diff --git a/TD2 Deep Learning.ipynb b/TD2 Deep Learning.ipynb
index ffe0153cf3dede39addb5253623bd0974149fc22..4c198c59d5e2fd37fa964a51e1bfd6d5bc14b6ed 100644
--- a/TD2 Deep Learning.ipynb	
+++ b/TD2 Deep Learning.ipynb	
@@ -5,7 +5,7 @@
    "id": "3d4b4327",
    "metadata": {},
    "source": [
-    "## Rapport de Rémi Girard & Philippe Berton"
+    "## Rapport de Rémi Girard"
    ]
   },
   {
@@ -346,8 +346,6 @@
    "id": "4492b0ae",
    "metadata": {},
    "source": [
-    "Nous avons repris ces instructions directement.\n",
-    "\n",
     "Build a new network with the following structure.\n",
     "\n",
     "- It has 3 convolutional layers of kernel size 3.\n",
@@ -361,7 +359,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "id": "317bf070",
    "metadata": {},
    "outputs": [
@@ -437,23 +435,68 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "id": "4b53f229",
    "metadata": {},
    "outputs": [
     {
-     "ename": "RuntimeError",
-     "evalue": "mat1 and mat2 shapes cannot be multiplied (80x256 and 1024x512)",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 0 \tTraining Loss: 45.387473 \tValidation Loss: 41.778890\n",
+      "Validation loss decreased (inf --> 41.778890).  Saving model ...\n",
+      "Epoch: 1 \tTraining Loss: 39.710381 \tValidation Loss: 35.580589\n",
+      "Validation loss decreased (41.778890 --> 35.580589).  Saving model ...\n",
+      "Epoch: 2 \tTraining Loss: 35.102491 \tValidation Loss: 31.372604\n",
+      "Validation loss decreased (35.580589 --> 31.372604).  Saving model ...\n",
+      "Epoch: 3 \tTraining Loss: 32.308584 \tValidation Loss: 29.150974\n",
+      "Validation loss decreased (31.372604 --> 29.150974).  Saving model ...\n",
+      "Epoch: 4 \tTraining Loss: 30.299783 \tValidation Loss: 27.625314\n",
+      "Validation loss decreased (29.150974 --> 27.625314).  Saving model ...\n",
+      "Epoch: 5 \tTraining Loss: 28.809755 \tValidation Loss: 26.581921\n",
+      "Validation loss decreased (27.625314 --> 26.581921).  Saving model ...\n",
+      "Epoch: 6 \tTraining Loss: 27.433523 \tValidation Loss: 25.207890\n",
+      "Validation loss decreased (26.581921 --> 25.207890).  Saving model ...\n",
+      "Epoch: 7 \tTraining Loss: 26.070307 \tValidation Loss: 23.653238\n",
+      "Validation loss decreased (25.207890 --> 23.653238).  Saving model ...\n",
+      "Epoch: 8 \tTraining Loss: 24.852040 \tValidation Loss: 22.611088\n",
+      "Validation loss decreased (23.653238 --> 22.611088).  Saving model ...\n",
+      "Epoch: 9 \tTraining Loss: 23.660346 \tValidation Loss: 22.185724\n",
+      "Validation loss decreased (22.611088 --> 22.185724).  Saving model ...\n",
+      "Epoch: 10 \tTraining Loss: 22.527712 \tValidation Loss: 20.529894\n",
+      "Validation loss decreased (22.185724 --> 20.529894).  Saving model ...\n",
+      "Epoch: 11 \tTraining Loss: 21.498114 \tValidation Loss: 19.539335\n",
+      "Validation loss decreased (20.529894 --> 19.539335).  Saving model ...\n",
+      "Epoch: 12 \tTraining Loss: 20.521416 \tValidation Loss: 19.195384\n",
+      "Validation loss decreased (19.539335 --> 19.195384).  Saving model ...\n",
+      "Epoch: 13 \tTraining Loss: 19.687801 \tValidation Loss: 18.525974\n",
+      "Validation loss decreased (19.195384 --> 18.525974).  Saving model ...\n",
+      "Epoch: 14 \tTraining Loss: 18.804486 \tValidation Loss: 18.450878\n",
+      "Validation loss decreased (18.525974 --> 18.450878).  Saving model ...\n",
+      "Epoch: 15 \tTraining Loss: 18.017811 \tValidation Loss: 18.017287\n",
+      "Validation loss decreased (18.450878 --> 18.017287).  Saving model ...\n",
+      "Epoch: 16 \tTraining Loss: 17.245886 \tValidation Loss: 17.276192\n",
+      "Validation loss decreased (18.017287 --> 17.276192).  Saving model ...\n",
+      "Epoch: 17 \tTraining Loss: 16.661335 \tValidation Loss: 17.073728\n",
+      "Validation loss decreased (17.276192 --> 17.073728).  Saving model ...\n",
+      "Epoch: 18 \tTraining Loss: 15.919614 \tValidation Loss: 16.473665\n",
+      "Validation loss decreased (17.073728 --> 16.473665).  Saving model ...\n"
+     ]
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
      "output_type": "error",
      "traceback": [
       "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
       "\u001b[1;32md:\\Centrale\\MOMMOD\\Deep Learning\\TD2\\deep-learning-tutorial-1\\TD2 Deep Learning.ipynb Cell 18\u001b[0m line \u001b[0;36m2\n\u001b[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=22'>23</a>\u001b[0m optimizer\u001b[39m.\u001b[39mzero_grad()\n\u001b[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=23'>24</a>\u001b[0m \u001b[39m# Forward pass: compute predicted outputs by passing inputs to the model\u001b[39;00m\n\u001b[1;32m---> <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=24'>25</a>\u001b[0m output \u001b[39m=\u001b[39m model(data)\n\u001b[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=25'>26</a>\u001b[0m \u001b[39m# Calculate the batch loss\u001b[39;00m\n\u001b[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=26'>27</a>\u001b[0m loss \u001b[39m=\u001b[39m criterion(output, target)\n",
