diff --git a/TD2 Deep Learning.ipynb b/TD2 Deep Learning.ipynb
index 2785b6125fcf3e84a31de04a07f9bab9dfe0dc5d..59c2fe85e4b1d4a5e8d4bbc9f0e05628f0abbc1f 100644
--- a/TD2 Deep Learning.ipynb	
+++ b/TD2 Deep Learning.ipynb	
@@ -1862,12 +1862,35 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 44,
       "id": "be2d31f5",
       "metadata": {
-        "id": "be2d31f5"
+        "id": "be2d31f5",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 224
+        },
+        "outputId": "fd082646-66f5-49bb-f4be-af1c2ac28978"
       },
-      "outputs": [],
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Mounted at /content/drive\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ],
       "source": [
         "import os\n",
         "\n",
@@ -1876,7 +1899,7 @@
         "import torch\n",
         "import torchvision\n",
         "from torchvision import datasets, transforms\n",
-        "\n",
+        "from google.colab import drive\n",
         "# Data augmentation and normalization for training\n",
         "# Just normalization for validation\n",
         "data_transforms = {\n",
@@ -1902,7 +1925,8 @@
         "    ),\n",
         "}\n",
         "\n",
-        "data_dir = \"hymenoptera_data\"\n",
+        "drive.mount('/content/drive')\n",
+        "data_dir = \"drive/MyDrive/Colab Notebooks/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",
@@ -1958,12 +1982,120 @@
     },
     {
       "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "P52pG2XLK5B1"
+      },
+      "id": "P52pG2XLK5B1",
       "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 46,
       "id": "572d824c",
       "metadata": {
-        "id": "572d824c"
+        "id": "572d824c",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "6d177b1a-4f55-41eb-dd99-7d799be0d844"
       },
-      "outputs": [],
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py:557: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
+            "  warnings.warn(_create_warning_msg(\n",
+            "/usr/local/lib/python3.10/dist-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",
+            "/usr/local/lib/python3.10/dist-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 /root/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth\n",
+            "100%|██████████| 44.7M/44.7M [00:00<00:00, 101MB/s]\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Epoch 1/10\n",
+            "----------\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.10/dist-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"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "train Loss: 0.5692 Acc: 0.7008\n",
+            "val Loss: 0.3884 Acc: 0.8105\n",
+            "\n",
+            "Epoch 2/10\n",
+            "----------\n",
+            "train Loss: 0.5273 Acc: 0.7746\n",
+            "val Loss: 0.3142 Acc: 0.8497\n",
+            "\n",
+            "Epoch 3/10\n",
+            "----------\n",
+            "train Loss: 0.5260 Acc: 0.7787\n",
+            "val Loss: 0.1930 Acc: 0.9150\n",
+            "\n",
+            "Epoch 4/10\n",
+            "----------\n",
+            "train Loss: 0.5688 Acc: 0.7582\n",
+            "val Loss: 0.2221 Acc: 0.9150\n",
+            "\n",
+            "Epoch 5/10\n",
+            "----------\n",
+            "train Loss: 0.5255 Acc: 0.7951\n",
+            "val Loss: 0.2291 Acc: 0.9216\n",
+            "\n",
+            "Epoch 6/10\n",
+            "----------\n",
+            "train Loss: 0.4819 Acc: 0.7705\n",
+            "val Loss: 0.5070 Acc: 0.7974\n",
+            "\n",
+            "Epoch 7/10\n",
+            "----------\n",
+            "train Loss: 0.4629 Acc: 0.7992\n",
+            "val Loss: 0.1744 Acc: 0.9477\n",
+            "\n",
+            "Epoch 8/10\n",
+            "----------\n",
+            "train Loss: 0.3263 Acc: 0.8361\n",
+            "val Loss: 0.1844 Acc: 0.9346\n",
+            "\n",
+            "Epoch 9/10\n",
+            "----------\n",
+            "train Loss: 0.3253 Acc: 0.8770\n",
+            "val Loss: 0.1961 Acc: 0.9346\n",
+            "\n",
+            "Epoch 10/10\n",
+            "----------\n",
+            "train Loss: 0.3388 Acc: 0.8320\n",
+            "val Loss: 0.1739 Acc: 0.9412\n",
+            "\n",
+            "Training complete in 6m 58s\n",
+            "Best val Acc: 0.947712\n"
+          ]
+        }
+      ],
       "source": [
         "import copy\n",
         "import os\n",
