diff --git a/TD2 Deep Learning.ipynb b/TD2 Deep Learning.ipynb
index 2b03d85feebca90be2950f98019fe2517cfcc423..d344fe77b722139d1c6378d5b246cd985a56d137 100644
--- a/TD2 Deep Learning.ipynb	
+++ b/TD2 Deep Learning.ipynb	
@@ -2310,6 +2310,15 @@
     ")\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "    -the code conducts fine-tuning on a pre-trained ResNet18 model using the Hymenoptera dataset for binary classification. Over the 10 training epochs: \n",
+    "    The initial epoch reveals moderate training accuracy and lower validation accuracy. \n",
+    "    Subsequent epochs exhibit improvements in both training and validation accuracy, peaking at 94.77% in validation Training loss fluctuates, yet the model effectively generalizes to the validation set."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "bbd48800",
@@ -2326,39 +2335,6 @@
     "Apply ther quantization (post and quantization aware) and evaluate impact on model size and accuracy."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 108,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#eval_model\n",
-    "\n",
-    "def eval_model(model, dataloader, criterion):\n",
-    "    model.eval()  # Set the model to evaluate mode\n",
-    "    running_loss = 0.0\n",
-    "    running_corrects = 0\n",
-    "\n",
-    "    with torch.no_grad():\n",
-    "        for inputs, labels in dataloader:\n",
-    "            inputs = inputs.to(device)\n",
-    "            labels = labels.to(device)\n",
-    "\n",
-    "            outputs = model(inputs)\n",
-    "            _, preds = torch.max(outputs, 1)\n",
-    "            loss = criterion(outputs, labels)\n",
-    "\n",
-    "            running_loss += loss.item() * inputs.size(0)\n",
-    "            running_corrects += torch.sum(preds == labels.data)\n",
-    "\n",
-    "    loss = running_loss / len(dataloader.dataset)\n",
-    "    accuracy = running_corrects.double() / len(dataloader.dataset)\n",
-    "\n",
-    "    print(\"Evaluation Loss: {:.4f} Accuracy: {:.4f}\".format(loss, accuracy))\n",
-    "    return loss, accuracy\n",
-    "\n"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 109,
@@ -2491,6 +2467,288 @@
     "eval_model(model, test_dataloader, criterion)\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 126,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "----------\n",
+      "train Loss: 0.7233 Acc: 0.6311\n",
+      "val Loss: 0.3162 Acc: 0.8758\n",
+      "\n",
+      "Epoch 2/10\n",
+      "----------\n",
+      "train Loss: 0.4187 Acc: 0.8115\n",
+      "val Loss: 0.3326 Acc: 0.8758\n",
+      "\n",
+      "Epoch 3/10\n",
+      "----------\n",
+      "train Loss: 0.4144 Acc: 0.8197\n",
+      "val Loss: 0.2013 Acc: 0.9477\n",
+      "\n",
+      "Epoch 4/10\n",
+      "----------\n",
+      "train Loss: 0.4652 Acc: 0.8033\n",
+      "val Loss: 0.2706 Acc: 0.9020\n",
+      "\n",
+      "Epoch 5/10\n",
+      "----------\n",
+      "train Loss: 0.4906 Acc: 0.7910\n",
+      "val Loss: 0.2601 Acc: 0.9216\n",
+      "\n",
+      "Epoch 6/10\n",
+      "----------\n",
+      "train Loss: 0.3980 Acc: 0.8279\n",
+      "val Loss: 0.1869 Acc: 0.9477\n",
+      "\n",
+      "Epoch 7/10\n",
+      "----------\n",
+      "train Loss: 0.3017 Acc: 0.8770\n",
+      "val Loss: 0.1723 Acc: 0.9412\n",
+      "\n",
+      "Epoch 8/10\n",
+      "----------\n",
+      "train Loss: 0.4272 Acc: 0.7869\n",
+      "val Loss: 0.1727 Acc: 0.9542\n",
+      "\n",
+      "Epoch 9/10\n",
+      "----------\n",
+      "train Loss: 0.2845 Acc: 0.8893\n",
+      "val Loss: 0.1666 Acc: 0.9477\n",
+      "\n",
+      "Epoch 10/10\n",
+      "----------\n",
+      "train Loss: 0.3986 Acc: 0.8115\n",
+      "val Loss: 0.1770 Acc: 0.9477\n",
+      "\n",
+      "Training complete in 5m 17s\n",
+      "Best val Acc: 0.954248\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "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(224),\n",
+    "            transforms.RandomHorizontalFlip(),\n",
+    "            transforms.ToTensor(),\n",
+    "            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),\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",
+    "\n",
+    "data_dir = \"hymenoptera_data\"\n",
+    "image_datasets = {\n",
+    "    x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])\n",
+    "    for x in [\"train\", \"val\"]\n",
+    "}\n",
+    "dataloaders = {\n",
+    "    x: torch.utils.data.DataLoader(\n",
+    "        image_datasets[x], batch_size=4, shuffle=True, num_workers=4\n",
+    "    )\n",
+    "    for x in [\"train\", \"val\"]\n",
+    "}\n",
+    "dataset_sizes = {x: len(image_datasets[x]) for x in [\"train\", \"val\"]}\n",
