diff --git a/TD2 Deep Learning.ipynb b/TD2 Deep Learning.ipynb
index 2ecfce959ae6b947b633a758433f9bea0bf6992e..de44c488965cb322cfe8f5c028ef905fcf7c66e0 100644
--- a/TD2 Deep Learning.ipynb	
+++ b/TD2 Deep Learning.ipynb	
@@ -31,14 +31,53 @@
     "Install and test PyTorch from  https://pytorch.org/get-started/locally."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "I am using a personal remote jupyter server that is running on a pc with two gpus."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "330a42f5",
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Wed Nov 22 20:09:07 2023       \n",
+      "+---------------------------------------------------------------------------------------+\n",
+      "| NVIDIA-SMI 535.129.03             Driver Version: 535.129.03   CUDA Version: 12.2     |\n",
+      "|-----------------------------------------+----------------------+----------------------+\n",
+      "| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
+      "| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |\n",
+      "|                                         |                      |               MIG M. |\n",
+      "|=========================================+======================+======================|\n",
+      "|   0  NVIDIA GeForce RTX 3090        Off | 00000000:01:00.0 Off |                  N/A |\n",
+      "|  0%   48C    P8              19W / 420W |    269MiB / 24576MiB |      0%      Default |\n",
+      "|                                         |                      |                  N/A |\n",
+      "+-----------------------------------------+----------------------+----------------------+\n",
+      "|   1  NVIDIA GeForce RTX 3070        Off | 00000000:07:00.0 Off |                  N/A |\n",
+      "|  0%   50C    P8              15W / 220W |     10MiB /  8192MiB |      0%      Default |\n",
+      "|                                         |                      |                  N/A |\n",
+      "+-----------------------------------------+----------------------+----------------------+\n",
+      "                                                                                         \n",
+      "+---------------------------------------------------------------------------------------+\n",
+      "| Processes:                                                                            |\n",
+      "|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |\n",
+      "|        ID   ID                                                             Usage      |\n",
+      "|=======================================================================================|\n",
+      "|    0   N/A  N/A      1670      G   /usr/lib/xorg/Xorg                          247MiB |\n",
+      "|    0   N/A  N/A      1841      G   /usr/bin/gnome-shell                         11MiB |\n",
+      "|    1   N/A  N/A      1670      G   /usr/lib/xorg/Xorg                            4MiB |\n",
+      "+---------------------------------------------------------------------------------------+\n"
+     ]
+    }
+   ],
    "source": [
-    "%pip install torch torchvision"
+    "!nvidia-smi"
    ]
   },
   {
@@ -52,10 +91,72 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "b1950f0a",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tensor([[ 1.8855e-03,  2.9108e-01,  1.0010e+00, -1.7448e+00,  1.8745e+00,\n",
+      "          3.0039e-01, -1.0610e+00, -4.2353e-01,  1.5882e+00,  4.7778e-01],\n",
+      "        [ 6.9629e-01, -2.1862e-01, -1.1275e+00, -2.2043e-01, -9.0295e-01,\n",
+      "         -1.9357e+00, -9.8882e-01,  9.4581e-01, -1.1930e+00,  9.8106e-01],\n",
+      "        [-3.3844e-01, -1.0876e-01, -4.0938e-01,  2.8881e-01, -1.9949e-01,\n",
+      "         -5.8048e-01, -7.5410e-01, -1.2992e+00, -4.5162e-01,  9.0695e-01],\n",
+      "        [ 9.0743e-01,  1.8967e+00,  2.6043e+00,  6.2713e-01,  8.9104e-01,\n",
+      "          4.2479e-01, -1.1447e+00, -1.5549e+00, -1.1788e+00, -3.2302e-01],\n",
+      "        [-1.1279e+00,  7.4629e-02, -9.2078e-01, -7.8896e-01, -2.4876e-01,\n",
+      "          1.5658e-01, -2.8966e-01, -1.0835e+00,  1.1235e+00, -6.8270e-01],\n",
+      "        [ 3.4747e-01, -1.4344e+00,  7.0211e-01,  1.9160e+00, -1.5627e+00,\n",
+      "          8.7415e-02,  7.2565e-01, -2.4600e-02, -2.1433e-01, -4.1230e-01],\n",
+      "        [ 1.6323e-01, -6.4762e-01,  7.1466e-02, -4.9402e-01,  4.6785e-01,\n",
+      "          1.2793e+00,  1.7295e+00,  1.6134e-01,  1.1057e+00, -9.2903e-01],\n",
+      "        [ 2.7565e-01,  1.1653e+00, -1.8649e+00, -6.0089e-01,  1.4255e-01,\n",
+      "          5.1984e-01,  1.4124e+00,  4.3731e-01, -7.1495e-01,  4.4668e-01],\n",
+      "        [-2.0284e+00,  3.2644e-02, -1.0220e+00, -7.5502e-01,  1.4939e+00,\n",
+      "          2.1324e+00, -9.7155e-02,  4.4492e-01,  2.0190e+00, -1.4172e+00],\n",
+      "        [ 7.7286e-01, -1.8415e-01, -1.7536e-01, -5.6652e-01, -1.4285e+00,\n",
+      "          1.0795e+00, -3.8429e-01, -1.8018e+00, -9.7339e-02,  7.7694e-01],\n",
+      "        [-8.3219e-01, -3.1330e-01,  5.0993e-01,  4.6975e-01, -2.6981e-01,\n",
+      "         -1.7035e-01,  8.6431e-01,  5.9563e-01, -1.7859e-01,  1.8930e+00],\n",
+      "        [-4.5472e-01,  1.7444e+00,  4.8612e-01, -5.4073e-01,  1.4415e+00,\n",
+      "          9.6243e-01,  6.3097e-01, -6.6990e-01,  1.6233e+00, -1.1163e+00],\n",
+      "        [ 2.8865e-01, -8.5031e-01,  8.4932e-01, -1.6480e-01, -9.4282e-01,\n",
+      "          1.9159e+00, -4.7449e-01,  1.0314e-01,  4.7082e-01, -1.5315e+00],\n",
+      "        [ 6.2820e-01, -9.2092e-01, -6.6795e-01,  5.1397e-01,  3.8067e-01,\n",
+      "         -1.4796e-02, -2.6149e-01, -1.2254e+00, -5.8194e-01, -1.5822e+00]])\n",
+      "AlexNet(\n",
+      "  (features): Sequential(\n",
+      "    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))\n",
+      "    (1): ReLU(inplace=True)\n",
+      "    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
+      "    (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))\n",
+      "    (4): ReLU(inplace=True)\n",
+      "    (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
+      "    (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
+      "    (7): ReLU(inplace=True)\n",
+      "    (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
+      "    (9): ReLU(inplace=True)\n",
+      "    (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
+      "    (11): ReLU(inplace=True)\n",
+      "    (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
+      "  )\n",
+      "  (avgpool): AdaptiveAvgPool2d(output_size=(6, 6))\n",
+      "  (classifier): Sequential(\n",
+      "    (0): Dropout(p=0.5, inplace=False)\n",
+      "    (1): Linear(in_features=9216, out_features=4096, bias=True)\n",
+      "    (2): ReLU(inplace=True)\n",
+      "    (3): Dropout(p=0.5, inplace=False)\n",
+      "    (4): Linear(in_features=4096, out_features=4096, bias=True)\n",
+      "    (5): ReLU(inplace=True)\n",
+      "    (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
+      "  )\n",
+      ")\n"
+     ]
+    }
+   ],
    "source": [
     "import torch\n",
