oijwIcUV+RgoioK6acjynLZuyPOctmnOdVp1XbFcrZG24upI0krNtElcmQ5LT0cinhTOEEmkP20whWJy4RpGBA4WD1GhRoo+awZsvvgKWvZY3/sOLlh6/ZKDkyVeSoZ9Q9O0RBHIco1UGXlraVtL3US0UgTf8P69R2xORrw/e5+sOiYvJFd2xgwWK2pb0rbJYbSuGowoyU2Ozg2Xsg2yTEH0+Nby0maP47Xh4XLN2js0ghAdURiaxjHOCobKJfva4Onnio3ScLqqGZYZ2mS42Ge1XtPgma4aWFqyTKUQjtZx7JfYRRJSD8sECjvXcGlvxGLtqU8DmZSs3Tw9PgR146mDRQtBlhkkAR8lp21gKCOjXkGuA6+UE9bTBZujPqPhgHpZcf9kzXDrAgeP92nrhjIzZMYQTcml6zcQRJZWonNNefkKG9dzVss1qshgkQpw3huwtrP0vhOe6C227ZxkhUJqTdkvka5hWUlsk3Soi5kg60bfxjpQKQ0H69kb9siV4g/+8ifsPzjmy7/9t7jxuc/zzp07zGczIpb+YMiHXv4wp77H2q8RpMyC89J0hhGdV4UnYPcZQhM7PzVzeszDP/xHHM1/wv33JKJ1XNoesDXKic4R8jX+CPKNHmjHVn9A29umN2ioXMTf+RH9j7zK8hcA9HNy09PUhA/YBP61dlVpjuX8w4tUHAN0MTdPOBjdXZ+ffeJpbIquKHQ2pD6mzDYfu6+R/u1CWi1bZzg5fICgphhtQkjx5lokAep2kTHUksm4T6YlmZY09ZK7t97l8MFDkDneu+4VSf1Ux/ZKQH93UQkh5aq54NNHTCLs2jqiynjuU7/LESNa0QMhMEYnYF9JpJLkeZb8rPIkFM2ynLZtOFNNKa2So2QMvDjyXBYLcurueMT5sT152pK1TJSK4WQXZXL64yF6vMWRDfz0aM6blaLefo7P/i/+d+iP/DZFWbK7OWZ7b5fjacvpDEYblxht7iBVxnBQoCUMyoL56QpsoC8FioBvai5duEATBc5J8I7dUUEhIqPBkK2dLTY3JmxuTpitl5zO1vRyzdWtMXuTEUZLylKw3Zd8aHeTZ7cmjIcjojFIo8m1YFwKtgaacU+xblpOlp6lTVha2uYa1nXDct0S8IQoqdtI69N2cDQYYEWOFIJBTyEj2NayXtcIUhLL5mTM8aKizDK2RiPyIkPKZPxnSoOQkVFZEkLkeLli1ThWK0fTCC73Sz58dY+tQUmwlqquEUpycnqaLF3ynDLPKHODkZGBDng0yEhoI00dqdvI4XSJEAEzGCGFYmd7E200umOZxxCILhCdJ7oGu1qwPj2lWa+ZL+Y0bUPTtrRtS900nWFjSGky3jEZ9fDacOXGNXY2N3j99iP+i3/0X/PDr/0pH7t2nSsbE0RTs7ezyYUbL/LuYYpQ8yFhumcGjqkgia5OPIFqzoqY6nyiMic4+ZN/Rjh8HVd7jg4sp8eON9494s23H7F/eExVTWmX+3h7TG9jA2U9ihzx4a8w+L3/NXdPHdjlv724nMHWQjw5jr8Gq/olMKrzWvPUlu/pdeZZ33iWsZfY6GdryKf1PGfSm3NpkRBE1BMMDIhC0AZBvZiTyQDuFCUiLRECqJgiraRW1OslWqYNXW0ds9OHvPlH/4KXf+vvk23uJj5NSPSos+0STz2W9Hp1YuCQFEggUB0Px+QFH/7Vv8MPvv5PGPk1w0KiiwGZigjnQIJrLUZnWNuS5xlV5RAixcEPBwYhFe1sTiYCzw4jw77i4UoybZJANQWcn43V3YdSVK0nVmtUzFGTPVbTBdE1ZFqyWs6Yrabc+Oo/4P5/9w7azClQDMoMHzyHx4d85LUP8cY77zE/nWJ6Gltbev2MXj9nsFpyuKyRMTKfLbi/XPHMpR0uDHtoKRmGgqw35otf/jyH9+5z+723kLmhCIq6qjiexURzCJBnOdqAdQGdBWSW3CwvFSVKpk5i0O9RDga4AOvGM6ssIgZaJTof9EBW9DidV9TW00TPamHJNUx6A65dvsh8eZriqlSLC47KSSqbM58ueXj8kHXTUJqcdZ0sYPLCkCO7lb7CB48MkUmecWlniyt72xRKUBaKxXzJwfEpi6VjHSS1a6mbmklRMBj2EDG5pDYCpkcHED+cMDSRaDh5CNy/cxuPxPSHXLl6jRtXLvN4f5/WJqeNc7ghuCTtcpaeEsgOVC/yAu8cXiQrogB4H1BCMhoMmExGNK1n49IFPjYa8e0//zaz2YI//JOv8ej9t/m9r/4Kz778PKvemNOV4nQlac/O3W7bF58CmqV4ylYlCoJMY41QSclRnRwzPfgZWR25kkuUAq8EB6vIQdVwf2m5ctpwaXvBtY1Ndva+QHvkubesKV66wcy+iNv7CFZkT2rHv6UOnU9r4t/+/bPbB3umR5L05awCn2FWT3Ur6a66leaZ1u/8MJJR/NnBJoRKnH+eyh6dB3RnjRocm1eeIdhPolc32dvO2T8UKCkpcomIirppCQSU6ipy46kaOHp4k9f/yX/FzkufYuOlDzPY2kGFtOpPsdVnd50IcGfNpzijCwBego8eZ1v6gxGf/o2/z/f//F+yXjzm5lsPuLQ94NKox6CEvCgINpCZjLpuMMZgXXv++cZoSJ4ZZvM5Vhom1ZrtXclBJbl1ZGl8IuMRnwI6hcDXFUtb01Q5XmaojUvEaorpj2mDYj1bUFzexu99BHv6jSQ9iRa8xM4Ed949wFRQBkN/e8TecMTRySF5XnIl7HH7wQPqxjEsSqK3rKolV1+8xjvvHxOynEsXt2iblguXL6NUxNx8l8VyRVOlkTaGwKDfx1pH9E/eBZcHGc9uFxg0y0XNdGU5nVccnK6orUdpg3WOXEtc8NQhYl2CAXwEIQKZASczpAhMtgboWLHZ63P58kXu3b9NFhR1Hbl55x5KpK5/q9/DdFmPWuvz974UGUql+/KkWPaXr19ke5zT1mvWdc1iuWKxbBBIijyn8ZDrAiUFpSpQ0hFCwARw00NaH3FCphFJKabLBXfv38L6Ch8d9x7eR2cZ4+0LPK4fIrxMBSo6RIyd42wgEyl0IrQea915n+2TzSdSJwviotdDaUMhMxQGPZzw0U9/ip++/iOW0xlv3LqD/edTnn/uBeTuda4uJC9MLpPrbfaDxkpFjAqlaoKX3fjXWWp3UhGtNco5glEoVTLaEajdLa5VDZcy6PUkmVZMF45Hy4b3ZoJTlVE9mDJvf4prG0Z7zyL2l5R+RXATXNFDdvjzv1mcnoLKPnjp90GF6qkV4s/jbk8o8OcVuvteV7sSEH/mdXP2691QdGaexVPd2tl3Q2Kul9euctI2TH9wk7LYZG88JUhNXVdkmaHIc5arikW9xncx1HleEqLHVidMb79JI3Ou9ccUvazD2n7efTR95Uzew3k8PaFLyXUC5y1lb8gnvvJ3+cEf/hM+9Gxkf7Xgm7cfEVzDx5/Z4/LAIDr1f1okJF+qsixwtqGXaxiUeKEYDQoUgStbGZcmhrsnlvcfL3FnL5pMXK9mXaHLjFXdonVO1ush+zmTrQuMJn3msyPyKy9Qbl/CHQTWrcPFMWLjGr1nPkKtJav3f8buy1cohGfXNOxcucLDu/ehXfGhGxeprWA2X9P4kqPZijfeO0TKHGU989kpN7jOd7/1TYK3bI1KZGhYhQwpNc456qZlVTUMh0M2Rj0GdkXdRJZzT9XWEFIkWSJP+rQxzTJ8s2ZjNEZJyePTFevGIaXkwoUxvnGs1zXr4MiMoTQwUJKiGGJczbXdLZq65cHDY/qDEYGAcW1ajBCQUlEAnuS8YUwG0TNbLWmiZ6ssGaqGZlkRomA6XTJbNqA1mZDsbA84qkoO3YjnX3uVrY0h1cM7zO68zWq1pDk+xDY1rclRaNAZD/ZvMVvOyDNDdLCqKt548x10lpOPJsl2uFpDUARnk/85llxJiB7TmfbFTuWBFOSZ6eQ8MomTm7SoWcynKJMx2BjzxV//Ej/45ne48/Ahrx9MeTj/MS9deEi/vs2zV67y3MXnWU4u8oBdjuKYpZQslGQVFEEEZIwgNFIGhIIMTV5XFHf+ksHh+7w4cEyee462WVGoko/++kcJ1nFy94DPih1+toA//O/+Ma+alrd++j79e8d4K9k6vsOtSQ/RSrwKiPBk6vrF+nJ2++vGPvglOqrzAU+cbQSe2uTBufpZdSfpebPUAUHnJNEzfIj4JOcvguh+X3QdTsLDIqK19Dc3eObv/69Y3H7Ew+/+t+SxIfgsBTYK6BsNssfpqkJIRb/XT/HovSGf+4f/KXV2kbZtsd3q8nwe/rmnKJ4f7xnZTYiEmQmRxobYWoTJeeXTX+U73/wXCGH51IducPvBEW/eOWTw4iV6skIIQdMkl9D1es1gMEjhpR27XStNkElSo4TixkSx1y9Q3vL+DFoEBEvwLvkWnaGeMlAOhxS9kgu7e2xs72Bdg7M1QvZZLiK2f4nBa79K7+WPUushbWspr3+MuLHJslnjDt6n/emfEPHkeR+7nqOUQmdpLDJZzr2F56u//hmy0vDum2/wJ3/0dS7ubXN0uqToTchln1JlrNY1oAlCYtBsX77M9at7PLj1Hu54waOTKS4IhsOCfi8nc56w9NQ2ILVjMOyR5RneWrY3xtiQ/MeuP3OVQaY5PTrgZD7D+0AeGtat4eBoH2UUIThaG2isxXYndLAObQzRhWQNHVJAbaYlQjj6/R5CGZybUQg4nLVcvLxHtVwxXRwgTYozmy5aBmvB5miLZ7/4txnduIH1lsGHPsXe/m3uf/+b3Lx1m3q9QI37hAguCB7u7yMklKZI8ILSeBtomzpFpmea3Z1rWNuwnE1xTYtuHL08WRNNJhOUEqyWq9Tpdy4gSkBZZmSZ5vR4ys7uFlVV0S+GiYOXZ7z2K59n8JO3eHT7DgerBeHREcrVhOkR68NbbF64wkvbe4xPYefCFRaLFY/EDvPJRarKYbMJIq7h4CETuyQ8/Anq6C02NrdwL32S3U9+mm/8wddYfP9P8X7J9nPPkw3GlKbHxcWUF15+kfr4mG/f3OdKv2Jno8fW4Q+4OLnCXT8CEThToYhfgMTPF23ig5uqXyIu6+e7qKdP9idJyU+GwHNGRkdqPA/bPCtEZ53UU23fmQFf2iTGzlER9GjIMhYMXn6R3eWXmL75baQ6TcWgMGS5YbloUCLZ9C2XKVE2CDg5OETcuIZrFsigEgcrCgjyvHA+/SjPOsAnhRmUFnhI28pQk29f5sO/9rf44R/8tyxPpvzmR3a5P5vw3s0jPnptghaRJjYgUkhj27YIoZCdBMe2FqkiNqbVdmWhWTc8t9Uj0zXvnyxZhtSNZYVBao3TkWywgR5s4ETg7qN9FqdTPv+FXycgsdZSj5/j4m/+HZrJFWZNg2xXxKCxqsfptMEJw2DvNfSq4fQb/xXrekn0js2NCb3BGKXnjAiYQcnDu2+z8ezLXLjxPHJrg/1HD2lC7CyWI62PrDoXBWUyPvraR7l1+yYnRcZs0WKFZDiZoFTG5taIVz/yIR49uMN8dsr+4QwRPNs72wRhOJ1OKYuSK3t7DPsjrG2Q2nL12jb9/cjB4xmHxyuOa5fe7GiMkRRlgVMpoTk3+omVTghY3yKExChBv5eRZ0mkXlXQM4LBsM+bdx6zJseuVvTGm2zmmkfHC2ZE9heBneducGnvEotl3WUwGsLGs+z+1jOEN75HHXL6HoKAEDXT6ZTWWZQSSK3RJNa9Xy3wLsl+FstFGudMhgqCjWLAxX7AZIZRkWNyTT0YpG1fpyHNizLRawRoowCB6sJIiI7VuqI/GPHq5z/HM9eu8OYPf8r9gyk/OEjP2fSkonf3mJc//Bo3bx8wFi1ius/F8RVee26TO9//DjmS+XyOaBz5xoSLH9nj/runrMOE1770K3ztv/xv+O53/5Q2BKY/qhj/7B5SR8Rgl/GFGxzPK3Qd0a1maSzuZMH2rZ9w4foXuStGyK6A/HxR+vlz75eZ/X4JHpVEii796wypPy804pxUKTt86uz3/FN/46xYPT1GnhE+BXRmg098rkTo0ouBGFoWJmf04itM776DaWYsvCdvHYOix6DMmNV1YtnGFFPkXcv73/oTXt19gZXaoHVVclMgojsmV+rwuuM4Y7GfMUO7J06GgOyy0pQXBF1TmpyN3QucHDb86NaUV65NGL20iY6qE2N33uuYjmOlQQjKMkfUERc8w/6Q+XLJcl2xXjdo49hQjudGmjvzyIkDXfTpDQas2wZTDLDNGu2XXB31GBeRUVEw9YHymUsUz/0nzHojYmNRLuAFRBzRde8NEVlWNcXGJUTeowgN68pw0G6xM7xBf7Pkwkc/iVycIB+/Q7v/gM0rz5DtXmC8tcU3vvEXvPHmTS5tD9g/mSFUhg3gbeSHP/wR165cYP/ePU4WSw7nNaPBiKtXLzKbz/nBj97k2asX2Rj1KHJJs27QmeLWvcesm4bHRzOycsBysaSua2azKXs7Q3TruLk/o3Jpa6WkRAPDfs7O9hYHhyfdu14SoiP4gIuJhzQpe2z0JFoEisxgjGFrkPHw0AGBUT9jua5YLWr8ouXKhU16xnBhZJg7SX7hGRqRYX3V2RolY8GlF4xf+QIgsDK9V11tk59625JrjSpyVGfzI4