       "File \u001b[1;32mc:\\Python310\\lib\\site-packages\\torch\\nn\\modules\\module.py:1190\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *input, **kwargs)\u001b[0m\n\u001b[0;32m   1186\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[0;32m   1187\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1188\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_forward_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_forward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1189\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1190\u001b[0m     \u001b[39mreturn\u001b[39;00m forward_call(\u001b[39m*\u001b[39m\u001b[39minput\u001b[39m, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n\u001b[0;32m   1191\u001b[0m \u001b[39m# Do not call functions when jit is used\u001b[39;00m\n\u001b[0;32m   1192\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[39m=\u001b[39m [], []\n",
-      "\u001b[1;32md:\\Centrale\\MOMMOD\\Deep Learning\\TD2\\deep-learning-tutorial-1\\TD2 Deep Learning.ipynb Cell 18\u001b[0m line \u001b[0;36m3\n\u001b[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=29'>30</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[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=30'>31</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[39m2\u001b[39m\u001b[39m*\u001b[39m\u001b[39m2\u001b[39m)\n\u001b[1;32m---> <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=31'>32</a>\u001b[0m x \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdropout(F\u001b[39m.\u001b[39mrelu(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mfc1(x)))\n\u001b[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=32'>33</a>\u001b[0m x \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdropout(F\u001b[39m.\u001b[39mrelu(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mfc2(x)))\n\u001b[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=33'>34</a>\u001b[0m x \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mfc3(x)\n",
+      "\u001b[1;32md:\\Centrale\\MOMMOD\\Deep Learning\\TD2\\deep-learning-tutorial-1\\TD2 Deep Learning.ipynb Cell 18\u001b[0m line \u001b[0;36m2\n\u001b[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=26'>27</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mforward\u001b[39m(\u001b[39mself\u001b[39m, x):\n\u001b[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=27'>28</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[1;32m---> <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=28'>29</a>\u001b[0m     x \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpool(F\u001b[39m.\u001b[39mrelu(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mconv2(x)))\n\u001b[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=29'>30</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[0;32m     <a href='vscode-notebook-cell:/d%3A/Centrale/MOMMOD/Deep%20Learning/TD2/deep-learning-tutorial-1/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=30'>31</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[1;32mc:\\Python310\\lib\\site-packages\\torch\\nn\\modules\\module.py:1190\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *input, **kwargs)\u001b[0m\n\u001b[0;32m   1186\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[0;32m   1187\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1188\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_forward_hooks \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_forward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1189\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1190\u001b[0m     \u001b[39mreturn\u001b[39;00m forward_call(\u001b[39m*\u001b[39m\u001b[39minput\u001b[39m, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n\u001b[0;32m   1191\u001b[0m \u001b[39m# Do not call functions when jit is used\u001b[39;00m\n\u001b[0;32m   1192\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[39m=\u001b[39m [], []\n",
-      "File \u001b[1;32mc:\\Python310\\lib\\site-packages\\torch\\nn\\modules\\linear.py:114\u001b[0m, in \u001b[0;36mLinear.forward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m    113\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mforward\u001b[39m(\u001b[39mself\u001b[39m, \u001b[39minput\u001b[39m: Tensor) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m Tensor:\n\u001b[1;32m--> 114\u001b[0m     \u001b[39mreturn\u001b[39;00m F\u001b[39m.\u001b[39;49mlinear(\u001b[39minput\u001b[39;49m, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mweight, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mbias)\n",
-      "\u001b[1;31mRuntimeError\u001b[0m: mat1 and mat2 shapes cannot be multiplied (80x256 and 1024x512)"