     "\n",
@@ -95,12 +196,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "6e18f2fd",
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
+    "import torch.nn as nn\n",
+    "import torch.nn.functional as F\n",
     "import torch\n",
+    "import numpy as np\n",
+    "from torchvision import datasets, transforms\n",
+    "from torch.utils.data.sampler import SubsetRandomSampler\n",
+    "import torch.optim as optim\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "6e18f2fd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CUDA is available!  Training on GPU ...\n"
+     ]
+    }
+   ],
+   "source": [
     "\n",
     "# check if CUDA is available\n",
     "train_on_gpu = torch.cuda.is_available()\n",
@@ -121,14 +244,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "462666a2",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Files already downloaded and verified\n",
+      "Files already downloaded and verified\n"
+     ]
+    }
+   ],
    "source": [
-    "import numpy as np\n",
-    "from torchvision import datasets, transforms\n",
-    "from torch.utils.data.sampler import SubsetRandomSampler\n",
     "\n",
     "# number of subprocesses to use for data loading\n",
     "num_workers = 0\n",
@@ -193,17 +322,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "317bf070",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Net(\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",
+      ")\n"
+     ]
+    }
+   ],
    "source": [
-    "import torch.nn as nn\n",
-    "import torch.nn.functional as F\n",
-    "\n",
     "# define the CNN architecture\n",
     "\n",
-    "\n",
     "class Net(nn.Module):\n",
     "    def __init__(self):\n",
     "        super(Net, self).__init__()\n",
@@ -217,6 +357,7 @@
     "    def forward(self, x):\n",
     "        x = self.pool(F.relu(self.conv1(x)))\n",
     "        x = self.pool(F.relu(self.conv2(x)))\n",
+    "        # print(f'x.shape = {x.shape}')\n",
     "        x = x.view(-1, 16 * 5 * 5)\n",
     "        x = F.relu(self.fc1(x))\n",
     "        x = F.relu(self.fc2(x))\n",
@@ -237,23 +378,88 @@
    "id": "a2dc4974",
    "metadata": {},
    "source": [
-    "Loss function and training using SGD (Stochastic Gradient Descent) optimizer"
+    "Loss function and training using SGD (Stochastic Gradient Descent) optimizer\n",
+    "> I added the running validation loss, to see if visually if overfitting occurs. <br>"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "id": "4b53f229",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 0 \tTraining Loss: 42.195077 \tValidation Loss: 37.653781\n",
+      "Validation loss decreased (inf --> 37.653781).  Saving model ...\n",
+      "Epoch: 1 \tTraining Loss: 34.255484 \tValidation Loss: 31.326523\n",
+      "Validation loss decreased (37.653781 --> 31.326523).  Saving model ...\n",
+      "Epoch: 2 \tTraining Loss: 29.847037 \tValidation Loss: 29.189521\n",
+      "Validation loss decreased (31.326523 --> 29.189521).  Saving model ...\n",
+      "Epoch: 3 \tTraining Loss: 27.616926 \tValidation Loss: 27.410780\n",
+      "Validation loss decreased (29.189521 --> 27.410780).  Saving model ...\n",
+      "Epoch: 4 \tTraining Loss: 26.090010 \tValidation Loss: 26.955581\n",
+      "Validation loss decreased (27.410780 --> 26.955581).  Saving model ...\n",
+      "Epoch: 5 \tTraining Loss: 24.904551 \tValidation Loss: 25.293382\n",
+      "Validation loss decreased (26.955581 --> 25.293382).  Saving model ...\n",
+      "Epoch: 6 \tTraining Loss: 23.761944 \tValidation Loss: 24.479699\n",
+      "Validation loss decreased (25.293382 --> 24.479699).  Saving model ...\n",
+      "Epoch: 7 \tTraining Loss: 22.853249 \tValidation Loss: 24.050349\n",
+      "Validation loss decreased (24.479699 --> 24.050349).  Saving model ...\n",
+      "Epoch: 8 \tTraining Loss: 21.941920 \tValidation Loss: 23.283681\n",
+      "Validation loss decreased (24.050349 --> 23.283681).  Saving model ...\n",
+      "Epoch: 9 \tTraining Loss: 21.182262 \tValidation Loss: 23.741841\n",
+      "Epoch: 10 \tTraining Loss: 20.406208 \tValidation Loss: 22.520819\n",
+      "Validation loss decreased (23.283681 --> 22.520819).  Saving model ...\n",
+      "Epoch: 11 \tTraining Loss: 19.685864 \tValidation Loss: 22.102845\n",
+      "Validation loss decreased (22.520819 --> 22.102845).  Saving model ...\n",
+      "Epoch: 12 \tTraining Loss: 19.020183 \tValidation Loss: 21.780847\n",
+      "Validation loss decreased (22.102845 --> 21.780847).  Saving model ...\n",
+      "Epoch: 13 \tTraining Loss: 18.338785 \tValidation Loss: 22.500668\n",
+      "Epoch: 14 \tTraining Loss: 17.766254 \tValidation Loss: 22.892189\n",
+      "Epoch: 15 \tTraining Loss: 17.163492 \tValidation Loss: 21.602836\n",
+      "Validation loss decreased (21.780847 --> 21.602836).  Saving model ...\n",
+      "Epoch: 16 \tTraining Loss: 16.566336 \tValidation Loss: 21.696428\n",
+      "Epoch: 17 \tTraining Loss: 16.004122 \tValidation Loss: 22.403157\n",
+      "Epoch: 18 \tTraining Loss: 15.494520 \tValidation Loss: 22.072053\n",
+      "Epoch: 19 \tTraining Loss: 15.033227 \tValidation Loss: 21.885703\n",
+      "Epoch: 20 \tTraining Loss: 14.516863 \tValidation Loss: 22.182539\n",
+      "Epoch: 21 \tTraining Loss: 14.037906 \tValidation Loss: 22.538788\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/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 17\u001b[0m line \u001b[0;36m1\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=13'>14</a>\u001b[0m \u001b[39m# Train the model\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=14'>15</a>\u001b[0m model\u001b[39m.\u001b[39mtrain()\n\u001b[0;32m---> <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=15'>16</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:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=16'>17</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:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=17'>18</a>\u001b[0m     \u001b[39mif\u001b[39;00m train_on_gpu:\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#X23sZmlsZQ%3D%3D?line=18'>19</a>\u001b[0m         data, target \u001b[39m=\u001b[39m data\u001b[39m.\u001b[39mcuda(), target\u001b[39m.