ROgac+EFydbHisR8TA7kaPq5sGB9i2IYZkUdTrFWgZybICpGRdVZ0oP2C0JjMZi8UKaRRGG5raIweGj37ld5k8/zI/+/6PaN/7CSo62iC4f7DmwckPaOuG2KwZCstke8kbP/g+r736cbx1lETaoo+8uMX2r36ZRwcNWyPNg+9/i+P772K15qRxPH644rktwSsv3GD/sOLrf/yniGD5wsUL5LnAeok2hqPDOTurQ+jdSP5z8sxZ5ekN91kpOIOQ/gNGvw6ueQJ6nbHDASHkz9EgnrRv8SwIGLor3Vmhoitu578AHclMdIXtbLEfkhshIXU03pMNdlH9DUx1SFG3FLkkywSyTVIW55JGTiqNd4LZg5u8/S/+EVc+/7uY7avULsWSW8I5Z+mpJQjx6fZTSIRM2JWUIGMC2DWCn337L9m/95CdUcm94zmFPub5i0Mk0NY+Xc11BjKS5cmw31rXaQJ7rOu6CwFN3WivV2JtwBjFrlJkRca7j2a0PpApzzO7A7RoUbGmrwsujAZYDAzHBNeiRps0PqKsQERLFKHjycRz7C106c9tzNChj/NrwvbzXPrK3yUbD/C37hBf/Ti6tbTvfZ/s4K+Y5PCd7/6Io6NDXnjuOWaPH2JjTlGMqOoVrU1uDN4HHj3c5/rVHZzw6HxEXva4c+8evm1xHg72D3j5uQtc3hnTNJ79WWDn8iXa5QyCwFrLw4cPkFKwWrfMZkv6eY+Vk2ghMUohdQqI1VlGnudo3W1olcREjXWB4CPrpuXKKBFKfZTMVy15HtnZ2qQcjLl19xGDfk5rHYWSFJRUJ2u8EmglKSlACtbW4sLZBKHOtaLORaSSKSJOSJxtQaROZzVfkDmHLko8IbkRxEj0jugdwVq8bRnniqvjMVFZfOORKtlU22AxAqJUuBAhOPq9AqMUG5MNmjbFYbkQUF5SeU8rYD5bUd0/QI2f5fP/89/m+Ed/zuLHf0R1+IBHqwrlHUIF2vsP2VYSf/+EpQtsjrfo5Rn78wWj7QtcZoM//r/8H9nZ3KOeL9kYjPnsr3+Jvcrz4GjGO9//Fn/jo7v8jf/Zb/KNr/+AOoPqtOWljz3PH//599mI0JIzdYby8V2yG5/CxuRN93Ng9NM1hZ8vYP+/bh8cQNrl99Ep288Sk590Vef31oHRqdwIRGdb3PncnB/dL0D94klvlewmQmfU1/E+RMQ4Tyt7OJHRl5p+f8R8ccKsiizXLbk2iGSWRfSOFgm+Zb7/Ju9+/YTyxS+x8eoncNGA70B+zjZ/QOfiSXccQnTYmezIqwJ01Bw/PKQ6vIPyC+49WPHJl6+ymXvaqJDeYzKDjqloNrZFa411iezorEXrZHcRvMPZQJGXzBcLpNRIbXDec3mjT085glSM+pJJHqmriqgiPjhaX6DKAaLsIdee6BNHR3Q+YUIKzi08YtogCZL3enQtx/OaYutFLvyN/5i1GrGsHdm1GyxP1yylYfL8p1CrA979yfcYFpL3ZjNOjg65emWP6WyeOjUh6JU9nI+JlS8CtWsYT8Y0+xWzoxmNa3HeIxC0IXLweMreIOPh4Qk/u3mK7uW8dGWH5WzJ7Zt3yKRCmcBk0ufSpQuAoL37iNAkA0GLx4eGGCSPHx+SZYrLl3aR2nByfMpisUQ4wWjUwyjBd957xKVLV5BOMt8/ZXi4IpcSgqBtI0GNUBsbhH4PUc9Rq8fI2NJ4i6ubZNLoBChJFKnQa5LqguCJEaSW+BiwzlL2+l3nIKlWS1Sm00wQLMG2CXd0HhEd24WhDG16PUMCRmRnaGddSkvWucA7R280JIRAkedMZ0uCD6waz8lizt2TBisVn3jlBvcfzfid1z5JVQ4Jr/0Og2uvsrj5Pa78+EfM7rzLdHHIyUqxljk2OkZZxk9/+iYOy9IHrl9vaKs1b7//FvWlmuXslK2L20gX8I3l0c27rOeW/TuHvP/GA156+aMs2iHv/Ph9blaRl776t3n0nT+n/NgX4MIN3jt5gJAKIVqI6ucWbalSfWBt+ncrVLHDoZ5YQcTzQvWkSHX3H1Mr16E8T7Z9Z4Xu36iqT3daZ/cR8SSjvtiBcIQIbYudPkIPxoTGYW2yNJVSoUIkU5zHYOloEdKwWCyZmILLl8c0eY967TriW+fH091n19/TRQM++Yjx3FPLCUXbNgTRApoHt29j3JrPvfocuXAgBbW1ZEaRFUlIGkIaN6VIPtgxpKy+qqmTXU0Xi6S07myeoV2v6JmUWtPTMF8t8EChc5QRmCwnH0xA6HTC4DtP+u4jpgtLiMn5QojEDwshYhtLtXuD67/6m8xVD2zK/mtbEFQIAlMNGxdeYfnDr5EXhud3tlmdOqbbI/KeoZkvaBUIpZFNwJI4UI+nlsFog3J7jJtO0a2lriqatkYgOJ4t+en7gVWbItLbOvDm+4/QSnLx4kUUgdpbJpMNosg4nR3z2S9+hrd//DNmqyUCw3jQ49rFLfqlQcsWowKyV6Y3cfD41ZKdfo8IbG9uIVvB6dEJWgtc6zGZQukN4sZVLn78VymuXSeaHF8vqO++zeL1P8fO75JVM9oQkDF5+gPnpESJTBcuLbuhQSa9olKUvZIQBDJq1utVcnZ1LuUGhgjRoWjY6BUEGXE+XZiV7k7DrjNrQkuW59RdnPxisWRdV9RtQ1M53ps23DtcoMshL750ibp1vPzxl4nSUDeBiKcdXUZ/dIu95z7P4OHbDN/4Fs3bP6NerVAegrXsW09m0sX00f4hjw+PWS6WnJ7+FCc1W3XDcrGgqSqm6+RkMW1KvvP11zmSI/JS8+LHPsZfvvUO4f5PMLZmeP0lHm2/gth8Dh0syfLwjKj09D/+3W6/lHvCWZeUqFNPTEzleZl8wkWiKz5nx3PuvnDWaT1VrOLTxYwnUfE+iE7h3fGbBNjHD8nW+4TBCKUtEDofUZKcxdrzgqgEXSyWpFnNefjdb7D9Gzcwps/S+qTP6QIpzh4fdDrlruh2IfRnIBv4GtPrc/eophSOa9cvc3Jyyje+/X0+/qGrbI/HaCIhKqKAfl5AiInNTqJxhJhy25zXjAYmPVZn0UqxbmpA0rqkARQkGxOtNSoKJIqi1yeKlOLrvOv4aKlAaSJKRXSnfE+e1xGLxHUFmF7JM7/2N5nrnOia9PsdBiekR7kWXwua4SYMt5k/vE0rBuTXPsHu7/w9Tr7/x8SHd8hkmXCwYY/dYc50usSIAcdtn+2PfJKLW5vMbr3F7uox+7ffJLoWLSSrxhME9HoGE/rofMLuxTHN9IAHD+9yULV8ol+yUQjEsKBdH7Gx3UsOn0qyNcoQLAlOM1vWOCFRao0pNpMzRChpwwStVuyMNNV8zcZGQdblGNb0qbae5/nf/Ds0ZY/jqiWuKyKKcOnjDLaus/jGP6dazCmiwAkPUT450USnyjjTiYrO4SDTLJp1Z3iXfNGlNojkXUMKU0hXjkubPa7sbSCCRXZ/GwHBp+2YEiptCmUqhMvVmnXdsKgaXON4NG147+ERpugRjeFoWnHh2V0OT4+5fu0SURq8iIToaHxkbQbEq59ja/dF/Edu45YHiFu3ePjWt2lcy4Xrz/Lw7m1OliucrWl95NKVLUa9DR7cesSiSfbQLkii8pyWEx7PW27efJ1Xr13j4se+ShnH1N/6fdS4Rz2+lIiq+QCHIKqICPJJbfr3KFLwS9ETnrrFsxO5K07iqft9UnHo6tmTjuX8Z9KJdWbtEYldEClPNoQx4qNMYueuc/PREA9uQrvGrjcpkGRG4ZEE71PoQgTvkqWvEgmEz01OrgRMb7P/h/+IyWe+it64QdMVs4TfPClO5ziVOCu86fgEaZOY9/u8+spLbDZ3Wa4y9ouMo4NHfOt7P+PKhT1uXLnEeJCT55LlaoWWiiLPklDZRuqmxWiFbQUuRmpru64ylXPvU/hmluUpFFMkW13TK8nzEmEyrFfMFzOMbYlBQ3TJTliAkSqpAoTAx4D3aSQUsUsXMRIXElNYxDOAMxVRoiSINEo6lRMGl6ntXfyVF7nyG7/Do6gJg0vM9UVufPyzvPHd73D5Q69yLas5+PZfsRru8PxX/xZq+xLWe7Y3n8EeP+DyZAd1cpvp8QHNcoWTkmBLst0X+dhv/UfJOO72j2iqBmWO2cgCzWpKriV2rij0JuteYPvjn6M+OYGj92hO7mM9TKs1KmSwWfDia59CHS/YeO2znNx5l/jud8nzfbLoUNJA1CxtwbNf+DUqbXCLGoU8jz8TvqZRAza/8j+hOl0QXLIUUlLxi0Ds2WtGTNKuzGhCE2maBikUKstR/kknlnBdgTEVlyZDCi1oKpcMGaUi+IhtHUopWuvOTxchBfPFAmtDsu2OYF2DMpIyLzC5IR+M6eWaenHM9rBgVUcaK1KHHjUheGKsWZge8eKrwKsULwRkcIyqGcWnv8L1T7Yob2nXa25+71tc+NxHWawl07f/31jvUXkK6Bjt7LLx4c9xPJuybb/BxlhSXbhCeelz6Lqlmh5QFX1UE0GY5BISutP+abj8f+yOCrqpSPz8F0JXbM4tP7uvi7NRrftq6F5U8dT3npQpOkFwOHcFTfQEgY9nRn0+dVQWTh/eY+vaJxh+9rdZv/WX5NVfAJ7oBVIqdExvFEKKtNJaMCoFWZ4TEeSLm8y/uWT42b9J2H0Ba59sMtMBi3PQLekU5TkVI2kWJU5orr/6GWbfe8gw06jNAT19hZOTkpv3H3Dr4SOeu3aJ65d2GJclTgaatqHIM4rcYJQg06YbOwUhrJKuq2kIwWN0hpQlxhhCTF2T6AikIUZs27KqG1atYKOqEXqAQqaOSkj0mV945xihlESiUV0EFEIiXMD5gBeqw7E6W+ggCSIihcf7gBtcIoyucfU3/jbLIFPnMdxk/PnfQ954kcFKsPfJz/Pun/5rhN7imc98GiYT2vUCLQJeGoq964TouPPoES++8hkev/8D1rM5jRnzwpe+StgY47xm8uo2j+8c8MLWHVbzE5ogqFuP1YoPf/XLmLXFvPhJfDTk7QnyR38Kb3yDXBlWaswzX/pduP4h3K23WQ23MR+5QP+lj9O+9Re07/w5vmmpHfQu3GCwfZFFlfBCpEB17z+kSeC3VJS7l5GxpTPWTr370xy8bkscYkwjX5ZTdO+ztrZEac9VDmf9ebCOC5sZFzd6iJB0qCEkImwUIj3nzqK1Ii+ytMF2HRYmJdZ5lFRsbGywpwuMyNjcHnDr6DHZy9d4fnuXu3f3KXY1hdDMU+uHlJEQM0RIsWcESyMUy72Psnf1Cqc71/GthejJTEZY9Tm5+iFm9w+Qec5oMuTCJ3+VKDWLakX74pfQDeyOLnJ46y/A5sx8RDz/BZid0jqNlILkpJQK9M/54v3/s6M6t3+IkRgivgNsz07sMzN4njrxnz64s+8JcRZHkz4/d+s8iyvt/mw4DypMDzKEBi48w/AjH+M026L40JcQB/v4o1v0ejn5eJOqWbI6PUELT5krtrfGED2zecV0OSeTAjGH1Xf/mL3fuoTTA+gkDVJ0T2nnoaWFRHXtd2rnU6ECix7tUl76CIub32KUa7LNMb0MeqXi0f4hb7x7m7sP9nn1uetcvLiFUWCr/297b/ojSZKe+f3MzI84M/LOrKqsu6qrq/o+p9lzcYYczpDcIYk9JECrBfQP6K/RBwFaQQJWghYQdkEtId5LasiZ4fRMT99HddfUfWTlnRm3H3bog7l7RGYf1QT5YT6UoauREeHh4e5m9trzPva+zztCmxApHHGsvIZVEBFHEcF4TK1RJ9eaWhix3+uTW02v2yMMI6/qaAxGG/pJzr2NbVZPnMPmOU75eDMpPOkrRBl57ypkqJTwJK+B0Dkv8O8czplC9NBLzggcwvqCGFpoOL7G4rFVRrKGsymhiYk7HaL5RbJUc+r55xgnKQuvfpPZS5eI5+fJjSFWAqFCQCCcJpxd5Phz36S5uEh65w4qMITtRWaOrTDSGoElA87+9r9AjTZY/9Gf4w5uM85ilq68jDr/DK2xpjfMMC4jVXXiZ78L/S3Mrz6ivnyC1soavcGA2YXT6CRHoBlLQePKt1FRyP7bf0mWZCyePAtAXGg+AVinfD0AHD7vNPB7zSKoeFVR1Gq0OIxzBfHt39fGEIeKmXrsXZ5GyDhJMFmO1UUystU0goxzy0uQZRiliiINMc6BkgLtDFGoaLdqpFmKzlOMtuRGE5da/WHEzm6f4+06y7Nt9kY5WQa37jzku68+zx//+AP+6OQiTz93hr/9eIPbXZ925qwvz+6QWBHinOX4Uy8jAsjScSEN7shtysKTT6PjFoOHbxHWFln9ze8TP/kyD67dYenyEoOxRRlway8gZ2bZowUkiEaLqNHx3LKYuLQVf13aBXf49T+LoRLwGSUGX4S0cI3KjwoDVn2p2tHjkAUVwkxOBDg5CbJ0lEGhJarxx4lCumHh8kv0tUDlI5JWm4UXv8PBL1Ky7fusrSyg8wajOAGbEEc1hJJcu7NDd5TRCGt0luawtRrByhL94ZBobgarPQ9UzmWJN1RhUZhSyioEBCecl2cxjuPPf4P9IKF38x2iwDE708TZnGa9xu5+h7vrW/zsg0+5cHCc86dWaTfrjDMfJ5NpyyjNULnfum7UY+J6DZXnBIWGVp7lBCpEyQCEZL/XZ++gxyDJqTU7hbCef5B+LHgLX0rylOW5RbGQeLUsiRKWQIAtq9IWiHdSWaggBJ0lmjmGxhFoh5Fl6W9wxpd4F/gBr4Ia8cJJtNM0hEAGAqEm8j4yaDDbvMDYBay89gcMbr5Nd+A1OBQKK4RXTWg0ke0niS7cJn/jLqK5wMpzr7A30L4cuHNIp3CZYxjFhM/9kPGNh8wtnyB1Eqk1Vnp3yllH4BTGBARPfIvazh67779JNDuPcIZIhX7CFOqsriiG6Wlo/8QoJlsZ2+fwMkVl+XNHkS6FqsZ0FEYkmUHIIsPC+gpDLh+zPBtxvBmSpRIZglQghPOfC0e97kMqkiRBKV8sVAUKEUiCICRJNdo5ji/NoPOcyIzIdYQ0KcvLy+goZnGuTZhpZvNdfnBlgf/y/j4PR75vXcHFOCe8mJ5kUmNPllysIIvbWCvY7Ha5+P3/Fs49xX7imDl1kQGOwDqsMjgR4xbP4IwikhptFLkoNx2KMVmpp0yjy3KrbTqd7dEw65HqCRPOxsNdU57YHiHMy99y1f8qI1aRQJNAdv+eLQl1W/FUZfyP9xMtjggpfP07qSRGOqwO0fNrJPEM2Wif7XtXeeXlJxHLK+xsbbNzkPHB9Q12BhorJNpCvr1Ne36RCydOkaydpzcYUAskOIsUBQEvLEpKQiG8G6XKAUVRvst3qhOS+fMvQH8HN94lSQcszLQYJQnNeIl6GLG+s8uv7jxgvzvg/Kk15tp16jVFM1a+sGmosMYQqQjl8STa5kglCaVEOF+95eH2HrvdA3SuWVo9gQgbRI0OQVwjdwZbEJWlPtikFYtHgVKxHrdK4QhkQSmWbrcrU8PLhcKVB6ABjMRKizEOI4zn9wKIAlWhsCAIfSWWku8rK2kLibAOJQyNYycJW21avRHaen4GPKrBWjKTUz/3HA9/+TbzJy9gmzPYsQZ8CATS4qRAWRD1OeZe+i1qrTZW+lgro4r7lNKXa8chHay+/H12emNqs7MIfHEE5PREAlDoMsRDTI37QnXD8y2miFQva9SJStfeGE9qKFXuBipUKCGIabgR55dbSCnpDfeZmW2DLJQ3iyK0eZJTq8XU4hrOCfqDLkL6GME0SzDOkWsI8JH2KSGjNOWFi8e5cPkJ/vLHH/Ls6WPsJikPbu7w9XOCF0412Ljaw0pVzCXnYyEFTAqPFnNVCoSVhIUHc/713yRq1xnlwhdoldLznyoBp5ACfEE7MARIpSqDMA2WhKMykqXtotg0mxiDR7ev5PpVGXtTxki4qdVGTIzVoSTjYsfMucnVT1JsSlhWcldT5y+OEUgQfvUVpbKe8iS3ETF5mqKFYndnm+31GsuLLWpxSLe7T3+c4KTPos+cJk9yRjs76Lfe4on588zOrqAz/5uq4KGk9EZLCOuJbCFRxUUpBEI4lNTUg5i81ub6dp+LCw069YBk1EdgGaeW48uL1Gox8zNtNrf3eOfqNWZadZbn2sx3Wj4rv9HwiE2ATL38sJCKXBtybRkMxnT7mxgnCMMaC3MLKCloNBosHT+FDGJkrv2qXIV5ePTpNyXs1Erl+8ZUmkQUBDtFMJ4rYt0m+Nx4jtm/5+GuD0osOiuwkkxM1Sy0ghxR8JFF3+GqPpbCz3HVmiVsz5HZEpkUrr8QaAGisUz83NeYOXaaYSY8OnHldRRXL/1461x+iQCPWqwsDIfyAEEUCrNCWkzU5Knf++9QygcWuyKsxTE5pS0QqZ0KvZkI9ApfLbyYdCWiKqkJitASazShDKjHMUM9RCkv5bM0M8Nyu0Fci2i3W5giANhOUSetdptGXCPLc0bjMUkyJoxr5Lmh3W4hC74qCiOMtvS1oFEPee3JY/zkZ2+Q2TozDcFHb3+KESEHWydpnHoCFQQYbat5WcbZ+XzdssZeMeMUheR3SDC7gLGCUPqwa/8sAWKwpUSMr44ztXPmf+NIGJJg0n/u8ESvlFQeham+knpC2WGWSSeWF1a6bMXRhyJOKzcOcchoVVrmopL259AXi5XM/0BZrLCYLT7BCpP1iNNdwkgRyQZ3N3ps7Y6Igpj+OCMMAiTKuyFS4JSgXosIhttc/S//Gydf+A5zz75K6kJ0lvjbMcZnlUsFyKokvJSgsARBzDDPuX37AcKMufNwh9s37vDCk2c52ZmjFkoOBiOSsWZxtkW7HrE0P8P23gGbO7tcu7eJerBNLYpptZrEkSKQEAYBOsvJtfZ6Sg6M9uoBs51ZJL7yBwgW52Z44tKT3Exc9XxQstiAcOBEMels1S+T4NtCRgc/2QRMFCOmljZX9F3plkshS4CFFfhAT2sqUOLDHIviHnICVMSRVUsIhxQeSYjinB7D+EXLOo9Wlp5/HeNCf322MAZOVePJx9d5Q2SQSGcx0u+KlW6Ow4cKKBkghEWEAboYS84pjHHFUJrkeXqvQRRIsLxmXwKu2uBxXj662qUu7tE4g8QRWIuIAnQeMBj1EVnK0krdG/2CRA+U8jPJ+pPWGzWfsA4M+gNyo4mi2BtThY+/04YoroFz1Oo15pzhRGuO/Z0DzrabfHBvl1t3YfvhLq+9+hzzs21++f5HRKtPkQsJLsc55Ql1Iao6AtMpGa5wk8pFxpWB3SpAVAq5U64ik82zsqdd8Uwr9+9Q84v9NIHtPvPH57evjKj8z7jJCusqruwQFVVyGdXuX2GchCwq31LsAAKlmFfpopQ3XpZ4Lm2XP1/hfJbzc7hDR/XJm5IwjDDGcjDWYHPm5pchGiEkaGtwQC0OcEYz01LcuHefa3//n1m8/j4rT79I68xTJDIkzzO/0jgf4oD1BLs3Wt6g3P7kJrf3+jSbNXQYsrN5wN/svcurl5/gytll5mcC0jgnzXMGPU272aJVj1lZnGMwThmMEvb29un3ewyEI5TS7zDiCKOAMAwJpWKcjJChwjnN0tISYVyjVp/j+WefZP7EKteu9/0qh8MUBQCoMgEK9FSi2bLPCvxiC6NWCiBOSqFN9aSYLDqleygL5CaEwQq/2yglpRPkF54yU/7oGHUUxsVfg/+8QIKU7r4sFrsQKolrX/DSzwt/fc55kUZDwfMIWcTb+Stx5eaHFAUPJQvRxBBdIDlTxKVUcVHOYZEVb+eNrJ9YTopKldZNI88iDKTVarI52PYLnPNBvXEUMhaSSBjOLrTReogKm0RhjjaaehyTpin1eoNmrY4TgoN+l0wXGQxyssuopPS8oBBorVFBRBTEdBpNVKTY2uxSiyzzLcHp55/kyeUWdaH5g9ee4W9upyQuKsaAnXRGOa8P9ZOo+sW58lkWMYmFwOWkLwuLIJgYvfLs0wVfSh966jeK//zYfBSUKtqjDVU1fv2gKgs2lPFU/uNC/1wUK/fU1qzAb5MrVcb4TJCXK+G29bl9rpgcYupnKys8sdk4B+l4SCvMIZPsHgyIhWKcpqwszDEe5YRBwPxCC1vs1yzEIf3hgLt72/STBKFT9q7/kt7dG7TW3mHtte8Qr54gy728ijZFsJ/QSOFTGLL+DtnNd1kJB2i7xNrxM5jdB2zc/YSfvncV7TTPnjtJXHNEoaSuBJnxkeONOGCx02QwGrMyN0OapiR5jjWGUAU+2jlUjMcJCEUjDmg2GnTaM3RmZhBK0miEnDt9ms00q1Z/W4galp1uXRH2UQClEmp7lGSrY8osgLKLp9vRweWqZHO/6yXw6EcWg1RQIqhyl2zynisWpjImruxTpjZR/M7llL5+8bGtEjJFdSz4BdngKHki4Uo9ND82XblbzAQJUdy/LRAnQlXUhS0MoHX4UuylKSoL6DoKJCopuVqPtAShkCSjEfl4hAhCVBiS5ilpf0gTx4UTiyzPt9naT3FOUG/U6fW6tFs+1SeOagxHYzKtSfOcMAp9ZW3hKy/h/EIkpSTPvISQKKSkx6MxB13LLz59yJmnXmFIi+Felx/81qu88dM3mR0LFpun6B5oEBLlMnSxm3mUwBYFunJTr93haVfM5ikUMjU/D73zFer0/WPbo+OohK3GiudtBIGUBTFbEOxu8k+4ciXyu2eRkoRBSKi8THG5E2WdT+vITE5uIdOCVBvfKf7nqtVWlTo2hYaxc4aoFjFMG7ikCy5mrDU2rJFox+4wRVvDznBArVVDIHmoE0apL5wZxjWS8ZiBg9jsYG8ecHPrPo3TT7L68tcJl5awuUVjMNoxH2pO1xT/11/8DdnoACXHzOoEEcRceO0p/i55yPrukJ+/8z6xcFw6e5IsGSClI1ISFTTJUo12mkg5orpE1JtoJGmWI6XAFekSptXEWBiPh8zPzxNHMa1mC+McT5w7QxQIXyKcQjXASu9KTRv+wghVOLjkEit3ujRgE35g4nlPAfYKFlMZRh9dYitaokwqFxR8V1EAtir4Wg3kiYwPU+cvJ0Q1J4TnuUpXdcJ/TlKzEIVMTzF5ZDHtPMKUE2QmSiPlr6d09TySKhdG74q4El0VwMMrX5b3Lw49IyHK6hweVc62Y57IYxCS/nCMq1mWOzM0cNSCnJ29HQIVMByNCp35Gs7hA4FNxjBLkMrng0ZKeoNq/DUIIX3Yg/IqtSoMPXEtIXOOjc19ZmLBjNviX379CjXq/N1f/Zi1E8tcPBFz4fIp/uMbt/l02xJJgXSmMra+/wqA4cqRMNUmQPzIZ5MFRUy/Lg6rzN2j7NX05/8U108KQSj9REB4LeWwECQLhCehwYuHGWs92Rj4Y0MpaISSOFDUCkMlpausrzECgyDJFZmxDHPNYJyT5AZjKOD7lBVHeFdMCnCCLGihTr5OeO8donyDaGaZIIpxeo8MTX/syUg9cgzGY/aGXazxqRQRmSexpSiy7FOS4X3GHz9kdP9j5q+8yvFXfxsrBSdrjmdPzvJ3f/0nKDXi2JVn2Lv+Mfmwy+qiJVRNjh07wXB8i2FmePPDjzl1bNVPH6v97pNzPjM/qhEI0LkhGWfMz7RIkoR6vcZwNKBWq5PmhjCqoYIl6vU6AONRShjFzM3PYZwmyw9AzKD1pFBFuUr6RXjaUBXjoDhwCpRTGS0EbsqAlJWd3ZGx6Yrz+G96N2+6gEdV56cyIIX7UnBKR6iwyUmr85XviQl3JqYMbfktR1U8szxn+V1RnNOXQJ/KPC1+yhbwqtzpLPnPsviIq849MVQlcY6w1ftCenLZiZD23Aqd0R1i6bD1OioUGJ2T54Za2ODgIKFWF2RZjiOk2+0ShyGu0HPPM00YBRjtsMbziJk2hIHf9YsK9c8ojoniGG1gNEoZpz1+65vf4Btff4E8MZhhzvrOJkk+5s76Bt95/Xkaepc/fOEE/+dP7rCXR+g8LW1s1ZeHx0U5Jqi8m+l+mnTwZxmoL25H0NvEVyo+fYSV4lFxVEL4OnLO+sINShEqSRwExEoWaSg+DseYYkBI6SVgFdQjn3RbC0NC6X3dcgW1xc5Bqi3jTDNIMwJh6I0laWYLnXUxcSUKH6NaC9od2i99mzTbRaR7zL78PXa2DxCbn7C8GDE/N6YWtXDScu/hLkFthjTL0BgUHhUqfGGHwCoya8BpbH+Lrbf+kv7dX7F84VlWz6zy1u0dsr27nFw9i24sMlt39PMxWwcj6qOE1ZkZ9mfa9Df26KcZ73/8KS+9cAmbGM+R5IZcaw66A+7cX2dr+wBjLC+/cIXVlUUCpWjUQ5QKMQ5yY3BIBv0+41GCdXDx4kX2D3bpLM5z78E9RO0yhgjndMULVv8ma1oxTkoX7/ASVu66Tdyr6WF1+BwV2hdTE1iUKKtwP6dWWsSk0k7pWk3OLKr/l8f4yyhSfZgyDpTnmr5yqt8p8x3L66pcO+dAeH1+KQtj5MrUF1ER+Z7KEmBlWSC4mriF41ddixCqvLli5xFSAurHL9J/8A7OpGAVQmuk8nIwmU6p1WtEUUSapSjlQzK0dhjr3TptHNL4NJncQp5rao0m1kIoA4LQpz1pp9nv9tneOyCMYn7v93/Aqy89x2D/gCyHG7+6ycxsi2Fvk1eefxGnNQ83t2nNSy7VN1k8d4q7vSa/vNVFE0L5LD4HUbnDA+jQc5/g8M83VZXb+Dn25/D+yqMNVNkegaigFQVQQPdASM+9hIqa8tINroLvheSu8vEWUSCohyFhIAlDLypXEetCVsSvsZZRJghCHx4QYkgCX76qcmGKgTWREfauTmoN+vgTqP42jWe+xrIO0PcvsPHGnzJr99FGMt9osXAhZDgcs7nbZzDICKSgUYvRWoO1GG0IZUCaG0bjMVKOMMl7JA8+5taPJFIIVo/NExwPcDMG3d3DdnuM5Jj2wiIu1Ryba7G1vYUMQ+7evcfq4jy5ThgNE3bWt9g46DIcp96gC0c9kuzv77GyPM9gmFCr1ej2DhBSMEzGBKpGlhs8G+EHfRzGpMZ6uZW6QEuJdLLK8C9dKHdolIiK8zm0cpWvv3i8fYYQF0fePJRgPmVUyqNtcVF+ajsQ1ucYCqaM1PT1TL30PzblhhbvT/yvCZdWGEULYE2FmqT0FV3MpLbIISPuAFGUWfLoSBzalT5ivytj6ArUJ/BuIrOztJYuk22+ixWaQEqcyT3yz1OklPSHA7QxpElCnuVY5Q1klmtwPilZCl+GLSBEBQHCOKIgJEkSBuOEsXF0+ynNRp2vf/N1Xvvayxzs7TLoDbl5+w7GZKTbOSpzXLlwxpf/Go9x+/vcvfsx2w+v8q9++EfMN5f4iw+2MEHkn4n1Lvl0Stlhu/UZB+8Lm7cF5cL0z9e+1FAFUrDYiv2K5PzuQyAhVBApnw8nhZoE10nhXULpRcgipQiUQCh/4eV2uTUOqUp3QBAFXteopqAZaIZZRq5lGYmANaKowVfKGsuKYzCLp+lnGbv9FGMG1FZPsfTS93n41/87PTOma9a4dOkCOzc+pSZi1k4tAAZcjhCCUZIyTixaQy12DIZDTJ4RRBEYizZjtDVcvb7L+NNfURch1mSeJwsE2+EtGnFI1JBcno+w2qCTlI/efINR4ss2CSGxeUamDZlwdOKYZy9f4MTqCsNBRpKMGY0zn9slvCbR2AzJM0MQhKweP0Gj1cY4w831B/RGI2pYnDB+R05w2O9iekX00/OfPGyOWK0pc4UVk9eHPbtplCbwEd8FIil4rHJCuGrbujCsFR95+Dc9Lz9Z0y0Fn1XsHogiBEGFAQJZCSS64noq77Kyd2IKAkxcxPIHjyaqT9+lA5TLyGyN9vlXSfduILJeUV3cp6+oIEDrnCRJCAKFzrWvdJPlqCA8VDVHBQqtfUi1FBLjNLkxdAdDNnYHJEawvDTHt157iSfOnmI86HP75m12dvbpD4cYo9nfv8urL79CrR5z0OuhpGA06KHzhI9u3GG19SN+8MM/4v7OPu+uZzgZVHip3ESoNuNKd3raeE318eeNqWng/cWAadKvj1osy/ZIQ7XUrqEKVU8piy1pITzfhM+L8wbLw2glvEGTShJIX9/OTl2Jta6C21JKEJbYCOIQmoGiHeekOvCFSI3xtfm0IzfWv3YOY73WknY5eTMkunABmydo58hGlmBlDblygeWsx6kf/FtGwxw9aCGy9xjnAyQQyxCnHI1mnWYrwBq/xb+zq0kTz73kToPzfJxUIUlvQBCCFtojRek1ukdJRqAirDNFNeeIWFsGsaI3duwlCYPMV1o5u7zEi889wXKnzWiUTQhe7QXuBoMRYRyTZb76TGd+jjTP+PTarzh95TzvX/2I9snnMXQQZlRxT+XAmSCnw3AdvgBqf8VlUojDPBYFWT6ZwIccRarBeMiIFS5f5RZy6JvV5Jh4l1OzYpJyAUU+qLUenRe2RhbCdTgf6yWLwN1pw+TK0Pki109IQaFXBEwl0Dqqc1eurJMTfkWUxyu0tgxbszQvfpPxp39NoCR5Zrx4YsGD1mq1AkElhGFIlmmEEBjr1RJcsbPnEEjlk5BHac5g3Ge/2yeKm3SaLZ5/5kkunD/D1vomH77zPjs7OwxTXYTP1JhfaDM33+ZgZ58sTWm2GgyzEcNkyCjJ+PTqJ3zv2xv84csnefDnH7GVNkBaH8oBVJXPp8H3lBGfMAViYoimvPSvsiIeGoZfcQX9UkOlpGCuERGU8sNyEq1c5hf7qG4QsoipERO1gXIMyOntyuKBSCkJAokSCmsVzkAeBuQmINc5mfEhC7m2aG3ItCHNZWGwHNpYrNXkRpCYgDwwZCXvICTNyy9C3iOcWUK0DOfXvs94/Slu/fiviXav0yfFyhpRY552ZGmGOTodsjo/Awh6vT71RsdDdaPpDxNmOk3CWsgoGxNHAXEYkOWW0TihFkU06hIVN7m12ePB/oj93JEZQzuKOTE3x/nzxzhxctVXtilgvlSSRqOGtZYgCBDK5/cFQUQQxGRJjlUJYafDtTv3sNE80dwTHBgNVuFsPskSKFFCxeQdGQVTcOHoKnl0FE3+X+zXOabeKf+eeiXKk4qpv6d+l8nnJQKrVnIxObEoEdMRstZRBItaSynmGARhtTtXhknYKlZIFDmpRRiDlEgpsAWSl0WOnpDFTuERc1tSFM4XfPQGRBwpLC4ERgiktRitkSefIt67TbZzDaWUDy/AVkbIWuP7OYx8EV3p5byDUJGmGVFUY5wkOCHZ73UZJZr+cEy90WRxYY52vcaJ5QWuXbvOwX6X8aCPBS/CGAYMhl3OnT9Fvdbkzu3bzM3OEkQBG3s71FsxBwcjkuaAmzeu8dwr3+DfvH6O//B3t+m60JfOKp8bh43JpCuPoOrq5RTydV/Z9kxO+RW+8AhDJWnXQ9/J5ZazdNVuj8AV0cl+C1rK6cHll7HpaHW/uJXn8e6hkpP4mdhajAnQ2heptNaSaUuSadJcEwWSPDdeyMs4tJFkxhAbyIwksw5TxOy0zp5FCU2gUwLni2R2Vo/x5Pf/iHs//X8RWx/TObbCM//yf+Tqu+9w8+c/xXQz4lqASTOaps58WKNer9MfDNDG4kJHGMcszzWZaUrub+yCqJEHlhxJGMdce7DN7W6Kto5GFDIbRhjrSGXA9jBl66NbLM53WJ7peBkWW7oHCWBxQoOMMFj2uwesbx1AI2ItUDTdHOdf/CYPaYPTOGEoo7rL9kgnT3zpy6pIhvvCo6oooyOfTAxWVfPxc0iuz6q8Tn9WnuYIFHOeNHfW1w6SQYCzrkiTkdUGgueaAhwWJYt8KwSRDMmNxaSF4miSorOMUTImzzKUdYBmnI68S69TothQD2Pmjz+BXF3zOvUOfMqJLNCiN4aeEjOMVZ3ZJ1/D/GIdsh5hEOKsJogF2hjyPKNeb2BzHztnrCUIg+o2s0zTHyXkFvrDlHpcZ67Tpl6vIazm+Ree4eaNG4xHI3rDIQII4zrGQTIasbCwQBTFWCeI6g16gwEmVLzx7pvMrizy4NZ9zs+1GQ+G7G9u8Mzp03z36ZQ/eWcTG9QQLinCQdQRiCQO9dWUffry9lXQ+lc89BG7fhAHqtg5KWRPVKEqIHxm62RX7rM/6Jybqk9HdSwIZCGmX8qo+AGsMEYRBpbIFBnkeY4QzisPSFCicP20wwSC2AhfJdj4wNFSn12oiFDWQCuEcEXwnyaab/H09/6Qqz8J2Nv4FAY7XHzpRZorSwy2tpiZWybr93j48Tvcu38VYzJGgy7DQZ/cWpxQLDYjTq10GOZwv9ell+UgA05llotnLtDY3eXhzj6Ztsy2OlCT7HR7fHL9gMwYAiWYnWmz1OnQiGPqjQbjUYJDMEgT9nueeLfCcu6Js5xYW+XSqRPUmyfZG2tMTCEf4iZGpURVXzZ63MTMlOkRh3gHUcQwVbt0ZYTU4SF11BBNaKdHDbepQXL0MstzlectFrVidfO+vvM8jlMCd0gjytMJ3v0TOBeQpoas32O8u05ysEFLJ0Ra84uPPmDYO8CYzAcaGwPSEYcRVkgWF2Y5f2yBlWMdWqLJzic/Z36hQxIu+Wi+ilA/egsB2mhGnVVqa5cZ33oLZJlHZ0BrarUYpQJSPfbl1JKEIAxJs5TcOrqDLqMsR1toN+te2TQMsNanhL35i58RFajSGk0YxaRJQqoNKgxQgWK2M0u/16fb6+KwjJRm9dQJ3nvnIwYHQ8bDDCEVw1GXqLvD9144zYOdHm/cGqEiecj1/WyfugliOkKYV2lubsoGfMF4mEZiX9WaPVI9QQlZoCVHoFxhXES1zUpBoovJcujfddaHILhiH/fIQPQSKrKSUSkvW0kqbShhLAKFJPIxW8LhkEhjPfdlpSfancM4D7W9kfLXFkhZPNCic61FWoNtN/j6D/41P/2L/4frn77PM1/7Lc6trGJWFrFOENeOc/mFp3n/x3/BTOh496c/QauQTnuO3cGAA52yu5MTRTNcfGoeGThaM3M0opzf/J3f5o//5O+JlrY4sbrAu29+yEK9xeW1C6QauknG3Yc77HS77HV7OCe8K4gjVJIwCpidm2NpvsP5UyucPbFKM4h4/vln+Ls3r7Mwu0YWaPaT3D/bQrzwS43UNGpxR94uY5U4PGTkkQHkODxoDxspceizSQrK0etwRcrFUaRVpuCU2l/l68IdK96r4t7sJBPCUw0+dcWNE7o7Gxw8uMvDm5/Q377H8YU6jjGNuTYqqtFpdDl/8SSz7RlUGOKcYDAasb+/x/72Pr2dDX6++QD1SZOZ2QWeurDCWpowiiQOX18QOR0u4Wemw+JEzjiBzqlnsPeukfY3wTkkmiBQOGfJ0tQXcDCGZJwgcl+fzznHOM3ozMx4gcUwIM1S6vWIPM9oN2JGif9uSf6lWc54nKCCiPmFOS6cO8321iab1nFi7Rj3Ht7j/t1NmkuLfPTuJwRY2s0aDkiTIeNBn9mFE/yb37zEZu8d7hzkCBF4uSApp1zisr9KlFvwooIKXX++uXGf89eRY/85OKpylQU89yj8WjJBUbIwOFODtlgurZOoKd7EuckAnriLk++VpLAQwuc9MpHKxRUJrMW2u5EUIQs+QK4sCGELDepAlrrTZVyOL55grcHpHKG8rvX3fvhH3L93h1haVCjRLsA5X2W3N0jY7/YJZ2Oe+43XGGcJmwdD7n98jeHA0Gh2EDFcunwWaQ0L8y32Rxn37t6lFcOxomT69iBhnGtqYY3lmRYnFttcWu4wylNGec44yYiCCGcdcRwSSEmr2aQWCJwVJNv7XH7uCsnIoTPN8uocm9sSawXKplhUkSBrK2NSRoH75z616lVEtjv0fmmsygd+dNBVmmFuuo+ZHD/Vl276XNUhU68rsv/oGJiKZHc+kbzkximSla02OKNRTqOsQ2iLsI6ku8fg7g3GG7dpRinJ3VssxgFnliXPPLXGvW6XG/cesrq4RKfRIhsMMUEEQlJrtTh7bJVnZp4lSTN+9eHHvPnGLyHLOLmywn/zh9/lP/znv+Li7/4PDBGVmoOYvrfinowF8oy8vkLj5DOY6/tk4zFJbjFphslTlKMqMioLSmWm3cI5R6MoOGp0RhBEKFUnCBRKxmRp7neFrc/3y41BKR97d+bUaS5cOk+/32V/v08gAtqzLXYGu5y+cJqf/e1b1FGsnjxOuxEjhA8+HY8HOJuzXI/4d999iv/5Lz5kb6SRgZ8zvs/lYYpxYhkebWMesW5W4+XIkPq89sgUGlFUai3/HSYbJxnz/tjyBgSq5KiOhjdPGeUKCbgJrHJHvuNjsyDy6uFeDVFrnxvoLE65Ksq4vDrhfDxXZUCLp2CMwIaFy4qAKOTK5SsYY1ASApQvp62ELz9lDHmSEjdiaiomtEPOnVjj45vXGXS7zK/O4qxjbr5NLQioBSmzzQZRTbCxP+CT25vkImSnO8bl9+nOzzE/26Zdj6hFgrkoZLEW+5QNPHHrrMGNBlglUXHMyvFV1k4vs61rnLzyEi9eOokM9/jrqwlWlDFuQJHYXA2FKYMwaWUqzcRl/FJ3bcpV5CiRzGSSFj07cdP+ka3Ufyp0M6vTBDLACoMkQChf/CNQEXo8xvS77G89YPTgI+rZBkvNmGvbNzh54QLjdkCSa3Tu2HiwzvLKIi//3vd47+Mb7PUGiCyht72JCxSzrRZtDA/39qjPzXH+qSeZn1/mr/7sT9na2uL6tS3u37jB2tZtxPGzYEAJXzV6svFw2NCneU7r2JOou9doyofUjUDnmpGFIPALbBgGhcRwjlKSLM0IAl8ncabdxjpHEASMx2OkUgwGA2r1JtoaxkmGCkKveiQVaZLw8QcfQ1jI5WiDO1C0Ftps3blPR6ecmptlPxnSmm/TajUJwhBjcroHW8zMnuDCygz/7jtX+F/+/G16pkmgNFaUyWuHvaWpHueoNSpjHEvXvQLzhxbAIxkSX2HMPFLmRRRlmEThAlL5opbp/KtDq+P0LUys0vRpp947HCsz3aqbUxAUUcFSFtpGrjRyHOJerS0E26RESQfCx6QIC0YJdCnLan3RgyL+vUj0BIpBtJUnSCzGQpKmRIFibsYjnqcunuLqJ3cxRZkuJSQi7NBup/zkH97iqcvnuHfvXf7we6/SDhVvvPUhd9Z32BmM2Ox2iQLFQqvNTCMiiiRBGFQgW4kAgSMNAo6vrHHy3BXGogn1BY63Z/nl3/yM3/jui7xxbYeeCZFOI/DfmY5NORppfOjVV92WKVzFKnDziItH+eyO4vqSX/qi004Rmh5DySrd14v6WfJkVAx4hyRC6BFuuMP++kP2t+7TUCmxScj3ttkYdnkoQ+L6LJ/eusVMo864N6Ax12E41tS6PXRvh69fOc+Z4/N8fP8uYVAjTzIW2y2cTmjIGDcYsLOfE8cRa+dOMRpHJNTpHXS5+8s3uPz7a4yI8QSEv4FyV7FaBCgQT32O2vnnya/uItAgHEpJAqUYj4cEodeqckajwpjZ2RlynTHoj/wmUpahAkea+QR0Uejmj0ZD6rUWSZb7za7ODOMkoT0zg8aR6JT20hz3t7doakveT+hnhg9vPuDCueOcPrbEaDTCOEcQRIwGB8wsrhJJycsXljh4/TL/8Se/InER0k5Vaiqm/XTK0aQ/mTyByu5MgRIO26JDNMMUQv8ye/XlhkpQxE0VCacl5CtX4yp1o3QzKHb+iisUBTI50qZ3Ar/s8j6LrFRR7EBirS4+n7ApDluUHfLnLZGeFAKkQ1rhS7o7B04V8sleEUBbX+BTIAkDSatRI1C+yo0WDoshlJJOvUbgHPm5Re7ee8CP3/qUUZpzZvUYV56c482P73Pm/EVeePYK/f09zl46y9eeOUm7HtOYaTM/P8sv3viQzW7C1laPLEtQKkA6CjE3R6gcc80WC2eeZqPnaK0dh1Syfucm7VCzMh9zZqHB1a1xoXNkiyTdSVR1iVYpEEq14n9RbkP12WR0CZhoEhV9cMitE1OnmlqQShez7MPKVSoHfcFZlmS5Dy0QKFkobQiJShWiv4cZ9Un6W2ysf4oe9Un7YxA5VmXEi/NY5WjOzbG1vUW3v8d8s8X8YoeFhTbD4Yj93j5hzXHu3EVGvS1+52vP0ZmbYd9oNh5sYo1mnI1Ix/t0ZhdYaM+RakncaBM1zvPC5Yu8s9bh5rV3OPn8i8Snn/KFMqoI+8JYTbnUzgmGxtI5dZn87ieE6W1EGKJUwyefxzFhGDAejWi3m4xHQ4wU6CwnCsJKtidNU5rNFsZakiRlPBrRaDQwxuKw1Ot1lFL0R30yozGBwMYK3e9z7d1PkKlhafU4t+5tkgvNidVF6lFAECqkDKjXG0QqIB/2SFVEHFm+8+Ia4zznP/3DbXTNa3qJYmwc5s+njNKkSz+XOpgMqCmD5KYM1j8VUQl8AGclweEANA6JxSfbWuPrx3kJl9DLC1fKj0eM1Oe6Iz60YWLs3KF/h44sfkcKCbaolyfKFB7/XatsxVuVNyGKJ6Okj4SfoDhfCYQyCNX6+4zikCQbY4zGCIiEN4dZllIPAuJQ0qkLTh1fZHNrwJ31TT69dYcfvR3RHab82V/+iB/+1iucWOzwf//p3zM/v8BMo8WoN+SH33mJjjNcf7jOmYsX+fTaDWwKYQAHI8f+3j7nTy0Q1zpYFTHKFf/+3/8frK2tcfbiedqzdeoq4Nxyg7u7KVpYnPBCecZRiOL551y6w5MkUIp3SmOlJrxTZaRctXIWZq4aTFUSqTjsMh5dc4QrwglEgTecXyxcNTK9+JwVPqhYlkJ4OsMO9hl3d0n2Nkl3NxmPdjkxN0NNOm5tbXL6xDzf/vpr/PTvf8HbH92iFUXENcd3Xn8JgeO9dz7gzt0HnFlb4/jyCmCxaP72//sbXnzmElub93ny+CK//NUtxt0BRmriWptaM8BKSxho6s1ZTq4scO9XG4RGc/HMMa7//ENuvPdTnjt+mlx1EMKnyHgpIH/jsnz2EoTTZK5O8/wzDK/dx+oMGfiFNoxC8twjNykdtVqNLMsQwldw0SYjCCMMOXmek6YZtVodnRm09kas026C1QyL0JkHO+vMLS8hjeKj9z9BpxphHTO5odvrsdBpcHp1jvmFeaSQjEYZG1t7rCzMk+ktOnMrPq5QOX7n5QvsjzR/9cEGBCEIW4wdyWShEkx7vOULOT0OijGE5bPGSEzG41dpjzZUshRdgTIuyltXWw1iaYryOEL5TpoyDp9p7rN/fzazv/j9I1ujJeleoavP2W0yxnhddWuKWVmijM8320LIwkhZX9od78pFhexGLYywxhKGAU4ptPVCaVEY0AwHtIKY1dkGm/sD7qxvgdG8d3OTzf2f0IkDHux3uXI24d/+wetsbY344798m9sbG5w5Ps+n1+8gTEhT9PjWN36Dt64+YGd7l2PHjnH3wQ63bv6SxeV1Lj2xhrU548ED6sdPk/UOqNmUTgwjG4AT5MaQW4t2kzqBk7XNVYjIUa6MohCCs4cMzee6bOLoS1GtnNXvCKr+EI4ikBIKyTp/FYVB9MhMIRxEeU7e75HsbrKzfo/+9jq9/U16wy6NWsD8bI35tsKMExY6HfJsTDrKmW00eOrscUStyZ2b1/jFGz9neXWRC1fOsf1gh/29bRwdludn2dntEYYBP/nZG1y6cI5Tx1c5NdNhrzNgp7fH4KDH3OIS41FCs2nQYoA2OYNkgx9fvUF46gqvt0/zzs//AQ4eEC53MKbAmWVUe8XnuYqbTfKUcPUS9u47yNEGShqcdr68m1IkXjkMhEQnaZFyExIAaZoQBiG5zmk2m4xGI2q1WlEmvegD50nx+1tb7I36uCBkb3uHPNUYB+PxmP0PPiRQkhNL81w4e4rhYEhnbhkZKFQo6A8GNJykd9BlpTnLcDQmrtX4Fy+fY2Nzn483B5iwhhPT9Q0nw6Lkow55/6Ki7wpUXn71C6iIr9Ae4fqVHNQkqNCnZJU5QbZYRURxlEZYUaEcUa68n4uk/KWK0kiVSZ7uiy1tyVkJwUS8rwiLmKiClrIgoghXKAnPiRtS/naFugrcKgsNaaUkynk+wRVKmVmSVGoRWZpRj2OkEERKUI8ls+0aC50a97d32O0O2DnY5X7mjcDbHz/kweafcWJlniTJWN/vsba4hMzHXDh9DBfO8Sc//YinzhzjlZcvkZqcU2dOEjTrSKV49tIa6w/u8/TT53jplVfp7g3Jc0M9lAQuIDdexA5dRGMXC4oQDl+CvHSzJj6YdSCmayoWIMtVx3DYzYNp1doJLygn8XQI6YODXRFmIiRKKgIhcQV5YK0lHSUkoy75YJ/RzgZ7924x7m4ySg7o9noM+31UIDGtJlInvLe9xdnjK+TJgI31ffqjf2B/Z4OTywvMKMHCzAz9cYozknQw4uknThPFEVdv3CYOFceWZ7Emp96a5fqdDdqtNge9LR5u7tJoNRnpAUmWooKAOIhIRyOGe32Ozc8wd+ISO7ngwuUOtz69zo23f8mF3zlBLmYx01BBuAm/LkBIhTOakWoTL58nubGBKxLgpfAhBlmWAXiRRhSD0ZB6vY5AEEUxudEkaYrD0x31ekyWa4RQpFrTHw1Y395is9clViH9vT1s7kutWQQyCEAFhDLg8vnTNBtRERaRkmqBHhla9Zg86zIaaoIwZmZuDikks03477//Iv/rn/yC6wOFVboqWutR5CGm6QvblzEN/5j25SXdC3fqsBDWxHw6LNZ6w1CGA5RfdNOG6gvP78DawngUbkVR1eQzxzFRFz38fERlwr0Wk6iONUduxrnC1Tt0XjHZH6C4XmnI0gQlY5xNQPriCwZHqATG+pLySina7SZZOkYFkmMLM3SavjbfwSBhrzfkYDhmnBru7/W4vzsAB9Zq/tPf/gOry/NcXe8yzmFze4fji3N8+zdeYTBKeP/abc6fOU2eJvzX//ojTq4d4/ixJbY2N9h4eICzTWaaNdLUkhSw21qKAgRFiSxRFq1Q5dOtnp21Dk2BwBxFoGy5KyjK0pEVYigXkdJYFetD4ckd3sIWShEoSagEgXNk/ZS9zS12tx+yu/OQwc46ZnhAmg5Jkj64lEB6BGtyQygEcaBQzjLuH/DcpYscDPfJ8pTcZGxtbbC4MM+DnT2yXLMyN0ermRG3WjSbLazJCZziwokTKGUJAsmp06f4+Op1aksNNrZ6zC3MMhg+YDDOmJtvIR3s7u9RI+DunfsMDwacv3CJ9swsg+6IXq/H5a99i7d/9GecOuhjZmeRQVDxtDgflGydrfTUhZDoLKG+ehl3+z1stk5uwOQZzviiJcYYslwTxxFxHOJDAAWjUYK2llqt7kn4MEIKgbaW3FnW17fY2T/gYDzwaiWRoqUUuTVoneGkAishT3ni4imeuHia8XhMLCKGwxFRvU4tiv2iJgxpOmA86tGZnyVJE7I8Yz5s8q+//TT/05++zcDUfE4gk5xPUXS4+4zNEkfWuEcbtUeZvK+gme6q2BhRwtujgRUlP2Qn0cLTbscX7eo553dPpt1EISc8VXlMda6SxOdwgmopf1wGdR69fY+KJtf4ecm5FVQVAmtCtrd3cC6bxAUJCFSAcxpjLdkoJY4ioiik05khSRKctTRqMZFSNMM+i60a48yS5JbBeEySGzKtSbQmzw3rmwdsbOyhC1T6Zz96j6u3ttnc3ufCueN8+5tP8dEHV2m2OnzjW6/T741YX7+HqnWQcYdWEBLYzONALTDKZwFIqGr8SeF5xgqOl49S+oDY3BaR/tJNVai2h6IR/M5e6d7JasGShbXyMU9e/VXICCHBjlM27z/k7rUP2bjzEUl/i1CCVIY8926OxVILoBXWCJVAihicYGm2Q10p9gb7GB3R7+6hTUqzFjEMItLMMOz2mGnO0B2NMMawNNdi0B9y/fY9ljsNXn/teUKXEQYhJs95cO8+RmdsrPeQFi6cPclSJ8aIEOkEm3fvc2trk3RpyMOtXdbWjtO69DTGZJyea3NvZ4fjV67w8S9+zP76TZZW1jCFNAvVhoFAFyXMPU8oEEZDrU24fBq70UMaTdCoY/LME/mJz0gIgoAkGWOKZ9lsNhknCUJKslwT1mKGo4TuYMi9rS229rqY3NBpNlnoNFCZoXswYKff92jKOQJnOXl8ld/8xrMcdHeYPXmGg96Q1MBMp0Wt3iEOQ8JQYYxhf3+fuN6g1miiwghNxhNn5vnu82f4r2/fY+iCothJ6aWIz7VBnwlJ+oJ2FG98WXtkeIIt8qsEE07M4WNeKFys8kNXaWZPGavPQVXV1rlzh4Tgpw1L6S5OW2/rqM5bfcuWRsgeMkQT+d2JoH3l6ZXoyk24G/8bEqkC9vYG3Lxxw6O0PCNQyvNvrtQL9zEuxhhGo4w4ColjX2BCSslSFDE/2yIZJ4yTBG0sad4gM5Y011iUH9BWop2PB5NCcfLkCt/53W9RD5sc68ScPHOWl772FLsbD2i3Wty6eQelmshaGxVENC2gnM83w/mSVghyU6x6otQSLwywLWOnwBVboko6jBU+YNZ4MTdbEI2iMEyl2kFJ0rui7ozfqfPBtQQSKQNGez02PnqX2x++RXf7DrWGYOXkMdZee5W6DDjY2qK7tUMsFXGgENaR5zl7/T65seg8Z2N3k1eee5bx7QGJzomDkHanTl3BxXNneHB/HWUtM40G9doyLhBEsS+n9vSFE8zOzWGcYWFxjlvXb+MMtGc6HOwP6cy2sUazu39AliS89+mnrB2bQ8kQmyVs7KwzMzfLsy++wpkLF5mpaWaX20TtFpvjnGde+w1+/tO/5/gzryGDhufgiudjnUUYgbFlgQ2HETCWAbWFs4w3PkQi0Vle8anWGGbabXKd02i0GI9GqFqIj7UKMdYhVcgwzbnx4CGbW9sMkwQl4dhcmxOdDkI69q1ld39IZg1KCmphwFK7ye9++wWWZto8XN/kzr1NTp46Q5ImCCF96S1rGfcG1XhJRiOUigo0mBOGIb//2hMIp/nzN2+RRp3C7XOVIahs1ecBp8/CrcPt0d6jP+zLVPaEENvAna92qsftcXvcHrd/UjvtnFv6vA++1FA9bo/b4/a4/Tq0z+ZFPG6P2+P2uP2atceG6nF73B63X/v22FA9bo/b4/Zr3x4bqsftcXvcfu3bY0P1uD1uj9uvffv/ATZo6AMbrCEDAAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "image_2 = Image.open(\"king_crab.png\")\n",
+    "# conversion en image RGB\n",
+    "image_2 = image_2.convert(\"RGB\")\n",
+    "plt.imshow(image_2), plt.xticks([]), plt.yticks([])\n",
     "\n",
-    "What is the size of the model? Quantize it and then check if the model is still able to correctly classify the other images.\n",
+    "# Now apply the transformation, expand the batch dimension, and send the image to the GPU\n",
+    "# image = data_transform(image).unsqueeze(0).cuda()\n",
+    "image_2 = data_transform(image_2).unsqueeze(0)\n",
     "\n",
-    "Experiment with other pre-trained CNN models.\n",
+    "# Get the 1000-dimensional model output\n",
+    "out = model(image_2)\n",
+    "# Find the predicted class\n",
+    "print(\"Predicted class is: {}\".format(labels[out.argmax()]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cf8287c5",
+   "metadata": {},
+   "source": [
+    "Les classifications pour le Golden Retriever et le King Crab sont bonnes. Le modèle semble être bon.\n",
     "\n",
-    "    \n"
+    "________\n",
+    "\n",
+    "Etudions la taille du modèle"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 95,
+   "id": "15668ee6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "model:  int8  \t Size (KB): 102523.238\n",
+      "model:  int8  \t Size (KB): 96379.996\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "96379996"
+      ]