+    "class_names = image_datasets[\"train\"].classes\n",
+    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+    "\n",
+    "# Helper function for displaying images\n",
+    "def imshow(inp, title=None):\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",
+    "    inp = std * inp + mean\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)\n",
+    "    plt.show()\n",
+    "\n",
+    "# Function to evaluate the model on a test set\n",
+    "def eval_model(model, dataloader, criterion):\n",
+    "    model.eval()\n",
+    "    running_loss = 0.0\n",
+    "    running_corrects = 0\n",
+    "\n",
+    "    for inputs, labels in dataloader:\n",
+    "        inputs = inputs.to(device)\n",
+    "        labels = labels.to(device)\n",
+    "\n",
+    "        with torch.no_grad():\n",
+    "            outputs = model(inputs)\n",
+    "            _, preds = torch.max(outputs, 1)\n",
+    "            loss = criterion(outputs, labels)\n",
+    "\n",
+    "        running_loss += loss.item() * inputs.size(0)\n",
+    "        running_corrects += torch.sum(preds == labels.data)\n",
+    "\n",
+    "    loss = running_loss / len(dataloader.dataset)\n",
+    "    acc = running_corrects.double() / len(dataloader.dataset)\n",
+    "\n",
+    "    print(\"Test Loss: {:.4f} Test Acc: {:.4f}\".format(loss, acc))\n",
+    "    return acc\n",
+    "\n",
+    "# Model training function\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 = []\n",
+    "    train_losses = []\n",
+    "    val_losses = []\n",
+    "    train_accuracies = []\n",
+    "    val_accuracies = []\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",
+    "        for phase in [\"train\", \"val\"]:\n",
+    "            if phase == \"train\":\n",
+    "                scheduler.step()\n",
+    "                model.train()\n",
+    "            else:\n",
+    "                model.eval()\n",
+    "\n",
+    "            running_loss = 0.0\n",
+    "            running_corrects = 0\n",
+    "\n",
+    "            for inputs, labels in dataloaders[phase]:\n",
+    "                inputs = inputs.to(device)\n",
+    "                labels = labels.to(device)\n",
+    "\n",
+    "                optimizer.zero_grad()\n",
+    "\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",
+    "                    if phase == \"train\":\n",
+    "                        loss.backward()\n",
+    "                        optimizer.step()\n",
+    "\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",
+    "            if phase == \"train\":\n",
+    "                train_losses.append(epoch_loss)\n",
+    "                train_accuracies.append(epoch_acc)\n",
+    "            elif phase == \"val\":\n",
+    "                val_losses.append(epoch_loss)\n",
+    "                val_accuracies.append(epoch_acc)\n",
+    "                if epoch_acc > best_acc:\n",
+    "                    best_acc = epoch_acc\n",
+    "                    best_model_wts = copy.deepcopy(model.state_dict())\n",
+    "\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",
+    "    model.load_state_dict(best_model_wts)\n",
+    "\n",
+    "    # Plot the losses and accuracies\n",
+    "    plt.figure(figsize=(10, 5))\n",
+    "\n",
+    "    # Plot losses\n",
+    "    plt.subplot(1, 2, 1)\n",
+    "    plt.plot(range(1, num_epochs + 1), train_losses, label=\"Training Loss\")\n",
+    "    plt.plot(range(1, num_epochs + 1), val_losses, label=\"Validation Loss\")\n",
+    "    plt.title(\"Training and Validation Loss\")\n",
+    "    plt.xlabel(\"Epoch\")\n",
+    "    plt.ylabel(\"Loss\")\n",
+    "    plt.legend()\n",
+    "\n",
+    "    # Plot accuracies\n",
+    "    plt.subplot(1, 2, 2)\n",
+    "    plt.plot(range(1, num_epochs + 1), train_accuracies, label=\"Training Accuracy\")\n",
+    "    plt.plot(range(1, num_epochs + 1), val_accuracies, label=\"Validation Accuracy\")\n",
+    "    plt.title(\"Training and Validation Accuracy\")\n",
+    "    plt.xlabel(\"Epoch\")\n",
+    "    plt.ylabel(\"Accuracy\")\n",
+    "    plt.legend()\n",
+    "\n",
+    "    plt.tight_layout()\n",
+    "    plt.show()\n",
+    "\n",
+    "    return model, epoch_time\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",
+    "num_ftrs = model.fc.in_features\n",
+    "model.fc = nn.Linear(num_ftrs, 2)\n",
+    "model = model.to(device)\n",
+    "criterion = nn.CrossEntropyLoss()\n",
+    "\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",
+    "\n",
+    "# Train the model\n",
+    "model, epoch_time = train_model(\n",
+    "    model, criterion, optimizer_conv, exp_lr_scheduler, num_epochs=10\n",
+    ")\n"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "04a263f0",