diff --git a/TD2 Deep Learning.ipynb b/TD2 Deep Learning.ipynb
index 2ecfce959ae6b947b633a758433f9bea0bf6992e..c44f4238382f4d2f376166cea5b44e23680912d8 100644
--- a/TD2 Deep Learning.ipynb	
+++ b/TD2 Deep Learning.ipynb	
@@ -33,10 +33,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "330a42f5",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: torch in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (2.1.1+cu118)\n",
+      "Requirement already satisfied: torchvision in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (0.16.1+cu118)\n",
+      "Requirement already satisfied: filelock in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from torch) (3.9.0)\n",
+      "Requirement already satisfied: typing-extensions in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from torch) (4.8.0)\n",
+      "Requirement already satisfied: sympy in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from torch) (1.12)\n",
+      "Requirement already satisfied: networkx in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from torch) (3.0)\n",
+      "Requirement already satisfied: jinja2 in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from torch) (3.1.2)\n",
+      "Requirement already satisfied: fsspec in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from torch) (2023.4.0)\n",
+      "Requirement already satisfied: numpy in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from torchvision) (1.26.2)\n",
+      "Requirement already satisfied: requests in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from torchvision) (2.28.1)\n",
+      "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from torchvision) (10.1.0)\n",
+      "Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from jinja2->torch) (2.1.3)\n",
+      "Requirement already satisfied: charset-normalizer<3,>=2 in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from requests->torchvision) (2.1.1)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from requests->torchvision) (3.4)\n",
+      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from requests->torchvision) (1.26.13)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from requests->torchvision) (2022.12.7)\n",
+      "Requirement already satisfied: mpmath>=0.19 in c:\\users\\lenovo\\anaconda3\\envs\\new\\lib\\site-packages (from sympy->torch) (1.3.0)\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
     "%pip install torch torchvision"
    ]
@@ -52,10 +77,72 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "id": "b1950f0a",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tensor([[ 0.6005, -0.8262, -1.1444,  1.8317,  0.2427,  1.2135,  0.5529,  0.3090,\n",
+      "          0.1768, -0.0671],\n",
+      "        [ 1.5132,  0.6618,  1.2110,  1.8297, -0.4285, -0.4998,  0.4473, -0.2253,\n",
+      "          1.4177, -0.0405],\n",
+      "        [-0.0883,  0.6764,  0.3432, -1.2304,  2.6615,  1.1792,  1.4577,  1.5665,\n",
+      "         -1.7107, -0.2310],\n",
+      "        [-1.2376,  0.3868,  0.4568, -1.3576,  1.7694,  1.4209,  2.0126, -0.2384,\n",
+      "         -0.9737, -0.5757],\n",
+      "        [ 0.1787, -0.5972,  0.9511,  0.0971,  0.0702,  0.6209, -0.5282,  0.1848,\n",
+      "         -0.4190,  3.4575],\n",
+      "        [ 0.3149,  2.1750, -1.6734, -0.0107, -0.2639,  0.3729, -0.3992,  1.0509,\n",
+      "         -0.1983, -0.5388],\n",
+      "        [-0.4991, -0.0539,  1.3420,  1.1376,  1.0812, -0.9487,  0.2711, -0.1039,\n",
+      "          0.6608,  0.1926],\n",
+      "        [-0.8309,  0.3424,  0.7537,  1.1209, -0.6249,  0.9049,  0.0279, -0.9683,\n",
+      "          1.5207,  1.3997],\n",
+      "        [-0.8293, -0.9169, -0.8743,  1.1780, -0.6684,  1.0099, -0.9231, -0.9749,\n",
+      "          0.6912, -0.9500],\n",
+      "        [ 0.4564,  0.5852,  1.0717, -0.9455, -0.6503,  1.3128,  0.3559,  0.1450,\n",
+      "          0.0160,  1.7602],\n",
+      "        [-1.3473, -0.6786,  0.2884,  1.3234,  0.6250, -0.0373,  0.5641,  0.5425,\n",
+      "          1.3457,  2.0471],\n",
+      "        [ 0.7055,  0.2446,  2.1138,  0.1851, -1.1334, -1.0468,  1.2929,  0.5373,\n",
+      "          0.9560,  0.1556],\n",
+      "        [-0.6760,  1.7166,  0.8109, -0.9636, -0.9815, -0.4989,  0.1184, -0.7103,\n",
+      "          0.3448,  0.4121],\n",
+      "        [ 0.6817, -1.2063,  0.8555, -0.7569, -1.3178, -0.9650, -1.0587,  1.2064,\n",
+      "         -0.0845,  0.6830]])\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",
@@ -95,10 +182,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "6e18f2fd",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CUDA is available!  Training on GPU ...\n"
+     ]
+    }
+   ],
    "source": [
     "import torch\n",
     "\n",
@@ -121,10 +216,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "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",
@@ -193,10 +297,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "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",
@@ -242,10 +361,58 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "id": "4b53f229",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 0 \tTraining Loss: 43.400863 \tValidation Loss: 38.021109\n",
+      "Validation loss decreased (inf --> 38.021109).  Saving model ...\n",
+      "Epoch: 1 \tTraining Loss: 35.353367 \tValidation Loss: 32.136121\n",
+      "Validation loss decreased (38.021109 --> 32.136121).  Saving model ...\n",
+      "Epoch: 2 \tTraining Loss: 30.913728 \tValidation Loss: 29.369840\n",
+      "Validation loss decreased (32.136121 --> 29.369840).  Saving model ...\n",
+      "Epoch: 3 \tTraining Loss: 28.601452 \tValidation Loss: 27.490179\n",
+      "Validation loss decreased (29.369840 --> 27.490179).  Saving model ...\n",
+      "Epoch: 4 \tTraining Loss: 26.915667 \tValidation Loss: 26.303214\n",
+      "Validation loss decreased (27.490179 --> 26.303214).  Saving model ...\n",