\u001b[39mcuda()\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/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    627\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    628\u001b[0m     \u001b[39m# TODO(https://github.com/pytorch/pytorch/issues/76750)\u001b[39;00m\n\u001b[1;32m    629\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_reset()  \u001b[39m# type: ignore[call-arg]\u001b[39;00m\n\u001b[0;32m--> 630\u001b[0m data \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_next_data()\n\u001b[1;32m    631\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    632\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    633\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    634\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~/.local/lib/python3.10/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    672\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_next_data\u001b[39m(\u001b[39mself\u001b[39m):\n\u001b[1;32m    673\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--> 674\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    675\u001b[0m     \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_pin_memory:\n\u001b[1;32m    676\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~/.local/lib/python3.10/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     49\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     50\u001b[0m     \u001b[39melse\u001b[39;00m:\n\u001b[0;32m---> 51\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     52\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m     53\u001b[0m     data \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdataset[possibly_batched_index]\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py:51\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m     49\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     50\u001b[0m     \u001b[39melse\u001b[39;00m:\n\u001b[0;32m---> 51\u001b[0m         data \u001b[39m=\u001b[39m [\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mdataset[idx] \u001b[39mfor\u001b[39;00m idx \u001b[39min\u001b[39;00m possibly_batched_index]\n\u001b[1;32m     52\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m     53\u001b[0m     data \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdataset[possibly_batched_index]\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/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    115\u001b[0m img \u001b[39m=\u001b[39m Image\u001b[39m.\u001b[39mfromarray(img)\n\u001b[1;32m    117\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--> 118\u001b[0m     img \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mtransform(img)\n\u001b[1;32m    120\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    121\u001b[0m     target \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mtarget_transform(target)\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/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     93\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m__call__\u001b[39m(\u001b[39mself\u001b[39m, img):\n\u001b[1;32m     94\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---> 95\u001b[0m         img \u001b[39m=\u001b[39m t(img)\n\u001b[1;32m     96\u001b[0m     \u001b[39mreturn\u001b[39;00m img\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/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   1516\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   1517\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m-> 1518\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~/.local/lib/python3.10/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   1522\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   1523\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1524\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   1525\u001b[0m         \u001b[39mor\u001b[39;00m _global_backward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1526\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\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   1529\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m   1530\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torchvision/transforms/transforms.py:277\u001b[0m, in \u001b[0;36mNormalize.forward\u001b[0;34m(self, tensor)\u001b[0m\n\u001b[1;32m    269\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mforward\u001b[39m(\u001b[39mself\u001b[39m, tensor: Tensor) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m Tensor:\n\u001b[1;32m    270\u001b[0m \u001b[39m    \u001b[39m\u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m    271\u001b[0m \u001b[39m    Args:\u001b[39;00m\n\u001b[1;32m    272\u001b[0m \u001b[39m        tensor (Tensor): Tensor image to be normalized.\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    275\u001b[0m \u001b[39m        Tensor: Normalized Tensor image.\u001b[39;00m\n\u001b[1;32m    276\u001b[0m \u001b[39m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 277\u001b[0m     \u001b[39mreturn\u001b[39;00m F\u001b[39m.\u001b[39;49mnormalize(tensor, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mmean, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mstd, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49minplace)\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torchvision/transforms/functional.py:363\u001b[0m, in \u001b[0;36mnormalize\u001b[0;34m(tensor, mean, std, inplace)\u001b[0m\n\u001b[1;32m    360\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39misinstance\u001b[39m(tensor, torch\u001b[39m.\u001b[39mTensor):\n\u001b[1;32m    361\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mTypeError\u001b[39;00m(\u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mimg should be Tensor Image. Got \u001b[39m\u001b[39m{\u001b[39;00m\u001b[39mtype\u001b[39m(tensor)\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m)\n\u001b[0;32m--> 363\u001b[0m \u001b[39mreturn\u001b[39;00m F_t\u001b[39m.\u001b[39;49mnormalize(tensor, mean\u001b[39m=\u001b[39;49mmean, std\u001b[39m=\u001b[39;49mstd, inplace\u001b[39m=\u001b[39;49minplace)\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torchvision/transforms/_functional_tensor.py:920\u001b[0m, in \u001b[0;36mnormalize\u001b[0;34m(tensor, mean, std, inplace)\u001b[0m\n\u001b[1;32m    917\u001b[0m     tensor \u001b[39m=\u001b[39m tensor\u001b[39m.\u001b[39mclone()\n\u001b[1;32m    919\u001b[0m dtype \u001b[39m=\u001b[39m tensor\u001b[39m.\u001b[39mdtype\n\u001b[0;32m--> 920\u001b[0m mean \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39;49mas_tensor(mean, dtype\u001b[39m=\u001b[39;49mdtype, device\u001b[39m=\u001b[39;49mtensor\u001b[39m.\u001b[39;49mdevice)\n\u001b[1;32m    921\u001b[0m std \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39mas_tensor(std, dtype\u001b[39m=\u001b[39mdtype, device\u001b[39m=\u001b[39mtensor\u001b[39m.\u001b[39mdevice)\n\u001b[1;32m    922\u001b[0m \u001b[39mif\u001b[39;00m (std \u001b[39m==\u001b[39m \u001b[39m0\u001b[39m)\u001b[39m.\u001b[39many():\n",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
    "source": [
-    "import torch.optim as optim\n",
     "\n",
     "criterion = nn.CrossEntropyLoss()  # specify loss function\n",
     "optimizer = optim.SGD(model.parameters(), lr=0.01)  # specify optimizer\n",
     "\n",
     "n_epochs = 30  # number of epochs to train the model\n",
     "train_loss_list = []  # list to store loss to visualize\n",
+    "running_validation_loss = []\n",
     "valid_loss_min = np.Inf  # track change in validation loss\n",
     "\n",
     "for epoch in range(n_epochs):\n",
@@ -297,6 +503,7 @@
     "    train_loss = train_loss / len(train_loader)\n",
     "    valid_loss = valid_loss / len(valid_loader)\n",
     "    train_loss_list.append(train_loss)\n",
+    "    running_validation_loss.append(valid_loss)\n",
     "\n",
     "    # Print training/validation statistics\n",
     "    print(\n",
@@ -321,22 +528,36 @@
    "id": "13e1df74",
    "metadata": {},
    "source": [
-    "Does overfit occur? If so, do an early stopping."