+     },
+     "execution_count": 95,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#taille du modèle\n",
+    "print_size_of_model(model, \"int8\")\n",
+    "#quantization\n",
+    "quantized_model_pretrained = torch.quantization.quantize_dynamic(model, dtype=torch.qint8)\n",
+    "# taille du nouveau modèle \n",
+    "print_size_of_model(quantized_model_pretrained, \"int8\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ba6099cf",
+   "metadata": {},
+   "source": [
+    "Le modèle pré-entrainé a une taille de 102523.238 KB.\n",
+    "Après compression sa taille est de 96379.996 KB."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 99,
+   "id": "b7098c44",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Predicted class is: Golden Retriever\n",
+      "Predicted class is: red king crab\n"
+     ]
+    }
+   ],
+   "source": [
+    "out = quantized_model_pretrained(image)\n",
+    "# Find the predicted class\n",
+    "print(\"Predicted class is: {}\".format(labels[out.argmax()]))\n",
+    "\n",
+    "out_2 = quantized_model_pretrained(image_2)\n",
+    "# Find the predicted class\n",
+    "print(\"Predicted class is: {}\".format(labels[out_2.argmax()]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "96393675",
+   "metadata": {},
+   "source": [
+    "Les prédictions sont toujours bonne avec le modèle compressé."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "id": "b36057e3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Predicted class is: Golden Retriever\n",
+      "Predicted class is: red king crab\n"
+     ]
+    }
+   ],
+   "source": [
+    "alexnet = models.alexnet()\n",
+    "\n",
+    "# Set layers such as dropout and batchnorm in evaluation mode\n",
+    "alexnet.eval()\n",
+    "\n",
+    "out = quantized_model_pretrained(image)\n",
+    "# Find the predicted class\n",
+    "print(\"Predicted class is: {}\".format(labels[out.argmax()]))\n",
+    "\n",
+    "out = alexnet(image_2)\n",
+    "print(\"Predicted class is: {}\".format(labels[out_2.argmax()]))"
    ]
   },
   {
@@ -1304,13 +1478,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 63,
    "id": "be2d31f5",
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -1409,7 +1583,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 105,
    "id": "572d824c",
    "metadata": {},
    "outputs": [
@@ -1420,9 +1594,7 @@
       "/Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\n",
       "  warnings.warn(\n",
       "/Users/franck/Library/Python/3.8/lib/python/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.\n",
-      "  warnings.warn(msg)\n",
-      "Downloading: \"https://download.pytorch.org/models/resnet18-f37072fd.pth\" to /Users/franck/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth\n",
-      "100%|██████████| 44.7M/44.7M [00:01<00:00, 35.1MB/s]\n"
+      "  warnings.warn(msg)\n"
      ]
     },
     {
@@ -1453,7 +1625,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "train Loss: 0.5863 Acc: 0.6721\n"
+      "train Loss: 0.6687 Acc: 0.6598\n"
      ]
     },
     {
@@ -1474,7 +1646,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "val Loss: 0.2437 Acc: 0.9276\n",
+      "val Loss: 0.2756 Acc: 0.9130\n",
       "\n",
       "Epoch 2/10\n",
       "----------\n"
@@ -1495,394 +1667,22 @@
      ]
     },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "train Loss: 0.5695 Acc: 0.7418\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "val Loss: 0.2151 Acc: 0.9539\n",
-      "\n",
-      "Epoch 3/10\n",
-      "----------\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "train Loss: 0.4273 Acc: 0.8074\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "val Loss: 0.1790 Acc: 0.9539\n",
-      "\n",
-      "Epoch 4/10\n",
-      "----------\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "train Loss: 0.5080 Acc: 0.7910\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "val Loss: 0.4991 Acc: 0.8092\n",
-      "\n",
-      "Epoch 5/10\n",
-      "----------\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "train Loss: 0.5020 Acc: 0.7992\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "val Loss: 0.2147 Acc: 0.9408\n",
-      "\n",
-      "Epoch 6/10\n",
-      "----------\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "train Loss: 0.3022 Acc: 0.8730\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "val Loss: 0.2138 Acc: 0.9342\n",
-      "\n",
-      "Epoch 7/10\n",
-      "----------\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "train Loss: 0.3056 Acc: 0.8607\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "val Loss: 0.1944 Acc: 0.9474\n",
-      "\n",
-      "Epoch 8/10\n",
-      "----------\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "train Loss: 0.4346 Acc: 0.8156\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "val Loss: 0.2299 Acc: 0.9342\n",
-      "\n",
-      "Epoch 9/10\n",
-      "----------\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "train Loss: 0.3944 Acc: 0.8074\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "val Loss: 0.2013 Acc: 0.9474\n",
-      "\n",
-      "Epoch 10/10\n",
-      "----------\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "train Loss: 0.3250 Acc: 0.8402\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n",
-      "/Users/franck/Library/Python/3.8/lib/python/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "val Loss: 0.2382 Acc: 0.9145\n",
-      "\n",
-      "Training complete in 14m 21s\n",
-      "Best val Acc: 0.953947\n"
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 60'\u001b[0m in \u001b[0;36m<cell line: 176>\u001b[0;34m()\u001b[0m\n\u001b[1;32m    <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000050?line=173'>174</a>\u001b[0m optimizer_conv \u001b[39m=\u001b[39m optim\u001b[39m.\u001b[39mSGD(model\u001b[39m.\u001b[39mfc\u001b[39m.\u001b[39mparameters(), lr\u001b[39m=\u001b[39m\u001b[39m0.001\u001b[39m, momentum\u001b[39m=\u001b[39m\u001b[39m0.9\u001b[39m)\n\u001b[1;32m    <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000050?line=174'>175</a>\u001b[0m exp_lr_scheduler \u001b[39m=\u001b[39m lr_scheduler\u001b[39m.\u001b[39mStepLR(optimizer_conv, step_size\u001b[39m=\u001b[39m\u001b[39m7\u001b[39m, gamma\u001b[39m=\u001b[39m\u001b[39m0.1\u001b[39m)\n\u001b[0;32m--> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000050?line=175'>176</a>\u001b[0m model, epoch_time \u001b[39m=\u001b[39m train_model(\n\u001b[1;32m    <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000050?line=176'>177</a>\u001b[0m     model, criterion, optimizer_conv, exp_lr_scheduler, num_epochs\u001b[39m=\u001b[39;49m\u001b[39m10\u001b[39;49m\n\u001b[1;32m    <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000050?line=177'>178</a>\u001b[0m )\n",