+      "Epoch: 5 \tTraining Loss: 25.459954 \tValidation Loss: 25.887691\n",
+      "Validation loss decreased (26.303214 --> 25.887691).  Saving model ...\n",
+      "Epoch: 6 \tTraining Loss: 24.229395 \tValidation Loss: 24.873652\n",
+      "Validation loss decreased (25.887691 --> 24.873652).  Saving model ...\n",
+      "Epoch: 7 \tTraining Loss: 23.164625 \tValidation Loss: 23.284470\n",
+      "Validation loss decreased (24.873652 --> 23.284470).  Saving model ...\n",
+      "Epoch: 8 \tTraining Loss: 22.206993 \tValidation Loss: 23.291942\n",
+      "Epoch: 9 \tTraining Loss: 21.421621 \tValidation Loss: 23.335741\n",
+      "Epoch: 10 \tTraining Loss: 20.651834 \tValidation Loss: 22.401363\n",
+      "Validation loss decreased (23.284470 --> 22.401363).  Saving model ...\n",
+      "Epoch: 11 \tTraining Loss: 19.985618 \tValidation Loss: 24.326989\n",
+      "Epoch: 12 \tTraining Loss: 19.291143 \tValidation Loss: 21.739429\n",
+      "Validation loss decreased (22.401363 --> 21.739429).  Saving model ...\n",
+      "Epoch: 13 \tTraining Loss: 18.624268 \tValidation Loss: 21.852032\n",
+      "Epoch: 14 \tTraining Loss: 17.965765 \tValidation Loss: 21.446357\n",
+      "Validation loss decreased (21.739429 --> 21.446357).  Saving model ...\n",
+      "Epoch: 15 \tTraining Loss: 17.394854 \tValidation Loss: 22.545597\n",
+      "Epoch: 16 \tTraining Loss: 16.794884 \tValidation Loss: 22.042855\n",
+      "Epoch: 17 \tTraining Loss: 16.227497 \tValidation Loss: 22.688590\n",
+      "Epoch: 18 \tTraining Loss: 15.704653 \tValidation Loss: 22.186874\n",
+      "Epoch: 19 \tTraining Loss: 15.155005 \tValidation Loss: 22.500867\n",
+      "Epoch: 20 \tTraining Loss: 14.652102 \tValidation Loss: 22.332764\n",
+      "Epoch: 21 \tTraining Loss: 14.156440 \tValidation Loss: 22.655204\n",
+      "Epoch: 22 \tTraining Loss: 13.740071 \tValidation Loss: 22.890621\n",
+      "Epoch: 23 \tTraining Loss: 13.230510 \tValidation Loss: 23.827616\n",
+      "Epoch: 24 \tTraining Loss: 12.847678 \tValidation Loss: 23.486764\n",
+      "Epoch: 25 \tTraining Loss: 12.306719 \tValidation Loss: 24.269633\n",
+      "Epoch: 26 \tTraining Loss: 11.897007 \tValidation Loss: 24.318152\n",
+      "Epoch: 27 \tTraining Loss: 11.547802 \tValidation Loss: 24.906728\n",
+      "Epoch: 28 \tTraining Loss: 11.044322 \tValidation Loss: 25.903962\n",
+      "Epoch: 29 \tTraining Loss: 10.720178 \tValidation Loss: 25.918305\n"
+     ]
+    }
+   ],
    "source": [
     "import torch.optim as optim\n",
     "\n",
@@ -253,7 +420,8 @@
     "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",
+    "train_loss_list = []  # list to store training loss to visualize\n",
+    "valid_loss_list = []    # list to store validation loss to visualize\n",
     "valid_loss_min = np.Inf  # track change in validation loss\n",
     "\n",
     "for epoch in range(n_epochs):\n",
@@ -297,6 +465,7 @@
     "    train_loss = train_loss / len(train_loader)\n",
     "    valid_loss = valid_loss / len(valid_loader)\n",
     "    train_loss_list.append(train_loss)\n",
+    "    valid_loss_list.append(valid_loss) # I added this list to plot it later with the train loss\n",
     "\n",
     "    # Print training/validation statistics\n",
     "    print(\n",
@@ -324,16 +493,42 @@
     "Does overfit occur? If so, do an early stopping."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "---\n",
+    " Answer to the question: \n",
+    "During the training process, the model's parameters are adjusted to minimize the training loss.\n",
+    "If the model is trained for too many epochs, it may start fitting the noise in the training data, leading to a decrease in training loss but an increase in validation loss.\n",
+    "Overfitting is often identified when the training loss continues to decrease while the validation loss starts to increase, indicating that the model is becoming too specialized for the training data. \n",
+    "To adress overfitting, we perform an early stopping when the validation loss starts to increase. \n",
+    "---\n"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "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",
+    "\n",
+    "plt.plot(range(n_epochs), train_loss_list, label='training loss')\n",
+    "plt.plot(range(n_epochs),valid_loss_list,label='validation loss')\n",
     "plt.xlabel(\"Epoch\")\n",
     "plt.ylabel(\"Loss\")\n",
     "plt.title(\"Performance of Model 1\")\n",
@@ -350,11 +545,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "id": "e93efdfc",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test Loss: 21.956040\n",
+      "\n",
+      "Test Accuracy of airplane: 67% (670/1000)\n",
+      "Test Accuracy of automobile: 78% (786/1000)\n",
+      "Test Accuracy of  bird: 57% (574/1000)\n",
+      "Test Accuracy of   cat: 46% (462/1000)\n",
+      "Test Accuracy of  deer: 54% (548/1000)\n",
+      "Test Accuracy of   dog: 46% (460/1000)\n",
+      "Test Accuracy of  frog: 73% (734/1000)\n",
+      "Test Accuracy of horse: 61% (615/1000)\n",
+      "Test Accuracy of  ship: 70% (703/1000)\n",
+      "Test Accuracy of truck: 64% (641/1000)\n",
+      "\n",
+      "Test Accuracy (Overall): 61% (6193/10000)\n"
+     ]
+    }
+   ],
    "source": [
+    "\n",
+    "\n",
     "model.load_state_dict(torch.load(\"./model_cifar.pt\"))\n",
     "\n",
     "# track test loss\n",
@@ -436,176 +654,1110 @@
   },
   {
    "cell_type": "markdown",
-   "id": "bc381cf4",
    "metadata": {},
    "source": [
-    "## Exercise 2: Quantization: try to compress the CNN to save space\n",
-    "\n",
-    "Quantization doc is available from https://pytorch.org/docs/stable/quantization.html#torch.quantization.quantize_dynamic\n",
-    "        \n",
-    "The Exercise is to quantize post training the above CNN model. Compare the size reduction and the impact on the classification accuracy \n",
-    "\n",
-    "\n",
-    "The size of the model is simply the size of the file."