+    "Does overfit occur? If so, do an early stopping.\n",
+    "> I did an early stopping around epoch 21."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "id": "d39df818",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "import matplotlib.pyplot as plt\n",
     "\n",
-    "plt.plot(range(n_epochs), train_loss_list)\n",
+    "plt.plot([i for i in range(len(train_loss_list))], train_loss_list)\n",
+    "plt.plot([i for i in range(len(running_validation_loss))], running_validation_loss)\n",
     "plt.xlabel(\"Epoch\")\n",
     "plt.ylabel(\"Loss\")\n",
     "plt.title(\"Performance of Model 1\")\n",
+    "plt.legend(['Train loss', 'Validation loss'])\n",
     "plt.show()"
    ]
   },
@@ -350,10 +571,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "id": "e93efdfc",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test Loss: 21.142969\n",
+      "\n",
+      "Test Accuracy of airplane: 63% (635/1000)\n",
+      "Test Accuracy of automobile: 77% (779/1000)\n",
+      "Test Accuracy of  bird: 45% (451/1000)\n",
+      "Test Accuracy of   cat: 52% (528/1000)\n",
+      "Test Accuracy of  deer: 62% (624/1000)\n",
+      "Test Accuracy of   dog: 48% (482/1000)\n",
+      "Test Accuracy of  frog: 72% (726/1000)\n",
+      "Test Accuracy of horse: 70% (708/1000)\n",
+      "Test Accuracy of  ship: 76% (768/1000)\n",
+      "Test Accuracy of truck: 67% (672/1000)\n",
+      "\n",
+      "Test Accuracy (Overall): 63% (6373/10000)\n"
+     ]
+    }
+   ],
    "source": [
     "model.load_state_dict(torch.load(\"./model_cifar.pt\"))\n",
     "\n",
@@ -371,6 +613,7 @@
     "    # forward pass: compute predicted outputs by passing inputs to the model\n",
     "    output = model(data)\n",
     "    # calculate the batch loss\n",
+    "    print(f'data = {data}\\n target = {target}')\n",
     "    loss = criterion(output, target)\n",
     "    # update test loss\n",
     "    test_loss += loss.item() * data.size(0)\n",
@@ -434,6 +677,304 @@
     "Compare the results obtained with this new network to those obtained previously."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CustomNet(\n",
+      "  (conv1): Conv2d(3, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
+      "  (conv2): Conv2d(16, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
+      "  (conv3): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
+      "  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
+      "  (fc1): Linear(in_features=1024, out_features=520, bias=True)\n",
+      "  (fc2): Linear(in_features=520, out_features=64, bias=True)\n",
+      "  (fc3): Linear(in_features=64, out_features=10, bias=True)\n",
+      ")\n"
+     ]
+    }
+   ],
+   "source": [
+    "class CustomNet(nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super(CustomNet, self).__init__()\n",
+    "        self.conv1 = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=3, stride=1, padding=1)\n",
+    "        self.conv2 = nn.Conv2d(in_channels=16, out_channels=32, kernel_size=3, stride=1, padding=1)\n",
+    "        self.conv3 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, stride=1, padding=1)\n",
+    "        \n",
+    "        self.pool = nn.MaxPool2d(kernel_size=2)\n",
+    "\n",
+    "        self.fc1 = nn.Linear(64 * 4 * 4, 520)\n",
+    "        self.fc2 = nn.Linear(520, 64)\n",
+    "        self.fc3 = nn.Linear(64, 10)\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = self.pool(F.relu(self.conv1(x)))\n",
+    "        x = self.pool(F.relu(self.conv2(x)))\n",
+    "        x = self.pool(F.relu(self.conv3(x)))\n",
+    "\n",
+    "        x = x.view(-1, 64 * 4 * 4)\n",
+    "\n",
+    "        # print(f'before first fully connected: x.shape = {x.shape}')\n",
+    "        x = F.relu(self.fc1(x))\n",
+    "        # print(f'after first fully connected, x.shape = {x.shape}')\n",
+    "        x = F.relu(self.fc2(x))\n",
+    "        x = self.fc3(x)\n",
+    "        return x\n",
+    "\n",
+    "\n",
+    "# create a complete CNN\n",
+    "custom_model = CustomNet()\n",
+    "print(custom_model)\n",
+    "# move tensors to GPU if CUDA is available\n",
+    "if train_on_gpu:\n",
+    "    custom_model.cuda()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Training of the new version of the neural network"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 0 \tTraining Loss: 1.134157 \tValidation Loss: 35.816960\n",
+      "Validation loss decreased (inf --> 35.816960).  Saving model ...\n",
+      "Epoch: 1 \tTraining Loss: 1.088380 \tValidation Loss: 37.159479\n",
+      "Epoch: 2 \tTraining Loss: 0.910855 \tValidation Loss: 37.244466\n",
+      "Epoch: 3 \tTraining Loss: 0.457045 \tValidation Loss: 39.297563\n",
+      "Epoch: 4 \tTraining Loss: 0.567809 \tValidation Loss: 39.350203\n",
+      "Epoch: 5 \tTraining Loss: 0.581826 \tValidation Loss: 39.824758\n",
+      "Epoch: 6 \tTraining Loss: 0.475355 \tValidation Loss: 41.428177\n",
+      "Epoch: 7 \tTraining Loss: 0.446757 \tValidation Loss: 39.261758\n",
+      "Epoch: 8 \tTraining Loss: 0.179121 \tValidation Loss: 42.353380\n",
+      "Epoch: 9 \tTraining Loss: 0.107020 \tValidation Loss: 44.952167\n",
+      "Epoch: 10 \tTraining Loss: 0.038190 \tValidation Loss: 42.309538\n",
+      "Epoch: 11 \tTraining Loss: 0.006820 \tValidation Loss: 43.020387\n",
+      "Epoch: 12 \tTraining Loss: 0.004769 \tValidation Loss: 43.565180\n",
+      "Epoch: 13 \tTraining Loss: 0.003950 \tValidation Loss: 44.026827\n",
+      "Epoch: 14 \tTraining Loss: 0.003434 \tValidation Loss: 44.447328\n",
+      "Epoch: 15 \tTraining Loss: 0.003062 \tValidation Loss: 44.806831\n",
+      "Epoch: 16 \tTraining Loss: 0.002774 \tValidation Loss: 45.128416\n",
+      "Epoch: 17 \tTraining Loss: 0.002539 \tValidation Loss: 45.398260\n",
+      "Epoch: 18 \tTraining Loss: 0.002356 \tValidation Loss: 45.667429\n",
+      "Epoch: 19 \tTraining Loss: 0.002191 \tValidation Loss: 45.895782\n",
+      "Epoch: 20 \tTraining Loss: 0.002060 \tValidation Loss: 46.140433\n",
+      "Epoch: 21 \tTraining Loss: 0.001937 \tValidation Loss: 46.355325\n",
+      "Epoch: 22 \tTraining Loss: 0.001834 \tValidation Loss: 46.542832\n",
+      "Epoch: 23 \tTraining Loss: 0.001739 \tValidation Loss: 46.742928\n",
+      "Epoch: 24 \tTraining Loss: 0.001656 \tValidation Loss: 46.915519\n",
+      "Epoch: 25 \tTraining Loss: 0.001580 \tValidation Loss: 47.089529\n",
+      "Epoch: 26 \tTraining Loss: 0.001512 \tValidation Loss: 47.235664\n",
+      "Epoch: 27 \tTraining Loss: 0.001450 \tValidation Loss: 47.399466\n",
+      "Epoch: 28 \tTraining Loss: 0.001393 \tValidation Loss: 47.562623\n",
+      "Epoch: 29 \tTraining Loss: 0.001340 \tValidation Loss: 47.701985\n"
+     ]
+    }
+   ],
+   "source": [
+    "criterion = nn.CrossEntropyLoss()  # specify loss function\n",
+    "optimizer = optim.SGD(custom_model.parameters(), lr=0.01)  # specify optimizer\n",
+    "\n",
+    "n_epochs = 30  # number of epochs to train the custom_model\n",
+    "train_loss_list = []  # list to store loss to visualize\n",
+    "valid_loss_min = np.Inf  # track change in validation loss\n",
+    "\n",
+    "for epoch in range(n_epochs):\n",
+    "    # Keep track of training and validation loss\n",
+    "    train_loss = 0.0\n",
+    "    valid_loss = 0.0\n",
+    "\n",
+    "    # Train the custom_model\n",
+    "    custom_model.train()\n",
+    "    for data, target in train_loader:\n",
+    "        # Move tensors to GPU if CUDA is available\n",
+    "        if train_on_gpu:\n",
+    "            data, target = data.cuda(), target.cuda()\n",
+    "        # Clear the gradients of all optimized variables\n",
+    "        optimizer.zero_grad()\n",
+    "        # Forward pass: compute predicted outputs by passing inputs to the custom_model\n",
+    "        output = custom_model(data)\n",