+      "File \u001b[1;32mc:\\Python310\\lib\\site-packages\\torch\\nn\\modules\\conv.py:463\u001b[0m, in \u001b[0;36mConv2d.forward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m    462\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mforward\u001b[39m(\u001b[39mself\u001b[39m, \u001b[39minput\u001b[39m: Tensor) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m Tensor:\n\u001b[1;32m--> 463\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_conv_forward(\u001b[39minput\u001b[39;49m, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mweight, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mbias)\n",
+      "File \u001b[1;32mc:\\Python310\\lib\\site-packages\\torch\\nn\\modules\\conv.py:459\u001b[0m, in \u001b[0;36mConv2d._conv_forward\u001b[1;34m(self, input, weight, bias)\u001b[0m\n\u001b[0;32m    455\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpadding_mode \u001b[39m!=\u001b[39m \u001b[39m'\u001b[39m\u001b[39mzeros\u001b[39m\u001b[39m'\u001b[39m:\n\u001b[0;32m    456\u001b[0m     \u001b[39mreturn\u001b[39;00m F\u001b[39m.\u001b[39mconv2d(F\u001b[39m.\u001b[39mpad(\u001b[39minput\u001b[39m, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_reversed_padding_repeated_twice, mode\u001b[39m=\u001b[39m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpadding_mode),\n\u001b[0;32m    457\u001b[0m                     weight, bias, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mstride,\n\u001b[0;32m    458\u001b[0m                     _pair(\u001b[39m0\u001b[39m), \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdilation, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mgroups)\n\u001b[1;32m--> 459\u001b[0m \u001b[39mreturn\u001b[39;00m F\u001b[39m.\u001b[39;49mconv2d(\u001b[39minput\u001b[39;49m, weight, bias, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mstride,\n\u001b[0;32m    460\u001b[0m                 \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mpadding, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mdilation, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mgroups)\n",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
      ]
     }
    ],
@@ -543,18 +586,18 @@
    "id": "38175cd3",
    "metadata": {},
    "source": [
-    "*Nous avons ajouté le suivi de la validation loss*"
+    "*Le suivi de la validation loss a été ajouté*"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "id": "d39df818",
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -564,7 +607,7 @@
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -576,13 +619,13 @@
    "source": [
     "import matplotlib.pyplot as plt\n",
     "\n",
-    "plt.plot(range(n_epochs), train_loss_list)\n",
+    "plt.plot(range(len(train_loss_list)), train_loss_list)\n",
     "plt.xlabel(\"Epoch\")\n",
     "plt.ylabel(\"Train Loss\")\n",
     "plt.title(\"Performance of Model 1\")\n",
     "plt.show()\n",
     "\n",
-    "plt.plot(range(n_epochs), valid_loss_list)\n",
+    "plt.plot(range(len(valid_loss_list)), valid_loss_list)\n",
     "plt.xlabel(\"Epoch\")\n",
     "plt.ylabel(\"Validation Loss\")\n",
     "plt.title(\"Performance of Model 1,\")\n",
@@ -599,7 +642,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "id": "e93efdfc",
    "metadata": {},
    "outputs": [
@@ -607,20 +650,20 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Test Loss: 17.760002\n",
+      "Test Loss: 16.619062\n",
       "\n",
-      "Test Accuracy of airplane: 75% (754/1000)\n",
-      "Test Accuracy of automobile: 85% (851/1000)\n",
-      "Test Accuracy of  bird: 53% (533/1000)\n",
-      "Test Accuracy of   cat: 52% (525/1000)\n",
-      "Test Accuracy of  deer: 66% (663/1000)\n",
-      "Test Accuracy of   dog: 59% (592/1000)\n",
-      "Test Accuracy of  frog: 76% (762/1000)\n",
-      "Test Accuracy of horse: 72% (727/1000)\n",
-      "Test Accuracy of  ship: 79% (794/1000)\n",
-      "Test Accuracy of truck: 79% (799/1000)\n",
+      "Test Accuracy of airplane: 77% (778/1000)\n",
+      "Test Accuracy of automobile: 82% (828/1000)\n",
+      "Test Accuracy of  bird: 52% (525/1000)\n",
+      "Test Accuracy of   cat: 48% (486/1000)\n",
+      "Test Accuracy of  deer: 64% (645/1000)\n",
+      "Test Accuracy of   dog: 58% (583/1000)\n",
+      "Test Accuracy of  frog: 88% (881/1000)\n",
+      "Test Accuracy of horse: 77% (772/1000)\n",
+      "Test Accuracy of  ship: 79% (799/1000)\n",
+      "Test Accuracy of truck: 83% (834/1000)\n",
       "\n",
-      "Test Accuracy (Overall): 70% (7000/10000)\n"
+      "Test Accuracy (Overall): 71% (7131/10000)\n"
      ]
     }
    ],
@@ -891,7 +934,7 @@
    "id": "d53f5be4",
    "metadata": {},
    "source": [
-    "Nous n'avons pas réussi à mettre en oeuvre l'aware quantization"
+    "Echec à mettre en oeuvre l'aware quantization"
    ]
   },
   {
@@ -910,6 +953,7 @@
     }
    ],
    "source": [
+    "break\n",
     "\n",
     "class M(torch.nn.Module):\n",
     "    def __init__(self):\n",
@@ -2227,7 +2271,7 @@
    "source": [
     "Modification du code pour inclure un test set:\n",
     "\n",
-    "Pour cela, nous avons mélangé les deux datasets de train et de validation, puis reséparé en 3 parties, en s'inspirant de l'exercice 1."
+    "Pour cela, les deux datasets de train et de validation ont été mélangé, puis reséparé en 3 parties, en s'inspirant de l'exercice 1."
    ]
   },
   {