+    "---\n",
+    "Here is the new network\n",
+    "---"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "ef623c26",
+   "execution_count": 11,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Net2(\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=512, bias=True)\n",
+      "  (fc2): Linear(in_features=512, out_features=64, bias=True)\n",
+      "  (fc3): Linear(in_features=64, out_features=10, bias=True)\n",
+      "  (dropout): Dropout(p=0.5, inplace=False)\n",
+      ")\n"
+     ]
+    }
+   ],
    "source": [
-    "import os\n",
+    "# define a new CNN architecture\n",
+    "\n",
+    "class Net2(nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super(Net2, self).__init__()\n",
+    "        # Convolutional Layers\n",
+    "        self.conv1 = nn.Conv2d(3, 16,3, padding=1)\n",
+    "        self.conv2 = nn.Conv2d(16,32, 3,padding=1)\n",
+    "        self.conv3 = nn.Conv2d(32,64,3,padding=1)\n",
     "\n",
+    "        #MaxPool Layer\n",
+    "        self.pool = nn.MaxPool2d(2,2)\n",
     "\n",
-    "def print_size_of_model(model, label=\"\"):\n",
-    "    torch.save(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",
+    "        #Fully connected Layer\n",
+    "        self.fc1 = nn.Linear(64 * 4 * 4, 512)\n",
+    "        self.fc2 = nn.Linear(512, 64)\n",
+    "        self.fc3 = nn.Linear(64, 10)\n",
     "\n",
+    "        #DropOut Layer\n",
+    "        self.dropout = nn.Dropout(0.5)\n",
     "\n",
-    "print_size_of_model(model, \"fp32\")"
+    "    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",
+    "        x = F.relu(self.fc1(x))\n",
+    "        x = self.dropout(x)\n",
+    "        x = F.relu(self.fc2(x))\n",
+    "        x = self.dropout(x)\n",
+    "        x = self.fc3(x)\n",
+    "        return x\n",
+    "\n",
+    "\n",
+    "# create a  CNN\n",
+    "model2 = Net2()\n",
+    "print(model2)\n",
+    "# move tensors to GPU if CUDA is available\n",
+    "if train_on_gpu:\n",
+    "    model2.cuda()"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "05c4e9ad",
    "metadata": {},
    "source": [
-    "Post training quantization example"
+    "---\n",
+    "Here we train the model2:\n",
+    "---"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "c4c65d4b",
+   "execution_count": 12,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch: 0 \tTraining Loss: 45.857789 \tValidation Loss: 44.560349\n",
+      "Validation loss decreased (inf --> 44.560349).  Saving model ...\n",
+      "Epoch: 1 \tTraining Loss: 41.778772 \tValidation Loss: 37.877069\n",
+      "Validation loss decreased (44.560349 --> 37.877069).  Saving model ...\n",
+      "Epoch: 2 \tTraining Loss: 37.083519 \tValidation Loss: 32.782693\n",
+      "Validation loss decreased (37.877069 --> 32.782693).  Saving model ...\n",
+      "Epoch: 3 \tTraining Loss: 33.402934 \tValidation Loss: 30.173893\n",
+      "Validation loss decreased (32.782693 --> 30.173893).  Saving model ...\n",
+      "Epoch: 4 \tTraining Loss: 31.229537 \tValidation Loss: 28.297551\n",
+      "Validation loss decreased (30.173893 --> 28.297551).  Saving model ...\n",
+      "Epoch: 5 \tTraining Loss: 29.413370 \tValidation Loss: 27.164286\n",
+      "Validation loss decreased (28.297551 --> 27.164286).  Saving model ...\n",
+      "Epoch: 6 \tTraining Loss: 27.889698 \tValidation Loss: 25.733314\n",
+      "Validation loss decreased (27.164286 --> 25.733314).  Saving model ...\n",
+      "Epoch: 7 \tTraining Loss: 26.490659 \tValidation Loss: 24.033053\n",
+      "Validation loss decreased (25.733314 --> 24.033053).  Saving model ...\n",
+      "Epoch: 8 \tTraining Loss: 25.185638 \tValidation Loss: 22.838416\n",
+      "Validation loss decreased (24.033053 --> 22.838416).  Saving model ...\n",
+      "Epoch: 9 \tTraining Loss: 23.968391 \tValidation Loss: 21.469535\n",
+      "Validation loss decreased (22.838416 --> 21.469535).  Saving model ...\n",
+      "Epoch: 10 \tTraining Loss: 22.870672 \tValidation Loss: 20.855845\n",
+      "Validation loss decreased (21.469535 --> 20.855845).  Saving model ...\n",
+      "Epoch: 11 \tTraining Loss: 21.748044 \tValidation Loss: 20.084015\n",
+      "Validation loss decreased (20.855845 --> 20.084015).  Saving model ...\n",
+      "Epoch: 12 \tTraining Loss: 20.823984 \tValidation Loss: 19.152056\n",
+      "Validation loss decreased (20.084015 --> 19.152056).  Saving model ...\n",
+      "Epoch: 13 \tTraining Loss: 19.860081 \tValidation Loss: 18.863754\n",
+      "Validation loss decreased (19.152056 --> 18.863754).  Saving model ...\n",
+      "Epoch: 14 \tTraining Loss: 19.011136 \tValidation Loss: 18.424995\n",
+      "Validation loss decreased (18.863754 --> 18.424995).  Saving model ...\n",
+      "Epoch: 15 \tTraining Loss: 18.079763 \tValidation Loss: 17.192690\n",
+      "Validation loss decreased (18.424995 --> 17.192690).  Saving model ...\n",
+      "Epoch: 16 \tTraining Loss: 17.376203 \tValidation Loss: 17.144983\n",
+      "Validation loss decreased (17.192690 --> 17.144983).  Saving model ...\n",
+      "Epoch: 17 \tTraining Loss: 16.608376 \tValidation Loss: 16.288037\n",
+      "Validation loss decreased (17.144983 --> 16.288037).  Saving model ...\n",
+      "Epoch: 18 \tTraining Loss: 15.988603 \tValidation Loss: 16.175762\n",
+      "Validation loss decreased (16.288037 --> 16.175762).  Saving model ...\n",
+      "Epoch: 19 \tTraining Loss: 15.412869 \tValidation Loss: 15.441982\n",
+      "Validation loss decreased (16.175762 --> 15.441982).  Saving model ...\n",
+      "Epoch: 20 \tTraining Loss: 14.778294 \tValidation Loss: 15.939022\n",
+      "Epoch: 21 \tTraining Loss: 14.146509 \tValidation Loss: 15.906133\n",
+      "Epoch: 22 \tTraining Loss: 13.569586 \tValidation Loss: 15.517570\n",
+      "Epoch: 23 \tTraining Loss: 13.081360 \tValidation Loss: 16.112445\n",
+      "Epoch: 24 \tTraining Loss: 12.587562 \tValidation Loss: 15.454825\n",
+      "Epoch: 25 \tTraining Loss: 12.073642 \tValidation Loss: 15.664324\n",
+      "Epoch: 26 \tTraining Loss: 11.623898 \tValidation Loss: 15.579594\n",
+      "Epoch: 27 \tTraining Loss: 11.123427 \tValidation Loss: 15.694448\n",
+      "Epoch: 28 \tTraining Loss: 10.639247 \tValidation Loss: 15.685701\n",
+      "Epoch: 29 \tTraining Loss: 10.170218 \tValidation Loss: 16.205130\n"
+     ]
+    }
+   ],
    "source": [
-    "import torch.quantization\n",
     "\n",
+    "criterion = nn.CrossEntropyLoss()  # specify loss function\n",
+    "optimizer = optim.SGD(model2.parameters(), lr=0.01)  # specify optimizer\n",
     "\n",
-    "quantized_model = torch.quantization.quantize_dynamic(model, dtype=torch.qint8)\n",
-    "print_size_of_model(quantized_model, \"int8\")"
+    "n_epochs = 30  # number of epochs to train the model\n",
+    "train_loss_list = []  # list to store loss to visualize\n",
+    "valid_loss_list = []\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 model\n",