+    "        # Calculate the batch loss\n",
+    "        loss = criterion(output, target)\n",
+    "        # Backward pass: compute gradient of the loss with respect to custom_model parameters\n",
+    "        loss.backward()\n",
+    "        # Perform a single optimization step (parameter update)\n",
+    "        optimizer.step()\n",
+    "        # Update training loss\n",
+    "        train_loss += loss.item() * data.size(0)\n",
+    "\n",
+    "    # Validate the custom_model\n",
+    "    custom_model.eval()\n",
+    "    for data, target in valid_loader:\n",
+    "        # Move tensors to GPU if CUDA is available\n",
+    "        if train_on_gpu:\n",
+    "            data, target = data.cuda(), target.cuda()\n",
+    "        # Forward pass: compute predicted outputs by passing inputs to the custom_model\n",
+    "        output = custom_model(data)\n",
+    "        # Calculate the batch loss\n",
+    "        loss = criterion(output, target)\n",
+    "        # Update average validation loss\n",
+    "        valid_loss += loss.item() * data.size(0)\n",
+    "\n",
+    "    # Calculate average losses\n",
+    "    train_loss = train_loss / len(train_loader)\n",
+    "    valid_loss = valid_loss / len(valid_loader)\n",
+    "    train_loss_list.append(train_loss)\n",
+    "\n",
+    "    # Print training/validation statistics\n",
+    "    print(\n",
+    "        \"Epoch: {} \\tTraining Loss: {:.6f} \\tValidation Loss: {:.6f}\".format(\n",
+    "            epoch, train_loss, valid_loss\n",
+    "        )\n",
+    "    )\n",
+    "\n",
+    "    # Save model if validation loss has decreased\n",
+    "    if valid_loss <= valid_loss_min:\n",
+    "        print(\n",
+    "            \"Validation loss decreased ({:.6f} --> {:.6f}).  Saving model ...\".format(\n",
+    "                valid_loss_min, valid_loss\n",
+    "            )\n",
+    "        )\n",
+    "        torch.save(custom_model.state_dict(), \"custom_model2_cifar.pt\")\n",
+    "        valid_loss_min = valid_loss"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "plt.plot(range(n_epochs), train_loss_list)\n",
+    "plt.xlabel(\"Epoch\")\n",
+    "plt.ylabel(\"Loss\")\n",
+    "plt.title(\"Performance of CustomModel\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test Loss: 36.168822\n",
+      "\n",
+      "Test Accuracy of airplane: 72% (728/1000)\n",
+      "Test Accuracy of automobile: 83% (836/1000)\n",
+      "Test Accuracy of  bird: 63% (637/1000)\n",
+      "Test Accuracy of   cat: 61% (617/1000)\n",
+      "Test Accuracy of  deer: 63% (635/1000)\n",
+      "Test Accuracy of   dog: 56% (562/1000)\n",
+      "Test Accuracy of  frog: 66% (664/1000)\n",
+      "Test Accuracy of horse: 76% (767/1000)\n",
+      "Test Accuracy of  ship: 87% (876/1000)\n",
+      "Test Accuracy of truck: 74% (743/1000)\n",
+      "\n",
+      "Test Accuracy (Overall): 70% (7065/10000)\n"
+     ]
+    }
+   ],
+   "source": [
+    "custom_model.load_state_dict(torch.load(\"./custom_model2_cifar.pt\"))\n",
+    "\n",
+    "# track test loss\n",
+    "test_loss = 0.0\n",
+    "class_correct = list(0.0 for i in range(10))\n",
+    "class_total = list(0.0 for i in range(10))\n",
+    "\n",
+    "custom_model.eval()\n",
+    "# iterate over test data\n",
+    "for data, target in test_loader:\n",
+    "    # move tensors to GPU if CUDA is available\n",
+    "    if train_on_gpu:\n",
+    "        data, target = data.cuda(), target.cuda()\n",
+    "    # forward pass: compute predicted outputs by passing inputs to the custom_model\n",
+    "    output = custom_model(data)\n",
+    "    # calculate the batch loss\n",
+    "    loss = criterion(output, target)\n",
+    "    # update test loss\n",
+    "    test_loss += loss.item() * data.size(0)\n",
+    "    # convert output probabilities to predicted class\n",
+    "    _, pred = torch.max(output, 1)\n",
+    "    # compare predictions to true label\n",
+    "    correct_tensor = pred.eq(target.data.view_as(pred))\n",
+    "    correct = (\n",
+    "        np.squeeze(correct_tensor.numpy())\n",
+    "        if not train_on_gpu\n",
+    "        else np.squeeze(correct_tensor.cpu().numpy())\n",
+    "    )\n",
+    "    # calculate test accuracy for each object class\n",
+    "    for i in range(batch_size):\n",
+    "        label = target.data[i]\n",
+    "        class_correct[label] += correct[i].item()\n",
+    "        class_total[label] += 1\n",
+    "\n",
+    "# average test loss\n",
+    "test_loss = test_loss / len(test_loader)\n",
+    "print(\"Test Loss: {:.6f}\\n\".format(test_loss))\n",
+    "\n",
+    "for i in range(10):\n",
+    "    if class_total[i] > 0:\n",
+    "        print(\n",
+    "            \"Test Accuracy of %5s: %2d%% (%2d/%2d)\"\n",
+    "            % (\n",
+    "                classes[i],\n",
+    "                100 * class_correct[i] / class_total[i],\n",
+    "                np.sum(class_correct[i]),\n",
+    "                np.sum(class_total[i]),\n",
+    "            )\n",
+    "        )\n",
+    "    else:\n",
+    "        print(\"Test Accuracy of %5s: N/A (no training examples)\" % (classes[i]))\n",
+    "\n",
+    "print(\n",
+    "    \"\\nTest Accuracy (Overall): %2d%% (%2d/%2d)\"\n",
+    "    % (\n",
+    "        100.0 * np.sum(class_correct) / np.sum(class_total),\n",
+    "        np.sum(class_correct),\n",
+    "        np.sum(class_total),\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    ">We observe an increased test accuracy with the modified model"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "bc381cf4",
@@ -451,23 +992,73 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 49,
    "id": "ef623c26",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "model:  fp32  \t Size (KB): 2365.954\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "2365954"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "import os\n",
     "\n",
     "\n",
     "def print_size_of_model(model, label=\"\"):\n",
-    "    torch.save(model.state_dict(), \"temp.p\")\n",
+    "    torch.save(custom_model.state_dict(), \"temp.p\")\n",
     "    size = os.path.getsize(\"temp.p\")\n",
     "    print(\"model: \", label, \" \\t\", \"Size (KB):\", size / 1e3)\n",
     "    os.remove(\"temp.p\")\n",
     "    return size\n",
     "\n",
     "\n",
-    "print_size_of_model(model, \"fp32\")"
+    "print_size_of_model(custom_model, \"fp32\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "model:  fp32  \t Size (KB): 2365.954\n",
+      "model:  int8  \t Size (KB): 2365.954\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "2365954"
+      ]
+     },
+     "execution_count": 60,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "first_model = Net()\n",
+    "first_model = first_model.load_state_dict(torch.load(\"./model_cifar.pt\"))\n",
+    "print_size_of_model(first_model, \"fp32\")\n",
+    "quantized_first_model = torch.quantization.quantize_dynamic(custom_model, dtype=torch.qint8)\n",
+    "print_size_of_model(quantized_first_model, \"int8\")"
    ]
   },
   {
@@ -480,15 +1071,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 62,
    "id": "c4c65d4b",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "model:  int8  \t Size (KB): 2365.954\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "2365954"
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "import torch.quantization\n",
     "\n",
     "\n",
-    "quantized_model = torch.quantization.quantize_dynamic(model, dtype=torch.qint8)\n",
+    "quantized_model = torch.quantization.quantize_dynamic(custom_model, dtype=torch.qint8)\n",
     "print_size_of_model(quantized_model, \"int8\")"
    ]
   },
@@ -500,6 +1109,177 @@