+      "\u001b[1;32m/Users/franck/Desktop/apprentissage profond/be/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 60'\u001b[0m in \u001b[0;36mtrain_model\u001b[0;34m(model, criterion, optimizer, scheduler, num_epochs)\u001b[0m\n\u001b[1;32m    <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000050?line=104'>105</a>\u001b[0m running_corrects \u001b[39m=\u001b[39m \u001b[39m0\u001b[39m\n\u001b[1;32m    <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000050?line=106'>107</a>\u001b[0m \u001b[39m# Iterate over data.\u001b[39;00m\n\u001b[0;32m--> <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000050?line=107'>108</a>\u001b[0m \u001b[39mfor\u001b[39;00m inputs, labels \u001b[39min\u001b[39;00m dataloaders[phase]:\n\u001b[1;32m    <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000050?line=108'>109</a>\u001b[0m     inputs \u001b[39m=\u001b[39m inputs\u001b[39m.\u001b[39mto(device)\n\u001b[1;32m    <a href='vscode-notebook-cell:/Users/franck/Desktop/apprentissage%20profond/be/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#ch0000050?line=109'>110</a>\u001b[0m     labels \u001b[39m=\u001b[39m labels\u001b[39m.\u001b[39mto(device)\n",
+      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py:630\u001b[0m, in \u001b[0;36m_BaseDataLoaderIter.__next__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=626'>627</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_sampler_iter \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=627'>628</a>\u001b[0m     \u001b[39m# TODO(https://github.com/pytorch/pytorch/issues/76750)\u001b[39;00m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=628'>629</a>\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_reset()  \u001b[39m# type: ignore[call-arg]\u001b[39;00m\n\u001b[0;32m--> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=629'>630</a>\u001b[0m data \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_next_data()\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=630'>631</a>\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_num_yielded \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m \u001b[39m1\u001b[39m\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=631'>632</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_dataset_kind \u001b[39m==\u001b[39m _DatasetKind\u001b[39m.\u001b[39mIterable \u001b[39mand\u001b[39;00m \\\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=632'>633</a>\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_IterableDataset_len_called \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m \u001b[39mand\u001b[39;00m \\\n\u001b[1;32m    <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=633'>634</a>\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_num_yielded \u001b[39m>\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_IterableDataset_len_called:\n",
+      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py:1317\u001b[0m, in \u001b[0;36m_MultiProcessingDataLoaderIter._next_data\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1313'>1314</a>\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1314'>1315</a>\u001b[0m     \u001b[39m# no valid `self._rcvd_idx` is found (i.e., didn't break)\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1315'>1316</a>\u001b[0m     \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_persistent_workers:\n\u001b[0;32m-> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1316'>1317</a>\u001b[0m         \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_shutdown_workers()\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1317'>1318</a>\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mStopIteration\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1319'>1320</a>\u001b[0m \u001b[39m# Now `self._rcvd_idx` is the batch index we want to fetch\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1320'>1321</a>\u001b[0m \n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1321'>1322</a>\u001b[0m \u001b[39m# Check if the next sample has already been generated\u001b[39;00m\n",
+      "File \u001b[0;32m~/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py:1442\u001b[0m, in \u001b[0;36m_MultiProcessingDataLoaderIter._shutdown_workers\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1436'>1437</a>\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_mark_worker_as_unavailable(worker_id, shutdown\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m)\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1437'>1438</a>\u001b[0m \u001b[39mfor\u001b[39;00m w \u001b[39min\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_workers:\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1438'>1439</a>\u001b[0m     \u001b[39m# We should be able to join here, but in case anything went\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1439'>1440</a>\u001b[0m     \u001b[39m# wrong, we set a timeout and if the workers fail to join,\u001b[39;00m\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1440'>1441</a>\u001b[0m     \u001b[39m# they are killed in the `finally` block.\u001b[39;00m\n\u001b[0;32m-> <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1441'>1442</a>\u001b[0m     w\u001b[39m.\u001b[39;49mjoin(timeout\u001b[39m=\u001b[39;49m_utils\u001b[39m.\u001b[39;49mMP_STATUS_CHECK_INTERVAL)\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1442'>1443</a>\u001b[0m \u001b[39mfor\u001b[39;00m q \u001b[39min\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_index_queues:\n\u001b[1;32m   <a href='file:///Users/franck/Library/Python/3.8/lib/python/site-packages/torch/utils/data/dataloader.py?line=1443'>1444</a>\u001b[0m     q\u001b[39m.\u001b[39mcancel_join_thread()\n",
+      "File \u001b[0;32m/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/process.py:149\u001b[0m, in \u001b[0;36mBaseProcess.join\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/process.py?line=146'>147</a>\u001b[0m \u001b[39massert\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_parent_pid \u001b[39m==\u001b[39m os\u001b[39m.\u001b[39mgetpid(), \u001b[39m'\u001b[39m\u001b[39mcan only join a child process\u001b[39m\u001b[39m'\u001b[39m\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/process.py?line=147'>148</a>\u001b[0m \u001b[39massert\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_popen \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m, \u001b[39m'\u001b[39m\u001b[39mcan only join a started process\u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m--> <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/process.py?line=148'>149</a>\u001b[0m res \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_popen\u001b[39m.\u001b[39;49mwait(timeout)\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/process.py?line=149'>150</a>\u001b[0m \u001b[39mif\u001b[39;00m res \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/process.py?line=150'>151</a>\u001b[0m     _children\u001b[39m.\u001b[39mdiscard(\u001b[39mself\u001b[39m)\n",