+    "    model2.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 model\n",
+    "        output = model2(data)\n",
+    "        \n",
+    "        \n",
+    "        # Calculate the batch loss\n",
+    "        loss = criterion(output, target)\n",
+    "        # Backward pass: compute gradient of the loss with respect to 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 model\n",
+    "    model2.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 model\n",
+    "        output = model2(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",
+    "    valid_loss_list.append(valid_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(model2.state_dict(), \"model_cifar.pt\")\n",
+    "        valid_loss_min = valid_loss"
    ]
   },
   {
-   "cell_type": "markdown",
-   "id": "7b108e17",
+   "cell_type": "code",
+   "execution_count": 13,
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
-    "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."
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "plt.plot(range(n_epochs), train_loss_list,label=\"training loss\")\n",
+    "plt.plot(range(n_epochs),valid_loss_list,label=\"validation loss\")\n",
+    "\n",
+    "plt.xlabel(\"Epoch\")\n",
+    "plt.ylabel(\"Loss\")\n",
+    "plt.legend()\n",
+    "plt.title(\"Performance of Model 2\")\n",
+    "plt.show()"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "a0a34b90",
    "metadata": {},
    "source": [
-    "Try training aware quantization to mitigate the impact on the accuracy (doc available here https://pytorch.org/docs/stable/quantization.html#torch.quantization.quantize_dynamic)"
+    "----\n",
+    "We note that validation voss are less than the first model. lets see the accuracy on the test data now:\n",
+    "\n",
+    "---"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "201470f9",
    "metadata": {},
    "source": [
-    "## Exercise 3: working with pre-trained models.\n",
-    "\n",
-    "PyTorch offers several pre-trained models https://pytorch.org/vision/0.8/models.html        \n",
-    "We will use ResNet50 trained on ImageNet dataset (https://www.image-net.org/index.php). Use the following code with the files `imagenet-simple-labels.json` that contains the imagenet labels and the image dog.png that we will use as test.\n"
+    "Here we apply the model with the lowest validation loss value:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "b4d13080",
+   "execution_count": 14,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test Loss: 16.039122\n",
+      "\n",
+      "Test Accuracy of airplane: 79% (799/1000)\n",
+      "Test Accuracy of automobile: 82% (820/1000)\n",
+      "Test Accuracy of  bird: 58% (584/1000)\n",
+      "Test Accuracy of   cat: 55% (552/1000)\n",
+      "Test Accuracy of  deer: 72% (723/1000)\n",
+      "Test Accuracy of   dog: 55% (551/1000)\n",
+      "Test Accuracy of  frog: 80% (807/1000)\n",
+      "Test Accuracy of horse: 76% (766/1000)\n",
+      "Test Accuracy of  ship: 86% (862/1000)\n",
+      "Test Accuracy of truck: 79% (790/1000)\n",
+      "\n",
+      "Test Accuracy (Overall): 72% (7254/10000)\n"
+     ]
+    }
+   ],
    "source": [
-    "import json\n",
-    "from PIL import Image\n",
-    "\n",
-    "# Choose an image to pass through the model\n",
-    "test_image = \"dog.png\"\n",
-    "\n",
-    "# Configure matplotlib for pretty inline plots\n",
-    "#%matplotlib inline\n",
-    "#%config InlineBackend.figure_format = 'retina'\n",
-    "\n",
-    "# Prepare the labels\n",
-    "with open(\"imagenet-simple-labels.json\") as f:\n",
-    "    labels = json.load(f)\n",
+    "model2.load_state_dict(torch.load(\"./model_cifar.pt\"))\n",
     "\n",
-    "# First prepare the transformations: resize the image to what the model was trained on and convert it to a tensor\n",
-    "data_transform = transforms.Compose(\n",
-    "    [\n",
-    "        transforms.Resize((224, 224)),\n",
-    "        transforms.ToTensor(),\n",
-    "        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),\n",
-    "    ]\n",
-    ")\n",
-    "# Load the image\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",
-    "image = Image.open(test_image)\n",
-    "plt.imshow(image), plt.xticks([]), plt.yticks([])\n",
+    "model2.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 model\n",
+    "    output = model2(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",
-    "# Now apply the transformation, expand the batch dimension, and send the image to the GPU\n",
-    "# image = data_transform(image).unsqueeze(0).cuda()\n",
-    "image = data_transform(image).unsqueeze(0)\n",
+    "# average test loss\n",
+    "test_loss = test_loss / len(test_loader)\n",
+    "print(\"Test Loss: {:.6f}\\n\".format(test_loss))\n",
     "\n",
-    "# Download the model if it's not there already. It will take a bit on the first run, after that it's fast\n",
-    "model = models.resnet50(pretrained=True)\n",
-    "# Send the model to the GPU\n",
-    "# model.cuda()\n",
-    "# Set layers such as dropout and batchnorm in evaluation mode\n",
-    "model.eval()\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",
-    "# Get the 1000-dimensional model output\n",
-    "out = model(image)\n",
-    "# Find the predicted class\n",
-    "print(\"Predicted class is: {}\".format(labels[out.argmax()]))"
+    "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",
-   "id": "184cfceb",
    "metadata": {},
    "source": [
-    "Experiments:\n",
-    "\n",
-    "Study the code and the results obtained. Possibly add other images downloaded from the internet.\n",
-    "\n",
-    "What is the size of the model? Quantize it and then check if the model is still able to correctly classify the other images.\n",
-    "\n",
-    "Experiment with other pre-trained CNN models.\n",
+    "---\n",
+    " Models comparaison: During the training, it's noticibale that the validation loss values are less than the one in the first model. It gives a first idea that the second model is performing better than the first one. This is confirmed by the test accuracy of model2 which is 73%, higher than the one of model1, 61%. So, the addes layer to the cnn net and the other modifications improved the accuracy of the classification.\n",
     "\n",
-    "    \n"
+    "---"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "5d57da4b",
+   "id": "bc381cf4",
    "metadata": {},
    "source": [
-    "## Exercise 4: Transfer Learning\n",
-    "    \n",
-    "    \n",
-    "For this work, we will use a pre-trained model (ResNet18) as a descriptor extractor and will refine the classification by training only the last fully connected layer of the network. Thus, the output layer of the pre-trained network will be replaced by a layer adapted to the new classes to be recognized which will be in our case ants and bees.\n",
-    "Download and unzip in your working directory the dataset available at the address :\n",
-    "    \n",