     "For each class, compare the classification test accuracy of the initial model and the quantized model. Also give the overall test accuracy for both models."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Compute correct classes for the quantized model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NotImplementedError",
+     "evalue": "Could not run 'quantized::linear_dynamic' with arguments from the 'CUDA' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'quantized::linear_dynamic' is only available for these backends: [CPU, BackendSelect, Python, FuncTorchDynamicLayerBackMode, Functionalize, Named, Conjugate, Negative, ZeroTensor, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradMPS, AutogradXPU, AutogradHPU, AutogradLazy, AutogradMeta, Tracer, AutocastCPU, AutocastCUDA, FuncTorchBatched, FuncTorchVmapMode, Batched, VmapMode, FuncTorchGradWrapper, PythonTLSSnapshot, FuncTorchDynamicLayerFrontMode, PreDispatch, PythonDispatcher].\n\nCPU: registered at ../aten/src/ATen/native/quantized/cpu/qlinear_dynamic.cpp:662 [kernel]\nBackendSelect: fallthrough registered at ../aten/src/ATen/core/BackendSelectFallbackKernel.cpp:3 [backend fallback]\nPython: registered at ../aten/src/ATen/core/PythonFallbackKernel.cpp:153 [backend fallback]\nFuncTorchDynamicLayerBackMode: registered at ../aten/src/ATen/functorch/DynamicLayer.cpp:498 [backend fallback]\nFunctionalize: registered at ../aten/src/ATen/FunctionalizeFallbackKernel.cpp:290 [backend fallback]\nNamed: registered at ../aten/src/ATen/core/NamedRegistrations.cpp:7 [backend fallback]\nConjugate: registered at ../aten/src/ATen/ConjugateFallback.cpp:17 [backend fallback]\nNegative: registered at ../aten/src/ATen/native/NegateFallback.cpp:19 [backend fallback]\nZeroTensor: registered at ../aten/src/ATen/ZeroTensorFallback.cpp:86 [backend fallback]\nADInplaceOrView: fallthrough registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:86 [backend fallback]\nAutogradOther: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:53 [backend fallback]\nAutogradCPU: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:57 [backend fallback]\nAutogradCUDA: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:65 [backend fallback]\nAutogradXLA: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:69 [backend fallback]\nAutogradMPS: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:77 [backend fallback]\nAutogradXPU: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:61 [backend fallback]\nAutogradHPU: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:90 [backend fallback]\nAutogradLazy: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:73 [backend fallback]\nAutogradMeta: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:81 [backend fallback]\nTracer: registered at ../torch/csrc/autograd/TraceTypeManual.cpp:296 [backend fallback]\nAutocastCPU: fallthrough registered at ../aten/src/ATen/autocast_mode.cpp:382 [backend fallback]\nAutocastCUDA: fallthrough registered at ../aten/src/ATen/autocast_mode.cpp:249 [backend fallback]\nFuncTorchBatched: registered at ../aten/src/ATen/functorch/LegacyBatchingRegistrations.cpp:710 [backend fallback]\nFuncTorchVmapMode: fallthrough registered at ../aten/src/ATen/functorch/VmapModeRegistrations.cpp:28 [backend fallback]\nBatched: registered at ../aten/src/ATen/LegacyBatchingRegistrations.cpp:1075 [backend fallback]\nVmapMode: fallthrough registered at ../aten/src/ATen/VmapModeRegistrations.cpp:33 [backend fallback]\nFuncTorchGradWrapper: registered at ../aten/src/ATen/functorch/TensorWrapper.cpp:203 [backend fallback]\nPythonTLSSnapshot: registered at ../aten/src/ATen/core/PythonFallbackKernel.cpp:161 [backend fallback]\nFuncTorchDynamicLayerFrontMode: registered at ../aten/src/ATen/functorch/DynamicLayer.cpp:494 [backend fallback]\nPreDispatch: registered at ../aten/src/ATen/core/PythonFallbackKernel.cpp:165 [backend fallback]\nPythonDispatcher: registered at ../aten/src/ATen/core/PythonFallbackKernel.cpp:157 [backend fallback]\n",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNotImplementedError\u001b[0m                       Traceback (most recent call last)",
+      "\u001b[1;32m/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 38\u001b[0m line \u001b[0;36m1\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#Y113sZmlsZQ%3D%3D?line=10'>11</a>\u001b[0m     data, target \u001b[39m=\u001b[39m data\u001b[39m.\u001b[39mcuda(), target\u001b[39m.\u001b[39mcuda()\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#Y113sZmlsZQ%3D%3D?line=11'>12</a>\u001b[0m \u001b[39m# forward pass: compute predicted outputs by passing inputs to the quantized_model\u001b[39;00m\n\u001b[0;32m---> <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#Y113sZmlsZQ%3D%3D?line=12'>13</a>\u001b[0m output \u001b[39m=\u001b[39m quantized_model(data)\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#Y113sZmlsZQ%3D%3D?line=13'>14</a>\u001b[0m \u001b[39m# calculate the batch loss\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#Y113sZmlsZQ%3D%3D?line=14'>15</a>\u001b[0m loss \u001b[39m=\u001b[39m criterion(output, target)\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/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   1516\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   1517\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m-> 1518\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~/.local/lib/python3.10/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   1522\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   1523\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1524\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   1525\u001b[0m         \u001b[39mor\u001b[39;00m _global_backward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1526\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\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   1529\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m   1530\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n",
+      "\u001b[1;32m/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2 Deep Learning.ipynb Cell 38\u001b[0m line \u001b[0;36m2\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#Y113sZmlsZQ%3D%3D?line=18'>19</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\u001b[1;32m     <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#Y113sZmlsZQ%3D%3D?line=20'>21</a>\u001b[0m \u001b[39m# print(f'before first fully connected: x.shape = {x.shape}')\u001b[39;00m\n\u001b[0;32m---> <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#Y113sZmlsZQ%3D%3D?line=21'>22</a>\u001b[0m x \u001b[39m=\u001b[39m F\u001b[39m.\u001b[39mrelu(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mfc1(x))\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#Y113sZmlsZQ%3D%3D?line=22'>23</a>\u001b[0m \u001b[39m# print(f'after first fully connected, x.shape = {x.shape}')\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/vl/Documents/4A/liming_chen_deep/be2/mod_4_6-td2/TD2%20Deep%20Learning.ipynb#Y113sZmlsZQ%3D%3D?line=23'>24</a>\u001b[0m x \u001b[39m=\u001b[39m F\u001b[39m.\u001b[39mrelu(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mfc2(x))\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/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   1516\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   1517\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m-> 1518\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~/.local/lib/python3.10/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   1522\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   1523\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1524\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   1525\u001b[0m         \u001b[39mor\u001b[39;00m _global_backward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1526\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\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   1529\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m   1530\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/ao/nn/quantized/dynamic/modules/linear.py:54\u001b[0m, in \u001b[0;36mLinear.forward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m     51\u001b[0m         Y \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39mops\u001b[39m.