@@ -2003,7 +2135,8 @@
         "    ),\n",
         "}\n",
         "\n",
-        "data_dir = \"hymenoptera_data\"\n",
+        "drive.mount('/content/drive')\n",
+        "data_dir = \"drive/MyDrive/Colab Notebooks/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",
@@ -2163,6 +2296,591 @@
       ],
       "id": "csZtjCLgYZ_s"
     },
+    {
+      "cell_type": "code",
+      "source": [
+        "import copy\n",
+        "import os\n",
+        "import time\n",
+        "\n",
+        "import matplotlib.pyplot as plt\n",
+        "import numpy as np\n",
+        "import torch\n",
+        "import torch.nn as nn\n",
+        "import torch.optim as optim\n",
+        "import torchvision\n",
+        "from torch.optim import lr_scheduler\n",
+        "from torchvision import datasets, transforms\n",
+        "\n",
+        "# Data augmentation and normalization for training\n",
+        "# Just normalization for validation\n",
+        "data_transforms = {\n",
+        "    \"train\": transforms.Compose(\n",
+        "        [\n",
+        "            transforms.RandomResizedCrop(\n",
+        "                224\n",
+        "            ),  # ImageNet models were trained on 224x224 images\n",
+        "            transforms.RandomHorizontalFlip(),  # flip horizontally 50% of the time - increases train set variability\n",
+        "            transforms.ToTensor(),  # convert it to a PyTorch tensor\n",
+        "            transforms.Normalize(\n",
+        "                [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]\n",
+        "            ),  # ImageNet models expect this norm\n",
+        "        ]\n",
+        "    ),\n",
+        "    \"val\": transforms.Compose(\n",
+        "        [\n",
+        "            transforms.Resize(256),\n",
+        "            transforms.CenterCrop(224),\n",
+        "            transforms.ToTensor(),\n",
+        "            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),\n",
+        "        ]\n",
+        "    ),\n",
+        "}\n",
+        "###### modified part #####\n",
+        "\n",
+        "data_dir = \"drive/MyDrive/Colab Notebooks/hymenoptera_data\"\n",
+        "# Initialize datasets for training and validation using the specified transformations\n",
+        "a = datasets.ImageFolder(os.path.join(data_dir, \"train\"), data_transforms[\"train\"])\n",
+        "b = datasets.ImageFolder(os.path.join(data_dir, \"val\"), data_transforms[\"val\"])\n",
+        "\n",
+        "# Combine training and validation datasets into a single dataset\n",
+        "image_dataset = torch.utils.data.ConcatDataset([a, b])\n",
+        "\n",
+        "# Retrieve class names from the training dataset\n",
+        "class_names = a.classes\n",
+        "# Set the device to GPU if available, else CPU\n",
+        "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+        "\n",
+        "# Configuration for data loading process\n",
+        "num_workers = 0  # Number of sub-processes used for data loading\n",
+        "batch_size = 4   # Number of images processed in each batch\n",
+        "\n",
+        "# Define proportions of dataset for validation and test sets\n",
+        "valid_size = 0.2  # 20% of dataset for validation\n",
+        "test_size  = 0.1  # 10% of dataset for testing\n",
+        "\n",
+        "# Randomly shuffle indices and split into train, validation, and test sets\n",
+        "num_train = len(image_dataset)\n",
+        "indices = list(range(num_train))\n",
+        "np.random.shuffle(indices)\n",
+        "split1 = int(np.floor(valid_size * num_train))\n",
+        "split2 = int(np.floor(test_size  * num_train)) + split1\n",
+        "valid_idx, test_idx, train_idx = indices[:split1], indices[split1:split2], indices[split2:]\n",
+        "\n",
+        "# Record the size of each dataset split\n",
+        "dataset_sizes = {\"train\": len(train_idx), \"val\": len(valid_idx)}\n",
+        "\n",
+        "# Samplers for selecting data during training, validation, and testing\n",
+        "train_sampler = SubsetRandomSampler(train_idx)\n",
+        "valid_sampler = SubsetRandomSampler(valid_idx)\n",
+        "test_sampler  = SubsetRandomSampler(test_idx)\n",
+        "\n",
+        "# Data loaders to batch and load images during model training and evaluation\n",
+        "dataloaders = {\n",
+        "    \"train\": torch.utils.data.DataLoader(image_dataset, batch_size=batch_size, sampler=train_sampler, num_workers=num_workers),\n",
+        "    \"val\": torch.utils.data.DataLoader(image_dataset, batch_size=batch_size, sampler=valid_sampler, num_workers=num_workers)\n",
+        "}\n",
+        "test_loader = torch.utils.data.DataLoader(image_dataset, batch_size=batch_size, sampler=test_sampler, num_workers=num_workers)\n",
+        "\n",
+        "\n",
+        "# Helper function for displaying images\n",
+        "def imshow(inp, title=None):\n",
+        "    \"\"\"Imshow for Tensor.\"\"\"\n",
+        "    inp = inp.numpy().transpose((1, 2, 0))\n",
+        "    mean = np.array([0.485, 0.456, 0.406])\n",
+        "    std = np.array([0.229, 0.224, 0.225])\n",
+        "\n",
+        "    # Un-normalize the images\n",
+        "    inp = std * inp + mean\n",
+        "    # Clip just in case\n",
+        "    inp = np.clip(inp, 0, 1)\n",
+        "    plt.imshow(inp)\n",
+        "    if title is not None:\n",
+        "        plt.title(title)\n",
+        "    plt.pause(0.001)  # pause a bit so that plots are updated\n",
+        "    plt.show()\n",
+        "\n",
+        "# Get a batch of training data\n",
+        "# inputs, classes = next(iter(dataloaders['train']))\n",
+        "\n",
+        "# 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",
+        "# training\n",
+        "\n",
+        "\n",
+        "def train_model(model, criterion, optimizer, scheduler, num_epochs=25):\n",
+        "    since = time.time()\n",
+        "\n",
+        "    best_model_wts = copy.deepcopy(model.state_dict())\n",
+        "    best_acc = 0.0\n",
+        "\n",
+        "    epoch_time = []  # we'll keep track of the time needed for each epoch\n",
+        "\n",
+        "    for epoch in range(num_epochs):\n",
+        "        epoch_start = time.time()\n",
+        "        print(\"Epoch {}/{}\".format(epoch + 1, num_epochs))\n",
+        "        print(\"-\" * 10)\n",
+        "\n",
+        "        # Each epoch has a training and validation phase\n",
+        "        for phase in [\"train\", \"val\"]:\n",
+        "            if phase == \"train\":\n",
+        "                scheduler.step()\n",
+        "                model.train()  # Set model to training mode\n",
+        "            else:\n",
+        "                model.eval()  # Set model to evaluate mode\n",
+        "\n",
+        "            running_loss = 0.0\n",
+        "            running_corrects = 0\n",
+        "\n",
+        "            # Iterate over data.\n",
+        "            for inputs, labels in dataloaders[phase]:\n",
+        "                inputs = inputs.to(device)\n",
+        "                labels = labels.to(device)\n",
+        "\n",
+        "                # zero the parameter gradients\n",
+        "                optimizer.zero_grad()\n",
+        "\n",
+        "                # Forward\n",
+        "                # Track history if only in training phase\n",
+        "                with torch.set_grad_enabled(phase == \"train\"):\n",
+        "                    outputs = model(inputs)\n",
+        "                    _, preds = torch.max(outputs, 1)\n",
+        "                    loss = criterion(outputs, labels)\n",
+        "\n",
+        "                    # backward + optimize only if in training phase\n",
+        "                    if phase == \"train\":\n",
+        "                        loss.backward()\n",
+        "                        optimizer.step()\n",
+        "\n",
+        "                # Statistics\n",
+        "                running_loss += loss.item() * inputs.size(0)\n",
+        "                running_corrects += torch.sum(preds == labels.data)\n",
+        "\n",
+        "            epoch_loss = running_loss / dataset_sizes[phase]\n",
+        "            epoch_acc = running_corrects.double() / dataset_sizes[phase]\n",
+        "\n",
+        "            print(\"{} Loss: {:.4f} Acc: {:.4f}\".format(phase, epoch_loss, epoch_acc))\n",
+        "\n",
+        "            # Deep copy the model\n",
+        "            if phase == \"val\" and epoch_acc > best_acc:\n",
+        "                best_acc = epoch_acc\n",
+        "                best_model_wts = copy.deepcopy(model.state_dict())\n",
+        "\n",
+        "        # Add the epoch time\n",
+        "        t_epoch = time.time() - epoch_start\n",
+        "        epoch_time.append(t_epoch)\n",
+        "        print()\n",
+        "\n",
+        "    time_elapsed = time.time() - since\n",
+        "    print(\n",
+        "        \"Training complete in {:.0f}m {:.0f}s\".format(\n",
+        "            time_elapsed // 60, time_elapsed % 60\n",
+        "        )\n",
+        "    )\n",
+        "    print(\"Best val Acc: {:4f}\".format(best_acc))\n",
+        "\n",
+        "    # Load best model weights\n",
+        "    model.load_state_dict(best_model_wts)\n",
+        "    return model, epoch_time\n",
+        "\n",
+        "\n",
+        "\n",
+        "\n",
+        "# Download a pre-trained ResNet18 model and freeze its weights\n",
+        "model = torchvision.models.resnet18(pretrained=True)\n",
+        "for param in model.parameters():\n",
+        "    param.requires_grad = False\n",
+        "\n",
+        "# Replace the final fully connected layer\n",
+        "# Parameters of newly constructed modules have requires_grad=True by default\n",
+        "num_ftrs = model.fc.in_features\n",
+        "model.fc = nn.Linear(num_ftrs, 2)\n",
+        "# Send the model to the GPU\n",
+        "model = model.to(device)\n",
+        "# Set the loss function\n",
+        "criterion = nn.CrossEntropyLoss()\n",
+        "\n",
+        "# Observe that only the parameters of the final layer are being optimized\n",
+        "optimizer_conv = optim.SGD(model.fc.parameters(), lr=0.001, momentum=0.9)\n",
+        "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",
+        ")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "pB_A4hywW-Zw",
+        "outputId": "93c62617-1955-44f9-d12b-5865d516dcbf"
+      },
+      "id": "pB_A4hywW-Zw",
+      "execution_count": 52,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.10/dist-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",
+            "/usr/local/lib/python3.10/dist-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"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Epoch 1/10\n",
+            "----------\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.10/dist-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"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "train Loss: 0.6051 Acc: 0.6882\n",
+            "val Loss: 0.1484 Acc: 0.9620\n",
+            "\n",
+            "Epoch 2/10\n",
+            "----------\n",
+            "train Loss: 0.4705 Acc: 0.7778\n",
+            "val Loss: 0.1482 Acc: 0.9620\n",
+            "\n",
+            "Epoch 3/10\n",
+            "----------\n",
+            "train Loss: 0.4658 Acc: 0.7885\n",
+            "val Loss: 0.2591 Acc: 0.8861\n",
+            "\n",
+            "Epoch 4/10\n",
+            "----------\n",
+            "train Loss: 0.4696 Acc: 0.8208\n",
+            "val Loss: 0.1403 Acc: 0.9620\n",
+            "\n",
+            "Epoch 5/10\n",
+            "----------\n",
+            "train Loss: 0.4905 Acc: 0.7885\n",
+            "val Loss: 0.2154 Acc: 0.8861\n",
+            "\n",
+            "Epoch 6/10\n",
+            "----------\n",
+            "train Loss: 0.3723 Acc: 0.8710\n",
+            "val Loss: 0.1817 Acc: 0.9241\n",
+            "\n",
+            "Epoch 7/10\n",
+            "----------\n",
+            "train Loss: 0.2563 Acc: 0.9140\n",
+            "val Loss: 0.1702 Acc: 0.8861\n",
+            "\n",
+            "Epoch 8/10\n",
+            "----------\n",
+            "train Loss: 0.3036 Acc: 0.8746\n",
+            "val Loss: 0.1820 Acc: 0.9241\n",
+            "\n",
+            "Epoch 9/10\n",
+            "----------\n",
+            "train Loss: 0.2920 Acc: 0.8817\n",
+            "val Loss: 0.1941 Acc: 0.9241\n",
+            "\n",
+            "Epoch 10/10\n",
+            "----------\n",
+            "train Loss: 0.3867 Acc: 0.8530\n",
+            "val Loss: 0.2133 Acc: 0.8987\n",
+            "\n",
+            "Training complete in 6m 16s\n",
+            "Best val Acc: 0.962025\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def eval_model(model, criterion):\n",
+        "    # Initialize variables to track test loss and accuracy per class\n",
+        "    test_loss = 0.0\n",
+        "    class_correct = [0.0 for _ in range(2)]\n",
+        "    class_total = [0.0 for _ in range(2)]\n",
+        "\n",
+        "    # Set the model to evaluation mode\n",
+        "    model.eval()\n",
+        "\n",
+        "    # Iterate over batches in the test data loader\n",
+        "    for data, target in test_loader:\n",
+        "        # If GPU is available, transfer data and target tensors to GPU\n",
+        "        if train_on_gpu:\n",
+        "            data, target = data.cuda(), target.cuda()\n",
+        "\n",
+        "        # Perform a forward pass through the model with the test data\n",
+        "        output = model(data)\n",
+        "\n",
+        "        # Compute the loss of the model's predictions against the true targets\n",
+        "        loss = criterion(output, target)\n",
+        "\n",
+        "        # Accumulate the test loss over all batches\n",
+        "        test_loss += loss.item() * data.size(0)\n",
+        "\n",
+        "        # Determine the model's predicted classes for this batch\n",
+        "        _, pred = torch.max(output, 1)\n",
+        "\n",
+        "        # Compare the predicted classes to the actual classes\n",
+        "        correct_tensor = pred.eq(target.data.view_as(pred))\n",
+        "        correct = np.squeeze(correct_tensor.numpy()) if not train_on_gpu else np.squeeze(correct_tensor.cpu().numpy())\n",
+        "\n",
+        "        # Update the accuracy metrics for each class\n",
+        "        for i in range(batch_size):\n",
+        "            try:\n",
+        "                label = target.data[i]\n",
+        "                class_correct[label] += correct[i].item()\n",
+        "                class_total[label] += 1\n",
+        "            except:\n",
+        "                pass\n",
+        "\n",
+        "    # Calculate and print the average loss over the test set\n",
+        "    test_loss = test_loss / len(test_loader)\n",
+        "    print(\"Test Loss: {:.6f}\\n\".format(test_loss))\n",
+        "\n",
+        "for i in range(2):\n",
+        "    if class_total[i] > 0:\n",
+        "        accuracy = 100 * class_correct[i] / class_total[i]\n",
+        "        print(f\"Test Accuracy for {class_names[i]:>5}: {accuracy:.2f}% ({int(np.sum(class_correct[i]))}/{int(np.sum(class_total[i]))})\")\n",
+        "    else:\n",
+        "        print(f\"Test Accuracy for {class_names[i]:>5}: Not Applicable (no training examples)\")\n",
+        "\n",
+        "overall_accuracy = 100.0 * np.sum(class_correct) / np.sum(class_total)\n",
+        "print(f\"\\nOverall Test Accuracy: {overall_accuracy:.2f}% ({int(np.sum(class_correct))}/{int(np.sum(class_total))})\")\n",
+        "\n",
+        "eval_model(model,criterion)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Dt3ucPlhXlzd",
+        "outputId": "8f391999-c1da-41f9-8236-c3bfd4e67d55"
+      },
+      "id": "Dt3ucPlhXlzd",
+      "execution_count": 58,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Test Accuracy for  ants: 73.40% (734/1000)\n",
+            "Test Accuracy for  bees: 80.80% (808/1000)\n",
+            "\n",
+            "Overall Test Accuracy: 65.39% (6539/10000)\n",
+            "Test Loss: 1.071686\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "\n",
+        "# Download a pre-trained ResNet18 model and freeze its weights\n",
+        "model = torchvision.models.resnet18(pretrained=True)\n",
+        "for param in model.parameters():\n",
+        "    param.requires_grad = False\n",
+        "\n",
+        "# Replace the final fully connected layer\n",
+        "# Parameters of newly constructed modules have requires_grad=True by default\n",
+        "num_ftrs = model.fc.in_features\n",
+        "model.fc = nn.Sequential(\n",
+        "    nn.Linear(num_ftrs,512),\n",
+        "    nn.ReLU(),\n",
+        "    nn.Dropout(),\n",
+        "    nn.Linear(512,2),\n",
+        "    nn.Dropout(),\n",
+        ")\n",
+        "\n",
+        "# Send the model to the GPU\n",
+        "model = model.to(device)\n",
+        "# Set the loss function\n",
+        "criterion = nn.CrossEntropyLoss()\n",
+        "\n",
+        "# Observe that only the parameters of the final layer are being optimized\n",
+        "optimizer_conv = optim.SGD(model.fc.parameters(), lr=0.001, momentum=0.9)\n",
+        "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",
+        "\n",
+        "eval_model(model,criterion)\n",
+        "\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "zWdpBQpkcki7",
+        "outputId": "5ee822f9-57c8-43c9-ff81-9e29dbfd6cae"
+      },
+      "id": "zWdpBQpkcki7",
+      "execution_count": 54,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Epoch 1/10\n",
+            "----------\n",
+            "train Loss: 0.6396 Acc: 0.5842\n",
+            "val Loss: 0.3509 Acc: 0.8354\n",
+            "\n",
+            "Epoch 2/10\n",
+            "----------\n",
+            "train Loss: 0.5438 Acc: 0.6989\n",
+            "val Loss: 0.2769 Acc: 0.9367\n",
+            "\n",
+            "Epoch 3/10\n",
+            "----------\n",
+            "train Loss: 0.7084 Acc: 0.6595\n",
+            "val Loss: 0.2347 Acc: 0.9494\n",
+            "\n",
+            "Epoch 4/10\n",
+            "----------\n",
+            "train Loss: 0.5043 Acc: 0.6882\n",
+            "val Loss: 0.2325 Acc: 0.8987\n",
+            "\n",
+            "Epoch 5/10\n",
+            "----------\n",
+            "train Loss: 0.5727 Acc: 0.6738\n",
+            "val Loss: 0.1864 Acc: 0.9494\n",
+            "\n",
+            "Epoch 6/10\n",
+            "----------\n",
+            "train Loss: 0.4690 Acc: 0.7778\n",
+            "val Loss: 0.1940 Acc: 0.9494\n",
+            "\n",
+            "Epoch 7/10\n",
+            "----------\n",
+            "train Loss: 0.5026 Acc: 0.7348\n",
+            "val Loss: 0.2486 Acc: 0.9114\n",
+            "\n",
+            "Epoch 8/10\n",
+            "----------\n",
+            "train Loss: 0.4637 Acc: 0.7419\n",
+            "val Loss: 0.2120 Acc: 0.9494\n",
+            "\n",
+            "Epoch 9/10\n",
+            "----------\n",
+            "train Loss: 0.4250 Acc: 0.7778\n",
+            "val Loss: 0.1957 Acc: 0.9620\n",
+            "\n",
+            "Epoch 10/10\n",
+            "----------\n",
+            "train Loss: 0.5271 Acc: 0.7240\n",
+            "val Loss: 0.1930 Acc: 0.9367\n",
+            "\n",
+            "Training complete in 6m 12s\n",
+            "Best val Acc: 0.962025\n",
+            "Test Loss: 0.970537\n",
+            "\n",
+            "Test Accuracy of  ants: 85% (18/21)\n",
+            "Test Accuracy of  bees: 94% (17/18)\n",
+            "\n",
+            "Test Accuracy (Overall): 89% (35/39)\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "We observe that the new model is a bit less accurate than the precedent one"
+      ],
+      "metadata": {
+        "id": "JKX8supteaMv"
+      },
+      "id": "JKX8supteaMv"
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Lets now look at quantization\n"
+      ],
+      "metadata": {
+        "id": "BfXSGYFKeq-X"
+      },
+      "id": "BfXSGYFKeq-X"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import torch.quantization\n",
+        "\n",
+        "\n",
+        "quantized_model = torch.quantization.quantize_dynamic(model, dtype=torch.qint8)\n",
+        "print_size_of_model(model, \"fp32\")\n",
+        "print_size_of_model(quantized_model, \"int8\")\n",
+        "print(\"-----\")\n",
+        "print(\"non-quantized model:\")\n",
+        "eval_model(model,criterion)\n",
+        "\n",
+        "print(\"-----\")\n",
+        "print(\"quantized model:\")\n",
+        "eval_model(quantized_model,criterion)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "ESI9kKjvetqe",
+        "outputId": "7671eb81-7b50-44ba-eb7b-c6e7abce9cbb"
+      },
+      "id": "ESI9kKjvetqe",
+      "execution_count": 57,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "model:  fp32  \t Size (KB): 45831.61\n",
+            "model:  int8  \t Size (KB): 45043.622\n",
+            "-----\n",
+            "non-quantized model:\n",
+            "Test Loss: 1.296086\n",
+            "\n",
+            "Test Accuracy of  ants: 76% (16/21)\n",
+            "Test Accuracy of  bees: 100% (18/18)\n",
+            "\n",
+            "Test Accuracy (Overall): 87% (34/39)\n",
+            "-----\n",
+            "quantized model:\n",
+            "Test Loss: 1.061615\n",
+            "\n",
+            "Test Accuracy of  ants: 80% (17/21)\n",
+            "Test Accuracy of  bees: 100% (18/18)\n",
+            "\n",
+            "Test Accuracy (Overall): 89% (35/39)\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "We observe that one image is not recognized in the non-quantized model and is recognized in the quantized model. This is quite unexpected."
+      ],
+      "metadata": {
+        "id": "79tI2vbrfTf4"
+      },
+      "id": "79tI2vbrfTf4"
+    },
     {
       "cell_type": "markdown",
       "id": "04a263f0",