+      "File \u001b[0;32m/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/popen_fork.py:44\u001b[0m, in \u001b[0;36mPopen.wait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m     <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/popen_fork.py?line=41'>42</a>\u001b[0m \u001b[39mif\u001b[39;00m timeout \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m     <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/popen_fork.py?line=42'>43</a>\u001b[0m     \u001b[39mfrom\u001b[39;00m \u001b[39mmultiprocessing\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mconnection\u001b[39;00m \u001b[39mimport\u001b[39;00m wait\n\u001b[0;32m---> <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/popen_fork.py?line=43'>44</a>\u001b[0m     \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m wait([\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49msentinel], timeout):\n\u001b[1;32m     <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/popen_fork.py?line=44'>45</a>\u001b[0m         \u001b[39mreturn\u001b[39;00m \u001b[39mNone\u001b[39;00m\n\u001b[1;32m     <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/popen_fork.py?line=45'>46</a>\u001b[0m \u001b[39m# This shouldn't block if wait() returned successfully.\u001b[39;00m\n",
+      "File \u001b[0;32m/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/connection.py:930\u001b[0m, in \u001b[0;36mwait\u001b[0;34m(object_list, timeout)\u001b[0m\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/connection.py?line=926'>927</a>\u001b[0m     deadline \u001b[39m=\u001b[39m time\u001b[39m.\u001b[39mmonotonic() \u001b[39m+\u001b[39m timeout\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/connection.py?line=928'>929</a>\u001b[0m \u001b[39mwhile\u001b[39;00m \u001b[39mTrue\u001b[39;00m:\n\u001b[0;32m--> <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/connection.py?line=929'>930</a>\u001b[0m     ready \u001b[39m=\u001b[39m selector\u001b[39m.\u001b[39;49mselect(timeout)\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/connection.py?line=930'>931</a>\u001b[0m     \u001b[39mif\u001b[39;00m ready:\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/multiprocessing/connection.py?line=931'>932</a>\u001b[0m         \u001b[39mreturn\u001b[39;00m [key\u001b[39m.\u001b[39mfileobj \u001b[39mfor\u001b[39;00m (key, events) \u001b[39min\u001b[39;00m ready]\n",
+      "File \u001b[0;32m/Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/selectors.py:415\u001b[0m, in \u001b[0;36m_PollLikeSelector.select\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/selectors.py?line=412'>413</a>\u001b[0m ready \u001b[39m=\u001b[39m []\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/selectors.py?line=413'>414</a>\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m--> <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/selectors.py?line=414'>415</a>\u001b[0m     fd_event_list \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_selector\u001b[39m.\u001b[39;49mpoll(timeout)\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/selectors.py?line=415'>416</a>\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mInterruptedError\u001b[39;00m:\n\u001b[1;32m    <a href='file:///Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.8/lib/python3.8/selectors.py?line=416'>417</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m ready\n",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
      ]
     }
    ],
@@ -2085,7 +1885,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 108,
    "id": "3495ae11",
    "metadata": {},
    "outputs": [
@@ -2093,9 +1893,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "okk\n",
-      "oisfn\n",
-      "['ants', 'bees']\n"
+      "<torch.utils.data.dataloader.DataLoader object at 0x12ac9f1c0>\n",
+      "{'train': 244, 'val': 138, 'test': 14}\n"
      ]
     },
     {
@@ -2111,10 +1910,10 @@
     {
      "data": {
       "text/plain": [
-       "'# Replace the final fully connected layer\\n# Parameters of newly constructed modules have requires_grad=True by default\\nnum_ftrs = model.fc.in_features\\nmodel.fc = nn.Linear(num_ftrs, 2)\\n# Send the model to the GPU\\nmodel = model.to(device)\\n# Set the loss function\\ncriterion = nn.CrossEntropyLoss()\\n\\n# Observe that only the parameters of the final layer are being optimized\\noptimizer_conv = optim.SGD(model.fc.parameters(), lr=0.001, momentum=0.9)\\nexp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)\\nmodel, epoch_time = train_model(\\n    model, criterion, optimizer_conv, exp_lr_scheduler, num_epochs=10\\n)\\n'"
+       "'# Replace the final fully connected layer\\n# Parameters of newly constructed modules have requires_grad=True by default\\nnum_ftrs = model.fc.in_features\\nmodel.fc = nn.Linear(num_ftrs, 2)\\n\\n\\n# Send the model to the GPU\\nmodel = model.to(device)\\n# Set the loss function\\ncriterion = nn.CrossEntropyLoss()\\n\\n# Observe that only the parameters of the final layer are being optimized\\noptimizer_conv = optim.SGD(model.fc.parameters(), lr=0.001, momentum=0.9)\\nexp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)\\nmodel, epoch_time = train_model(\\n    model, criterion, optimizer_conv, exp_lr_scheduler, num_epochs=10\\n)\\n'"
       ]
      },
-     "execution_count": 31,
+     "execution_count": 108,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -2288,7 +2087,9 @@
     "\n",
     "def eval_model():\n",
     "    return\n",
-    "\n",
+    "    \n",
+    "print(dataloaders[\"test\"])\n",
+    "print(dataset_sizes)\n",
     "\n",
     "# Download a pre-trained ResNet18 model and freeze its weights\n",
     "model = torchvision.models.resnet18(pretrained=True)\n",
@@ -2299,6 +2100,8 @@
     "# Parameters of newly constructed modules have requires_grad=True by default\n",
     "num_ftrs = model.fc.in_features\n",
     "model.fc = nn.Linear(num_ftrs, 2)\n",
+    "\n",
+    "\n",
     "# Send the model to the GPU\n",
     "model = model.to(device)\n",
     "# Set the loss function\n",
diff --git a/king_crab.png b/king_crab.png
index 8741610f56dd1c52f2090dc2b44136038356079f..8214b1e7d36b74d4537e7c1c6144f516e7e5b5f3 100644
Binary files a/king_crab.png and b/king_crab.png differ