\u001b[39mquantized\u001b[39m.\u001b[39mlinear_dynamic(\n\u001b[1;32m     52\u001b[0m             x, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_packed_params\u001b[39m.\u001b[39m_packed_params)\n\u001b[1;32m     53\u001b[0m     \u001b[39melse\u001b[39;00m:\n\u001b[0;32m---> 54\u001b[0m         Y \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39;49mops\u001b[39m.\u001b[39;49mquantized\u001b[39m.\u001b[39;49mlinear_dynamic(\n\u001b[1;32m     55\u001b[0m             x, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_packed_params\u001b[39m.\u001b[39;49m_packed_params, reduce_range\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m)\n\u001b[1;32m     56\u001b[0m \u001b[39melif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_packed_params\u001b[39m.\u001b[39mdtype \u001b[39m==\u001b[39m torch\u001b[39m.\u001b[39mfloat16:\n\u001b[1;32m     57\u001b[0m     Y \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39mops\u001b[39m.\u001b[39mquantized\u001b[39m.\u001b[39mlinear_dynamic_fp16(\n\u001b[1;32m     58\u001b[0m         x, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_packed_params\u001b[39m.\u001b[39m_packed_params)\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/_ops.py:692\u001b[0m, in \u001b[0;36mOpOverloadPacket.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    687\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m__call__\u001b[39m(\u001b[39mself\u001b[39m, \u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs):\n\u001b[1;32m    688\u001b[0m     \u001b[39m# overloading __call__ to ensure torch.ops.foo.bar()\u001b[39;00m\n\u001b[1;32m    689\u001b[0m     \u001b[39m# is still callable from JIT\u001b[39;00m\n\u001b[1;32m    690\u001b[0m     \u001b[39m# We save the function ptr as the `op` attribute on\u001b[39;00m\n\u001b[1;32m    691\u001b[0m     \u001b[39m# OpOverloadPacket to access it here.\u001b[39;00m\n\u001b[0;32m--> 692\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_op(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs \u001b[39mor\u001b[39;49;00m {})\n",
+      "\u001b[0;31mNotImplementedError\u001b[0m: Could not run 'quantized::linear_dynamic' with arguments from the 'CUDA' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'quantized::linear_dynamic' is only available for these backends: [CPU, BackendSelect, Python, FuncTorchDynamicLayerBackMode, Functionalize, Named, Conjugate, Negative, ZeroTensor, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradMPS, AutogradXPU, AutogradHPU, AutogradLazy, AutogradMeta, Tracer, AutocastCPU, AutocastCUDA, FuncTorchBatched, FuncTorchVmapMode, Batched, VmapMode, FuncTorchGradWrapper, PythonTLSSnapshot, FuncTorchDynamicLayerFrontMode, PreDispatch, PythonDispatcher].\n\nCPU: registered at ../aten/src/ATen/native/quantized/cpu/qlinear_dynamic.cpp:662 [kernel]\nBackendSelect: fallthrough registered at ../aten/src/ATen/core/BackendSelectFallbackKernel.cpp:3 [backend fallback]\nPython: registered at ../aten/src/ATen/core/PythonFallbackKernel.cpp:153 [backend fallback]\nFuncTorchDynamicLayerBackMode: registered at ../aten/src/ATen/functorch/DynamicLayer.cpp:498 [backend fallback]\nFunctionalize: registered at ../aten/src/ATen/FunctionalizeFallbackKernel.cpp:290 [backend fallback]\nNamed: registered at ../aten/src/ATen/core/NamedRegistrations.cpp:7 [backend fallback]\nConjugate: registered at ../aten/src/ATen/ConjugateFallback.cpp:17 [backend fallback]\nNegative: registered at ../aten/src/ATen/native/NegateFallback.cpp:19 [backend fallback]\nZeroTensor: registered at ../aten/src/ATen/ZeroTensorFallback.cpp:86 [backend fallback]\nADInplaceOrView: fallthrough registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:86 [backend fallback]\nAutogradOther: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:53 [backend fallback]\nAutogradCPU: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:57 [backend fallback]\nAutogradCUDA: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:65 [backend fallback]\nAutogradXLA: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:69 [backend fallback]\nAutogradMPS: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:77 [backend fallback]\nAutogradXPU: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:61 [backend fallback]\nAutogradHPU: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:90 [backend fallback]\nAutogradLazy: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:73 [backend fallback]\nAutogradMeta: registered at ../aten/src/ATen/core/VariableFallbackKernel.cpp:81 [backend fallback]\nTracer: registered at ../torch/csrc/autograd/TraceTypeManual.cpp:296 [backend fallback]\nAutocastCPU: fallthrough registered at ../aten/src/ATen/autocast_mode.cpp:382 [backend fallback]\nAutocastCUDA: fallthrough registered at ../aten/src/ATen/autocast_mode.cpp:249 [backend fallback]\nFuncTorchBatched: registered at ../aten/src/ATen/functorch/LegacyBatchingRegistrations.cpp:710 [backend fallback]\nFuncTorchVmapMode: fallthrough registered at ../aten/src/ATen/functorch/VmapModeRegistrations.cpp:28 [backend fallback]\nBatched: registered at ../aten/src/ATen/LegacyBatchingRegistrations.cpp:1075 [backend fallback]\nVmapMode: fallthrough registered at ../aten/src/ATen/VmapModeRegistrations.cpp:33 [backend fallback]\nFuncTorchGradWrapper: registered at ../aten/src/ATen/functorch/TensorWrapper.cpp:203 [backend fallback]\nPythonTLSSnapshot: registered at ../aten/src/ATen/core/PythonFallbackKernel.cpp:161 [backend fallback]\nFuncTorchDynamicLayerFrontMode: registered at ../aten/src/ATen/functorch/DynamicLayer.cpp:494 [backend fallback]\nPreDispatch: registered at ../aten/src/ATen/core/PythonFallbackKernel.cpp:165 [backend fallback]\nPythonDispatcher: registered at ../aten/src/ATen/core/PythonFallbackKernel.cpp:157 [backend fallback]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# track test loss\n",
+    "test_loss = 0.0\n",
+    "class_correct_quantized = list(0.0 for i in range(10))\n",
+    "class_total_quantized = list(0.0 for i in range(10))\n",
+    "\n",
+    "quantized_model.eval()\n",
+    "# iterate over test data\n",
+    "for data, target in test_loader:\n",
+    "    # move tensors to GPU if CUDA is available\n",
+    "    if train_on_gpu:\n",
+    "        data, target = data.cuda(), target.cuda()\n",
+    "    # forward pass: compute predicted outputs by passing inputs to the quantized_model\n",
+    "    output = quantized_model(data)\n",
+    "    # calculate the batch loss\n",
+    "    loss = criterion(output, target)\n",
+    "    # update test loss\n",
+    "    test_loss += loss.item() * data.size(0)\n",
+    "    # convert output probabilities to predicted class\n",
+    "    _, pred = torch.max(output, 1)\n",
+    "    # compare predictions to true label\n",
+    "    correct_tensor = pred.eq(target.data.view_as(pred))\n",
+    "    correct = (\n",
+    "        np.squeeze(correct_tensor.numpy())\n",
+    "        if not train_on_gpu\n",
+    "        else np.squeeze(correct_tensor.cpu().numpy())\n",
+    "    )\n",
+    "    # calculate test accuracy for each object class\n",
+    "    for i in range(batch_size):\n",
+    "        label = target.data[i]\n",
+    "        class_correct_quantized[label] += correct[i].item()\n",
+    "        class_total_quantized[label] += 1\n",
+    "\n",
+    "# average test loss\n",
+    "test_loss = test_loss / len(test_loader)\n",
+    "print(\"Test Loss: {:.6f}\\n\".format(test_loss))\n",
+    "\n",
+    "for i in range(10):\n",