-    "https://download.pytorch.org/tutorial/hymenoptera_data.zip\n",
-    "    \n",
-    "Execute the following code in order to display some images of the dataset."
+    "## Exercise 2: Quantization: try to compress the CNN to save space\n",
+    "\n",
+    "Quantization doc is available from https://pytorch.org/docs/stable/quantization.html#torch.quantization.quantize_dynamic\n",
+    "        \n",
+    "The Exercise is to quantize post training the above CNN model. Compare the size reduction and the impact on the classification accuracy \n",
+    "\n",
+    "\n",
+    "The size of the model is simply the size of the file."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "be2d31f5",
+   "execution_count": 15,
+   "id": "ef623c26",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "model:  fp32  \t Size (KB): 251.342\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "251342"
+      ]
+     },
+     "execution_count": 15,
+     "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",
+    "    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\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "05c4e9ad",
+   "metadata": {},
+   "source": [
+    "Post training quantization example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "c4c65d4b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "model:  int8  \t Size (KB): 76.65\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "76650"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import torch.quantization\n",
+    "\n",
+    "\n",
+    "quantized_model = torch.quantization.quantize_dynamic(model, dtype=torch.qint8)\n",
+    "print_size_of_model(quantized_model, \"int8\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7b108e17",
+   "metadata": {},
+   "source": [
+    "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": "code",
+   "execution_count": 18,
+   "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[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNotImplementedError\u001b[0m                       Traceback (most recent call last)",
+      "\u001b[1;32mc:\\Users\\LENOVO\\Desktop\\deeplearning\\td-2-deep-learning\\TD2 Deep Learning.ipynb Cell 36\u001b[0m line \u001b[0;36m1\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X50sZmlsZQ%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[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X50sZmlsZQ%3D%3D?line=11'>12</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:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X50sZmlsZQ%3D%3D?line=12'>13</a>\u001b[0m output \u001b[39m=\u001b[39m quantized_model(data)\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X50sZmlsZQ%3D%3D?line=13'>14</a>\u001b[0m \u001b[39m# calculate the batch loss\u001b[39;00m\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X50sZmlsZQ%3D%3D?line=14'>15</a>\u001b[0m loss \u001b[39m=\u001b[39m criterion(output, target)\n",
+      "File \u001b[1;32mc:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\nn\\modules\\module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;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[0;32m   1517\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m-> 1518\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_call_impl(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n",
+      "File \u001b[1;32mc:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\nn\\modules\\module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;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[0;32m   1523\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[0;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[0;32m   1525\u001b[0m         \u001b[39mor\u001b[39;00m _global_backward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1526\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1527\u001b[0m     \u001b[39mreturn\u001b[39;00m forward_call(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n\u001b[0;32m   1529\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m   1530\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n",
+      "\u001b[1;32mc:\\Users\\LENOVO\\Desktop\\deeplearning\\td-2-deep-learning\\TD2 Deep Learning.ipynb Cell 36\u001b[0m line \u001b[0;36m2\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X50sZmlsZQ%3D%3D?line=18'>19</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[39mconv2(x)))\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X50sZmlsZQ%3D%3D?line=19'>20</a>\u001b[0m x \u001b[39m=\u001b[39m x\u001b[39m.\u001b[39mview(\u001b[39m-\u001b[39m\u001b[39m1\u001b[39m, \u001b[39m16\u001b[39m \u001b[39m*\u001b[39m \u001b[39m5\u001b[39m \u001b[39m*\u001b[39m \u001b[39m5\u001b[39m)\n\u001b[1;32m---> <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X50sZmlsZQ%3D%3D?line=20'>21</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[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X50sZmlsZQ%3D%3D?line=21'>22</a>\u001b[0m x \u001b[39m=\u001b[39m F\u001b[39m.\u001b[39mrelu(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mfc2(x))\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X50sZmlsZQ%3D%3D?line=22'>23</a>\u001b[0m x \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mfc3(x)\n",
+      "File \u001b[1;32mc:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\nn\\modules\\module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;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[0;32m   1517\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m-> 1518\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_call_impl(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n",
+      "File \u001b[1;32mc:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\nn\\modules\\module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;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[0;32m   1523\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[0;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[0;32m   1525\u001b[0m         \u001b[39mor\u001b[39;00m _global_backward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1526\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1527\u001b[0m     \u001b[39mreturn\u001b[39;00m forward_call(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n\u001b[0;32m   1529\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m   1530\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\ao\\nn\\quantized\\dynamic\\modules\\linear.py:54\u001b[0m, in \u001b[0;36mLinear.forward\u001b[1;34m(self, x)\u001b[0m\n\u001b[0;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[0;32m     52\u001b[0m             x, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_packed_params\u001b[39m.\u001b[39m_packed_params)\n\u001b[0;32m     53\u001b[0m     \u001b[39melse\u001b[39;00m:\n\u001b[1;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[0;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[0;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[0;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[0;32m     58\u001b[0m         x, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_packed_params\u001b[39m.\u001b[39m_packed_params)\n",
+      "File \u001b[1;32mc:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\_ops.py:692\u001b[0m, in \u001b[0;36mOpOverloadPacket.__call__\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;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[0;32m    688\u001b[0m     \u001b[39m# overloading __call__ to ensure torch.ops.foo.bar()\u001b[39;00m\n\u001b[0;32m    689\u001b[0m     \u001b[39m# is still callable from JIT\u001b[39;00m\n\u001b[0;32m    690\u001b[0m     \u001b[39m# We save the function ptr as the `op` attribute on\u001b[39;00m\n\u001b[0;32m    691\u001b[0m     \u001b[39m# OpOverloadPacket to access it here.\u001b[39;00m\n\u001b[1;32m--> 692\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_op(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs \u001b[39mor\u001b[39;00m {})\n",
+      "\u001b[1;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": [
+    "\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",
+    "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 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[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": [
+    "---\n",
+    "comments here\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a0a34b90",
+   "metadata": {},
+   "source": [
+    "Try training aware quantization to mitigate the impact on the accuracy (doc available here https://pytorch.org/docs/stable/quantization.html#torch.quantization.quantize_dynamic)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class NetAwareQuantized(nn.Module):\n",
+    "\n",
+    "    def __init__(self):\n",
+    "\n",
+    "        super(NetAwareQuantized, self).__init__()\n",
+    "        #Same architecture as the previous model \n",
+    "        # Convolutional Layers\n",
+    "        self.conv1 = nn.Conv2d(3, 16,3, padding=1)\n",
+    "        self.conv2 = nn.Conv2d(16,32, 3,padding=1)\n",
+    "        self.conv3 = nn.Conv2d(32,64,3,padding=1)\n",
+    "\n",
+    "        #MaxPool Layer\n",
+    "        self.pool = nn.MaxPool2d(2,2)\n",
+    "\n",
+    "        #Fully connected Layer\n",
+    "        self.fc1 = nn.Linear(64 * 4 * 4, 512)\n",
+    "        self.fc2 = nn.Linear(512, 64)\n",
+    "        self.fc3 = nn.Linear(64, 10)\n",
+    "\n",
+    "        #DropOut Layer\n",
+    "        self.dropout = nn.Dropout(0.5)\n",
+    "\n",
+    "\n",
+    "        #adding the quant and dequant \n",
+    "        #QuantStub converts tensors from floating point to quantized\n",
+    "        self.quant = torch.quantization.QuantStub()\n",
+    "\n",
+    "        #DeQuantStub converts tensors from quantized to floating point\n",
+    "        self.dequant = torch.quantization.DeQuantStub()\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "\n",
+    "        x = self.quant(x)\n",
+    "\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",
+    "        x = x.view(-1, 64 * 4 * 4)\n",
+    "        x = F.relu(self.fc1(x))\n",
+    "        x = self.dropout(x) \n",
+    "        x = F.relu(self.fc2(x))\n",
+    "        x = self.dropout(x)\n",
+    "        x = self.fc3(x)\n",
+    "        x = self.dequant(x)\n",
+    "\n",
+    "        return x"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\ao\\quantization\\quantize.py:309: UserWarning: None of the submodule got qconfig applied. Make sure you passed correct configuration through `qconfig_dict` or by assigning the `.qconfig` attribute directly on submodules\n",
+      "  warnings.warn(\"None of the submodule got qconfig applied. Make sure you \"\n"
+     ]
+    },
+    {
+     "ename": "RuntimeError",
+     "evalue": "Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
+      "\u001b[1;32mc:\\Users\\LENOVO\\Desktop\\deeplearning\\td-2-deep-learning\\TD2 Deep Learning.ipynb Cell 40\u001b[0m line \u001b[0;36m3\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X54sZmlsZQ%3D%3D?line=28'>29</a>\u001b[0m optimizer\u001b[39m.\u001b[39mzero_grad()\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X54sZmlsZQ%3D%3D?line=29'>30</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:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X54sZmlsZQ%3D%3D?line=30'>31</a>\u001b[0m output \u001b[39m=\u001b[39m model_qat(data)\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X54sZmlsZQ%3D%3D?line=31'>32</a>\u001b[0m \u001b[39m# Calculate the batch loss\u001b[39;00m\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X54sZmlsZQ%3D%3D?line=32'>33</a>\u001b[0m loss \u001b[39m=\u001b[39m criterion(output, target)\n",
+      "File \u001b[1;32mc:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\nn\\modules\\module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;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[0;32m   1517\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m-> 1518\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_call_impl(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n",
+      "File \u001b[1;32mc:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\nn\\modules\\module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;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[0;32m   1523\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[0;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[0;32m   1525\u001b[0m         \u001b[39mor\u001b[39;00m _global_backward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1526\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1527\u001b[0m     \u001b[39mreturn\u001b[39;00m forward_call(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n\u001b[0;32m   1529\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m   1530\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n",
+      "\u001b[1;32mc:\\Users\\LENOVO\\Desktop\\deeplearning\\td-2-deep-learning\\TD2 Deep Learning.ipynb Cell 40\u001b[0m line \u001b[0;36m3\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X54sZmlsZQ%3D%3D?line=30'>31</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:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X54sZmlsZQ%3D%3D?line=32'>33</a>\u001b[0m     x \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mquant(x)\n\u001b[1;32m---> <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X54sZmlsZQ%3D%3D?line=34'>35</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;49mconv1(x)))\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X54sZmlsZQ%3D%3D?line=35'>36</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[39mconv2(x)))\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X54sZmlsZQ%3D%3D?line=36'>37</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",
+      "File \u001b[1;32mc:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\nn\\modules\\module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;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[0;32m   1517\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m-> 1518\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_call_impl(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n",
+      "File \u001b[1;32mc:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\nn\\modules\\module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;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[0;32m   1523\u001b[0m \u001b[39m# this function, and just call forward.\u001b[39;00m\n\u001b[0;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[0;32m   1525\u001b[0m         \u001b[39mor\u001b[39;00m _global_backward_pre_hooks \u001b[39mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1526\u001b[0m         \u001b[39mor\u001b[39;00m _global_forward_hooks \u001b[39mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1527\u001b[0m     \u001b[39mreturn\u001b[39;00m forward_call(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n\u001b[0;32m   1529\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m   1530\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\nn\\modules\\conv.py:460\u001b[0m, in \u001b[0;36mConv2d.forward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m    459\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--> 460\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:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\site-packages\\torch\\nn\\modules\\conv.py:456\u001b[0m, in \u001b[0;36mConv2d._conv_forward\u001b[1;34m(self, input, weight, bias)\u001b[0m\n\u001b[0;32m    452\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    453\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    454\u001b[0m                     weight, bias, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mstride,\n\u001b[0;32m    455\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--> 456\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    457\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;31mRuntimeError\u001b[0m: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same"
+     ]
+    }
+   ],
+   "source": [
+    "import copy\n",
+    "import torch.quantization.quantize_fx as quantize_fx\n",
+    "Aware_model=NetAwareQuantized()\n",
+    "\n",
+    "Aware_model.train()\n",
+    "model_to_quantize = copy.deepcopy(Aware_model)\n",
+    "model.qconfig = torch.quantization.get_default_qat_qconfig(\"qnnpack\")\n",
+    "model_qat = torch.quantization.prepare_qat(Aware_model, inplace=False)\n",
+    "\n",
+    "# quantization aware training\n",
+    "model_qat = torch.quantization.convert(model_qat.eval(), inplace=False)\n",
+    "n_epochs=30\n",
+    "train_loss_list = []  # list to store loss to visualize\n",
+    "valid_loss_list=[]\n",
+    "criterion = nn.CrossEntropyLoss()  # specify loss function\n",
+    "optimizer = optim.SGD(model_qat.parameters(), lr=0.01)  # specify optimizer\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 model\n",
+    "    model_qat.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 model\n",
+    "        output = model_qat(data)\n",
+    "        # Calculate the batch loss\n",
+    "        loss = criterion(output, target)\n",
+    "        # Backward pass: compute gradient of the loss with respect to 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 model\n",
+    "    model_qat.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 model\n",
+    "        output = model_qat(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",
+    "    valid_loss_list.append(valid_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",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "plt.plot(range(n_epochs), train_loss_list,label=\"training loss\")\n",
+    "plt.plot(range(n_epochs),valid_loss_list,label=\"validation loss\")\n",
+    "\n",
+    "plt.xlabel(\"Epoch\")\n",
+    "plt.ylabel(\"Loss\")\n",
+    "\n",
+    "plt.legend()\n",
+    "plt.title(\"Performance of the aware quantization Model \")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 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",
+    "Aware_model.eval()\n",
+    "# iterate over test data\n",
+    "for data, target in test_loader:\n",
+    "    \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 model\n",
+    "\n",
+    "    output = Aware_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",
+   "id": "201470f9",
+   "metadata": {},
+   "source": [
+    "## Exercise 3: working with pre-trained models.\n",
+    "\n",
+    "PyTorch offers several pre-trained models https://pytorch.org/vision/0.8/models.html        \n",
+    "We will use ResNet50 trained on ImageNet dataset (https://www.image-net.org/index.php). Use the following code with the files `imagenet-simple-labels.json` that contains the imagenet labels and the image dog.png that we will use as test.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Experiments:\n",
+    "\n",
+    "Study the code and the results obtained. Possibly add other images downloaded from the internet.\n",
+    "\n",
+    "What is the size of the model? Quantize it and then check if the model is still able to correctly classify the other images.\n",
+    "\n",
+    "Experiment with other pre-trained CNN models."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "b4d13080",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\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",
+      "c:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\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"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "test_photo is dog.png Predicted class is: Golden Retriever\n",
+      "test_photo is guinea_pig.jpg Predicted class is: guinea pig\n",
+      "test_photo is husky.jpeg Predicted class is: husky\n",
+      "test_photo is toilet_paper.png Predicted class is: paper towel\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import json\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "from torchvision import datasets, transforms, models\n",
+    "from PIL import Image\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "# Configure matplotlib for pretty inline plots\n",
+    "#%matplotlib inline\n",
+    "#%config InlineBackend.figure_format = 'retina'\n",
+    "\n",
+    "# Prepare the labels\n",
+    "with open(\"imagenet-simple-labels.json\") as f:\n",
+    "    labels = json.load(f)\n",
+    "\n",
+    "# First prepare the transformations: resize the image to what the model was trained on and convert it to a tensor\n",
+    "data_transform = transforms.Compose(\n",
+    "    [\n",
+    "        transforms.Resize((224, 224)),\n",
+    "        transforms.ToTensor(),\n",
+    "        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "\n",
+    "# Download the model if it's not there already. It will take a bit on the first run, after that it's fast\n",
+    "model = models.resnet50(pretrained=True)\n",
+    "# Send the model to the GPU\n",
+    "# model.cuda()\n",
+    "# Set layers such as dropout and batchnorm in evaluation mode\n",
+    "model.eval()\n",
+    "\n",
+    "\n",
+    "# Load the images\n",
+    "# a folder named images_test is created to add more photos from the internet\n",
+    "\n",
+    "test_photos=os.listdir('images_test')\n",
+    "for i in range(len(test_photos)):\n",
+    "\n",
+    "    image = Image.open('images_test/'+test_photos[i]).convert('RGB')\n",
+    "    plt.imshow(image), plt.xticks([]), plt.yticks([])\n",
+    "\n",
+    "    # Now apply the transformation, expand the batch dimension, and send the image to the GPU\n",
+    "    # image = data_transform(image).unsqueeze(0).cuda()\n",
+    "    image = data_transform(image).unsqueeze(0)\n",
+    "\n",
+    "    # Get the 1000-dimensional model output\n",
+    "    out = model(image)\n",
+    "    # Find the predicted class\n",
+    "    print(\"test_photo is\",test_photos[i],\"Predicted class is: {}\".format(labels[out.argmax()]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We traied the model with 4 photos from the internet and it worked perfectly"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "184cfceb",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "Size of the model is 102523.238 kb :\n",
+    "\n",
+    "---\n",
+    "\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "model:  fp32  \t Size (KB): 102523.238\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "102523238"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\n",
+    "print_size_of_model(model, \"fp32\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "Quantization of the model:\n",
+    "the size is lower as expected :))\n",
+    "size is decreased by 9%\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "model:  int8  \t Size (KB): 96379.996\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "96379996"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "quantizedModel = torch.quantization.quantize_dynamic(model, dtype=torch.qint8)\n",
+    "print_size_of_model(quantizedModel, \"int8\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\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",
+      "c:\\Users\\LENOVO\\anaconda3\\envs\\new\\lib\\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"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "test_photo is dog.png Predicted class is: Golden Retriever\n",
+      "test_photo is guinea_pig.jpg Predicted class is: guinea pig\n",
+      "test_photo is husky.jpeg Predicted class is: husky\n",
+      "test_photo is toilet_paper.png Predicted class is: paper towel\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "quantizedModel = models.resnet50(pretrained=True)\n",
+    "# Send the model to the GPU\n",
+    "# model.cuda()\n",
+    "# Set layers such as dropout and batchnorm in evaluation mode\n",
+    "quantizedModel.eval()\n",
+    "\n",
+    "\n",
+    "# Load the images\n",
+    "# a folder named images_test is created to add more photos from the internet\n",
+    "\n",
+    "test_photos=os.listdir('images_test')\n",
+    "for i in range(len(test_photos)):\n",
+    "\n",
+    "    image = Image.open('images_test/'+test_photos[i]).convert('RGB')\n",
+    "    plt.imshow(image), plt.xticks([]), plt.yticks([])\n",
+    "\n",
+    "    # Now apply the transformation, expand the batch dimension, and send the image to the GPU\n",
+    "    # image = data_transform(image).unsqueeze(0).cuda()\n",
+    "    image = data_transform(image).unsqueeze(0)\n",
+    "\n",
+    "    # Get the 1000-dimensional model output\n",
+    "    out = quantizedModel(image)\n",
+    "    # Find the predicted class\n",
+    "    print(\"test_photo is\",test_photos[i],\"Predicted class is: {}\".format(labels[out.argmax()]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "After Quantization, the model is still able to classify the images used for the test"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5d57da4b",
+   "metadata": {},
+   "source": [
+    "## Exercise 4: Transfer Learning\n",
+    "    \n",
+    "    \n",
+    "For this work, we will use a pre-trained model (ResNet18) as a descriptor extractor and will refine the classification by training only the last fully connected layer of the network. Thus, the output layer of the pre-trained network will be replaced by a layer adapted to the new classes to be recognized which will be in our case ants and bees.\n",
+    "Download and unzip in your working directory the dataset available at the address :\n",
+    "    \n",
+    "https://download.pytorch.org/tutorial/hymenoptera_data.zip\n",
+    "    \n",
+    "Execute the following code in order to display some images of the dataset."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "be2d31f5",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -696,10 +1848,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "572d824c",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'matplotlib'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "\u001b[1;32mc:\\Users\\LENOVO\\Desktop\\deeplearning\\td-2-deep-learning\\TD2 Deep Learning.ipynb Cell 49\u001b[0m line \u001b[0;36m5\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X66sZmlsZQ%3D%3D?line=1'>2</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mos\u001b[39;00m\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X66sZmlsZQ%3D%3D?line=2'>3</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mtime\u001b[39;00m\n\u001b[1;32m----> <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X66sZmlsZQ%3D%3D?line=4'>5</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mmatplotlib\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mpyplot\u001b[39;00m \u001b[39mas\u001b[39;00m \u001b[39mplt\u001b[39;00m\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X66sZmlsZQ%3D%3D?line=5'>6</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mnumpy\u001b[39;00m \u001b[39mas\u001b[39;00m \u001b[39mnp\u001b[39;00m\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/LENOVO/Desktop/deeplearning/td-2-deep-learning/TD2%20Deep%20Learning.ipynb#X66sZmlsZQ%3D%3D?line=6'>7</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mtorch\u001b[39;00m\n",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'matplotlib'"
+     ]
+    }
+   ],
    "source": [
     "import copy\n",
     "import os\n",
@@ -940,7 +2104,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.10.13"
   },
   "vscode": {
    "interpreter": {
diff --git a/dog.png b/images_test/dog.png
similarity index 100%
rename from dog.png
rename to images_test/dog.png
diff --git a/images_test/husky.jpeg b/images_test/husky.jpeg
new file mode 100644
index 0000000000000000000000000000000000000000..dddeed32b163343c766694bdec1d95d56f1d20cf
Binary files /dev/null and b/images_test/husky.jpeg differ
diff --git a/images_test/toilet_paper.png b/images_test/toilet_paper.png
new file mode 100644
index 0000000000000000000000000000000000000000..d9c4ddb3cb843df5e1a2d72014d0284c476a80eb
Binary files /dev/null and b/images_test/toilet_paper.png differ