+    "    if class_total_quantized[i] > 0:\n",
+    "        print(\n",
+    "            \"Test Accuracy of %5s: %2d%% (%2d/%2d)\"\n",
+    "            % (\n",
+    "                classes[i],\n",
+    "                100 * class_correct_quantized[i] / class_total_quantized[i],\n",
+    "                np.sum(class_correct_quantized[i]),\n",
+    "                np.sum(class_total_quantized[i]),\n",
+    "            )\n",
+    "        )\n",
+    "    else:\n",
+    "        print(\"Test Accuracy of %5s: N/A (no training examples)\" % (classes[i]))\n",
+    "\n",
+    "print(\n",
+    "    \"\\nTest Accuracy (Overall): %2d%% (%2d/%2d)\"\n",
+    "    % (\n",
+    "        100.0 * np.sum(class_correct_quantized) / np.sum(class_total_quantized),\n",
+    "        np.sum(class_correct_quantized),\n",
+    "        np.sum(class_total_quantized),\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "class_correct = [728.0, 836.0, 637.0, 617.0, 635.0, 562.0, 664.0, 767.0, 876.0, 743.0]\n",
+      "class_total = [1000.0, 1000.0, 1000.0, 1000.0, 1000.0, 1000.0, 1000.0, 1000.0, 1000.0, 1000.0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(f'class_correct = {class_correct}')\n",
+    "print(f'class_total = {class_total}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_accuracy_classes = [c_correct/c_total for (c_correct, c_total) in zip(class_correct, class_total)]\n",
+    "test_accuracy_classes_quantized = [c_correct/c_total for (c_correct, c_total) in zip(class_correct_quantized, class_total_quantized)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[0.728, 0.836, 0.637, 0.617, 0.635, 0.562, 0.664, 0.767, 0.876, 0.743]"
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_accuracy_classes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<BarContainer object of 10 artists>"
+      ]
+     },
+     "execution_count": 46,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.bar([i for i in range(1,11)], test_accuracy_classes, color='blue', edgecolor='black')"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "a0a34b90",
@@ -521,10 +1301,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 65,
    "id": "b4d13080",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/hacklexander/.local/lib/python3.10/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",
+      "/home/hacklexander/.local/lib/python3.10/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=ResNet50_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet50_Weights.DEFAULT` to get the most up-to-date weights.\n",
+      "  warnings.warn(msg)\n",
+      "Downloading: \"https://download.pytorch.org/models/resnet50-0676ba61.pth\" to /home/hacklexander/.cache/torch/hub/checkpoints/resnet50-0676ba61.pth\n",
+      "100.0%"
+     ]
+    }
+   ],
    "source": [
     "import json\n",
     "from PIL import Image\n",
@@ -586,6 +1379,36 @@
     "    \n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "model:  fp32  \t Size (KB): 2365.954\n",
+      "model:  int8  \t Size (KB): 2365.954\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "2365954"
+      ]
+     },
+     "execution_count": 66,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "print_size_of_model(model, \"fp32\")\n",
+    "quantized_resnet50 = torch.quantization.quantize_dynamic(model, dtype=torch.qint8)\n",
+    "print_size_of_model(quantized_resnet50, \"int8\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "5d57da4b",
@@ -604,10 +1427,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 68,
    "id": "be2d31f5",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "import os\n",
     "\n",
@@ -642,7 +1476,7 @@
     "    ),\n",
     "}\n",
     "\n",
-    "data_dir = \"hymenoptera_data\"\n",
+    "data_dir = \"hymenoptera_data/hymenoptera_data\"\n",
     "# Create train and validation datasets and loaders\n",
     "image_datasets = {\n",
     "    x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])\n",
@@ -682,8 +1516,7 @@
     "# Make a grid from batch\n",
     "out = torchvision.utils.make_grid(inputs)\n",
     "\n",
-    "imshow(out, title=[class_names[x] for x in classes])\n",
-    "\n"
+    "imshow(out, title=[class_names[x] for x in classes])"
    ]
   },
   {
@@ -696,10 +1529,102 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 70,
    "id": "572d824c",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/hacklexander/.local/lib/python3.10/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",
+      "/home/hacklexander/.local/lib/python3.10/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 /home/hacklexander/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth\n",
+      "0.1%"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100.0%\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "----------\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/hacklexander/.local/lib/python3.10/site-packages/torch/optim/lr_scheduler.py:136: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order: `optimizer.step()` before `lr_scheduler.step()`.  Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate\n",
+      "  warnings.warn(\"Detected call of `lr_scheduler.step()` before `optimizer.step()`. \"\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "train Loss: 0.6541 Acc: 0.6066\n",
+      "val Loss: 0.3065 Acc: 0.8497\n",
+      "\n",
+      "Epoch 2/10\n",
+      "----------\n",
+      "train Loss: 0.4837 Acc: 0.7910\n",
+      "val Loss: 0.1637 Acc: 0.9477\n",
+      "\n",
+      "Epoch 3/10\n",
+      "----------\n",
+      "train Loss: 0.4998 Acc: 0.7541\n",
+      "val Loss: 0.1664 Acc: 0.9477\n",
+      "\n",
+      "Epoch 4/10\n",
+      "----------\n",
+      "train Loss: 0.3661 Acc: 0.8156\n",
+      "val Loss: 0.4234 Acc: 0.8497\n",
+      "\n",
+      "Epoch 5/10\n",
+      "----------\n",
+      "train Loss: 0.3994 Acc: 0.8197\n",
+      "val Loss: 0.1507 Acc: 0.9542\n",
+      "\n",
+      "Epoch 6/10\n",
+      "----------\n",
+      "train Loss: 0.7117 Acc: 0.7254\n",
+      "val Loss: 0.2423 Acc: 0.9216\n",
+      "\n",
+      "Epoch 7/10\n",
+      "----------\n",
+      "train Loss: 0.2918 Acc: 0.8730\n",
+      "val Loss: 0.1659 Acc: 0.9542\n",
+      "\n",
+      "Epoch 8/10\n",
+      "----------\n",
+      "train Loss: 0.4188 Acc: 0.8156\n",
+      "val Loss: 0.1598 Acc: 0.9477\n",
+      "\n",
+      "Epoch 9/10\n",
+      "----------\n",
+      "train Loss: 0.3808 Acc: 0.8484\n",
+      "val Loss: 0.1795 Acc: 0.9412\n",
+      "\n",
+      "Epoch 10/10\n",
+      "----------\n",
+      "train Loss: 0.4709 Acc: 0.7869\n",
+      "val Loss: 0.1637 Acc: 0.9477\n",
+      "\n",
+      "Training complete in 0m 5s\n",
+      "Best val Acc: 0.954248\n"
+     ]
+    }
+   ],
    "source": [
     "import copy\n",
     "import os\n",
@@ -739,7 +1664,7 @@
     "    ),\n",
     "}\n",
     "\n",
-    "data_dir = \"hymenoptera_data\"\n",
+    "data_dir = \"hymenoptera_data/hymenoptera_data/\"\n",
     "# Create train and validation datasets and loaders\n",
     "image_datasets = {\n",
     "    x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])\n",
@@ -878,7 +1803,7 @@
     "exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)\n",
     "model, epoch_time = train_model(\n",
     "    model, criterion, optimizer_conv, exp_lr_scheduler, num_epochs=10\n",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -897,6 +1822,20 @@
     "Apply ther quantization (post and quantization aware) and evaluate impact on model size and accuracy."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Modification of eval_model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "id": "04a263f0",
@@ -926,7 +1865,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.8.5 ('base')",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -940,7 +1879,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {