diff --git a/.gitignore b/.gitignore
index f3436fe1fd3e8a7064887098b38e50dfda48b27d..d962e7bd0f4772b2d885ebc3d18ac4c0ec7399be 100644
--- a/.gitignore
+++ b/.gitignore
@@ -4,6 +4,8 @@
 # Data
 data/*
 transfer_learning/hymenoptera_data/*
+hymenoptera_data_2/*
+hymenoptera_data.zip
 
 # Torch model
 *.pt
diff --git a/TD2 Deep Learning.ipynb b/TD2 Deep Learning.ipynb
index e74a28a2f6d8755f670ebd74b120311912280413..5c66439dffb5a274277af52d724761c575de7223 100644
--- a/TD2 Deep Learning.ipynb	
+++ b/TD2 Deep Learning.ipynb	
@@ -1758,10 +1758,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 41,
    "id": "be2d31f5",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "import os\n",
     "\n",
@@ -1850,10 +1861,93 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 42,
    "id": "572d824c",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\basil\\AppData\\Local\\Programs\\Python\\Python39\\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\\basil\\AppData\\Local\\Programs\\Python\\Python39\\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=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"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "----------\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\basil\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\torch\\optim\\lr_scheduler.py:138: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order: `optimizer.step()` before `lr_scheduler.step()`.  Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate\n",
+      "  warnings.warn(\"Detected call of `lr_scheduler.step()` before `optimizer.step()`. \"\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "train Loss: 0.5628 Acc: 0.6844\n",
+      "val Loss: 0.2225 Acc: 0.9412\n",
+      "\n",
+      "Epoch 2/10\n",
+      "----------\n",
+      "train Loss: 0.4648 Acc: 0.7787\n",
+      "val Loss: 0.2554 Acc: 0.9085\n",
+      "\n",
+      "Epoch 3/10\n",
+      "----------\n",
+      "train Loss: 0.3467 Acc: 0.8443\n",
+      "val Loss: 0.1586 Acc: 0.9477\n",
+      "\n",
+      "Epoch 4/10\n",
+      "----------\n",
+      "train Loss: 0.4071 Acc: 0.8361\n",
+      "val Loss: 0.4426 Acc: 0.8301\n",
+      "\n",
+      "Epoch 5/10\n",
+      "----------\n",
+      "train Loss: 0.5322 Acc: 0.7541\n",
+      "val Loss: 0.1989 Acc: 0.9150\n",
+      "\n",
+      "Epoch 6/10\n",
+      "----------\n",
+      "train Loss: 0.4771 Acc: 0.8074\n",
+      "val Loss: 0.2121 Acc: 0.9477\n",
+      "\n",
+      "Epoch 7/10\n",
+      "----------\n",
+      "train Loss: 0.2927 Acc: 0.8689\n",
+      "val Loss: 0.2111 Acc: 0.9477\n",
+      "\n",
+      "Epoch 8/10\n",
+      "----------\n",
+      "train Loss: 0.3218 Acc: 0.8443\n",
+      "val Loss: 0.1833 Acc: 0.9542\n",
+      "\n",
+      "Epoch 9/10\n",
+      "----------\n",
+      "train Loss: 0.4240 Acc: 0.8156\n",
+      "val Loss: 0.1996 Acc: 0.9412\n",
+      "\n",
+      "Epoch 10/10\n",
+      "----------\n",
+      "train Loss: 0.3845 Acc: 0.8238\n",
+      "val Loss: 0.1800 Acc: 0.9542\n",
+      "\n",
+      "Training complete in 4m 25s\n",
+      "Best val Acc: 0.954248\n"
+     ]
+    }
+   ],
    "source": [
     "import copy\n",
     "import os\n",
@@ -2051,6 +2145,744 @@
     "Apply ther quantization (post and quantization aware) and evaluate impact on model size and accuracy."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 1. Creation of a test set\n",
+    "\n",
+    "We create a new folder in the working directory, and we name it `hymenoptera_data_2`. We want to reorganize the data into two subfolders named `ants` and `bees`. Once all the images of ants and bees from the `hymenoptera_data` are placed in the correct subfolder, we can divide them into three groups : train, validation and test.\n",
+    "\n",
+    "**We move the images from `hymenoptera_data` to a new folder `hymenoptera_data_2` in the working directory**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 85,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The new directory hymenoptera_data_2 is created!\n",
+      "The new directory hymenoptera_data_2/ants is created!\n",
+      "The new directory hymenoptera_data_2/bees is created!\n"
+     ]
+    }
+   ],
+   "source": [
+    "# create train, validation and test batches\n",
+    "\n",
+    "import os\n",
+    "import random\n",
+    "\n",
+    "cwd = os.getcwd()\n",
+    "directory = \"hymenoptera_data\"\n",
+    "\n",
+    "# *************************\n",
+    "# STEP 1 :create new folder\n",
+    "# *************************\n",
+    "\n",
+    "new_directory = \"hymenoptera_data_2\"\n",
+    "# Check whether the specified path exists or not\n",
+    "isExist = os.path.exists(os.path.join(cwd, new_directory))\n",
+    "if not isExist:\n",
+    "\n",
+    "   # Create a new directory because it does not exist\n",
+    "   os.makedirs(new_directory)\n",
+    "   print(f\"The new directory {new_directory} is created!\")\n",
+    "# create subfolders\n",
+    "sub1 = \"hymenoptera_data_2/ants\"\n",
+    "sub2 = \"hymenoptera_data_2/bees\"\n",
+    "for subfolder in [sub1, sub2]:\n",
+    "   isExist = os.path.exists(os.path.join(cwd, subfolder))\n",
+    "   if not isExist:\n",
+    "\n",
+    "      # Create a new directory because it does not exist\n",
+    "      os.makedirs(subfolder)\n",
+    "      print(f\"The new directory {subfolder} is created!\")\n",
+    "\n",
+    "\n",
+    "# *************************\n",
+    "# STEP 2 : copy images in subfolders\n",
+    "# *************************\n",
+    "path_ants1 = os.path.join(\"hymenoptera_data\",\"train\",\"ants\")\n",
+    "path_bees1 = os.path.join(\"hymenoptera_data\",\"train\",\"bees\")\n",
+    "path_ants2 = os.path.join(\"hymenoptera_data\",\"val\",\"ants\")\n",
+    "path_bees2 = os.path.join(\"hymenoptera_data\",\"val\",\"bees\")\n",
+    "\n",
+    "list_ants1 = os.listdir(path_ants1).copy()\n",
+    "list_ants2 = os.listdir(path_ants2).copy()\n",
+    "\n",
+    "for fname in list_ants1:\n",
+    "   original_directory = os.path.join(path_ants1,fname)\n",
+    "   destination_directory = os.path.join(\"hymenoptera_data_2\",'ants', fname )\n",
+    "   os.rename(original_directory, destination_directory)\n",
+    "for fname in list_ants2:\n",
+    "   original_directory = os.path.join(path_ants2,fname)\n",
+    "   destination_directory = os.path.join(\"hymenoptera_data_2\",'ants', fname )\n",
+    "   os.rename(original_directory, destination_directory)\n",
+    "\n",
+    "\n",
+    "list_bees1 = os.listdir(path_bees1).copy()\n",
+    "list_bees2 = os.listdir(path_bees2).copy()\n",
+    "for fname in list_bees1:\n",
+    "   original_directory = os.path.join(path_bees1,fname)\n",
+    "   destination_directory = os.path.join(\"hymenoptera_data_2\",'bees', fname )\n",
+    "   os.rename(original_directory, destination_directory)\n",
+    "for fname in list_bees2:\n",
+    "   original_directory = os.path.join(path_bees2,fname)\n",
+    "   destination_directory = os.path.join(\"hymenoptera_data_2\",'bees', fname )\n",
+    "   os.rename(original_directory, destination_directory)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "At this point, the folder `hymenoptera_data_2` contains two subfolders which regroup respectively all the images of bees and ants from the `hymenoptera` data set."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 86,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "there are :\n",
+      "194 images of ants\n",
+      "204 images of bees\n"
+     ]
+    }
+   ],
+   "source": [
+    "sub1 = os.path.join(cwd, \"hymenoptera_data_2/ants\")\n",
+    "sub2 = os.path.join(cwd, \"hymenoptera_data_2/bees\")\n",
+    "\n",
+    "list_ants = os.listdir(sub1)\n",
+    "list_bees = os.listdir(sub2)\n",
+    "\n",
+    "print(f\"there are :\\n{len(list_ants)} images of ants\\n{len(list_bees)} images of bees\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now the file `hymenoptera_data_2` contains 2 subfolders named `ants` (contains 194 images of ants) and `bees` (contains 194 images of bees)\n",
+    "\n",
+    "In the subfolder `ants` we create 3 subfolders : `ants_train`, `ants_val` and `ants_test`.\n",
+    "In the subfolder `bees` we create 3 subfolders : `bees_train`, `bees_val` and `bees_test`.\n",
+    "\n",
+    "The goal is then to regroup those files in order to obtain the following structure :\n",
+    "\n",
+    "The file `hymenoptera_data_2` contains 3 subfiles : `train`, `val` and `test`.\n",
+    "Each subfile contains 2 subfiles : `ants` and `bees`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create subfolders\n",
+    "sub1 = \"hymenoptera_data_2/ants/ants_train\"\n",
+    "sub2 = \"hymenoptera_data_2/ants/ants_val\"\n",
+    "sub3 = \"hymenoptera_data_2/ants/ants_test\"\n",
+    "sub4 = \"hymenoptera_data_2/bees/bees_train\"\n",
+    "sub5 = \"hymenoptera_data_2/bees/bees_val\"\n",
+    "sub6 = \"hymenoptera_data_2/bees/bees_test\"\n",
+    "sub7 = \"hymenoptera_data_2/train\"\n",
+    "sub8 = \"hymenoptera_data_2/val\"\n",
+    "sub9 = \"hymenoptera_data_2/test\"\n",
+    "for subfolder in [sub1, sub2, sub3, sub4, sub5, sub6, ]:\n",
+    "   isExist = os.path.exists(os.path.join(cwd, subfolder))\n",
+    "   if not isExist:\n",
+    "\n",
+    "      # Create a new directory because it does not exist\n",
+    "      os.makedirs(subfolder)\n",
+    "      print(f\"The new directory {subfolder} is created!\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The idea of this reorganization is to take roughly 20% of the initial train batch and 50% of the initial validation batch in order to create the test batch.\n",
+    "\n",
+    "The new train and validation batches contain thus less elements than the previous ones.\n",
+    "\n",
+    "The new train batch contains 318 pictures (156 ants, 162 bees), the validation and test batches both contain 40 pictures (19 ants and 21 bees).\n",
+    "\n",
+    "We are now able to slightly modify the initial model and then train is with the new train and validation batches. We then evaluate the model using the test, which we created to serve this purpose."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 90,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "list ants_test : 19 \t list ants_val : 19 \t list ants_train : 156\n",
+      "initial length 194\n",
+      "list bees_test : 21 \t list bees_val : 21 \t list bees_train : 162\n",
+      "initial length 204\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_dir = \"hymenoptera_data_2\"\n",
+    "\n",
+    "list1 = [os.path.join(data_dir,x) for x in [\"ants\",\"bees\"]]\n",
+    "\n",
+    "# create test, validation and training samples\n",
+    "\n",
+    "#ants\n",
+    "path = list1[0]\n",
+    "\n",
+    "list_ants = os.listdir(path).copy()\n",
+    "for x in ['ants_test','ants_train','ants_val']:\n",
+    "    list_ants.remove(x)\n",
+    "# list_ants contains only file names of ants pictures\n",
+    "\n",
+    "list_ants_test = random.sample(list_ants,19)\n",
+    "list_ants_train = [x for x in list_ants if x not in list_ants_test]\n",
+    "\n",
+    "\n",
+    "list_ants_val = random.sample(list_ants_train,19)\n",
+    "list_ants_train = [x for x in list_ants_train if x not in list_ants_val]\n",
+    "\n",
+    "print(f'list ants_test : {len(list_ants_test)} \\t list ants_val : {len(list_ants_val)} \\t list ants_train : {len(list_ants_train)}')\n",
+    "print(f'initial length {len(list_ants)}')\n",
+    "\n",
+    "# put the pictures of ants in the right folders\n",
+    "for fname in list_ants_test:\n",
+    "    os.rename(os.path.join(path,fname), os.path.join( os.path.join(path,'ants_test'), fname ))\n",
+    "for fname in list_ants_val:\n",
+    "    os.rename(os.path.join(path,fname), os.path.join( os.path.join(path,'ants_val'), fname ))\n",
+    "for fname in list_ants_train:\n",
+    "    os.rename(os.path.join(path,fname), os.path.join( os.path.join(path,'ants_train'), fname ))\n",
+    "\n",
+    "# bees\n",
+    "path = list1[1]\n",
+    "\n",
+    "list_bees = os.listdir(path).copy()\n",
+    "for x in ['bees_test','bees_train','bees_val']:\n",
+    "    list_bees.remove(x)\n",
+    "\n",
+    "list_bees_test = random.sample(list_bees,21)\n",
+    "list_bees_train = [x for x in list_bees if x not in list_bees_test]\n",
+    "\n",
+    "\n",
+    "list_bees_val = random.sample(list_bees_train,21)\n",
+    "list_bees_train = [x for x in list_bees_train if x not in list_bees_val]\n",
+    "\n",
+    "print(f'list bees_test : {len(list_bees_test)} \\t list bees_val : {len(list_bees_val)} \\t list bees_train : {len(list_bees_train)}')\n",
+    "print(f'initial length {len(list_bees)}')\n",
+    "\n",
+    "# put the pictures of bees in the right folders\n",
+    "for fname in list_bees_test:\n",
+    "    os.rename(os.path.join(path,fname), os.path.join( os.path.join(path,'bees_test'), fname ))\n",
+    "for fname in list_bees_val:\n",
+    "    os.rename(os.path.join(path,fname), os.path.join( os.path.join(path,'bees_val'), fname ))\n",
+    "for fname in list_bees_train:\n",
+    "    os.rename(os.path.join(path,fname), os.path.join( os.path.join(path,'bees_train'), fname ))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 91,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The new directory hymenoptera_data_2/train/ants is created!\n",
+      "The new directory hymenoptera_data_2/train/bees is created!\n",
+      "The new directory hymenoptera_data_2/test/ants is created!\n",
+      "The new directory hymenoptera_data_2/test/bees is created!\n",
+      "The new directory hymenoptera_data_2/val/ants is created!\n",
+      "The new directory hymenoptera_data_2/val/bees is created!\n"
+     ]
+    }
+   ],
+   "source": [
+    "# regroup the ants and bees images in the test, train and val subfolders\n",
+    "\n",
+    "# create subfolders\n",
+    "sub1 = \"hymenoptera_data_2/train/ants\"\n",
+    "sub2 = \"hymenoptera_data_2/train/bees\"\n",
+    "sub3 = \"hymenoptera_data_2/test/ants\"\n",
+    "sub4 = \"hymenoptera_data_2/test/bees\"\n",
+    "sub5 = \"hymenoptera_data_2/val/ants\"\n",
+    "sub6 = \"hymenoptera_data_2/val/bees\"\n",
+    "for subfolder in [sub1, sub2, sub3, sub4, sub5, sub6]:\n",
+    "   isExist = os.path.exists(os.path.join(cwd, subfolder))\n",
+    "   if not isExist:\n",
+    "\n",
+    "      # Create a new directory because it does not exist\n",
+    "      os.makedirs(subfolder)\n",
+    "      print(f\"The new directory {subfolder} is created!\")\n",
+    "\n",
+    "data_dir = os.path.join(\"hymenoptera_data_2\",\"ants\")\n",
+    "list_ants = [os.path.join(data_dir,x) for x in [\"ants_test\",\"ants_train\",\"ants_val\"]]\n",
+    "data_dir = os.path.join(\"hymenoptera_data_2\",\"bees\")\n",
+    "list_bees = [os.path.join(data_dir,x) for x in [\"bees_test\",\"bees_train\",\"bees_val\"]]\n",
+    "\n",
+    "path = list_ants[0]\n",
+    "list_ants_test = os.listdir(path).copy()\n",
+    "for fname in list_ants_test:\n",
+    "   os.rename(os.path.join(path,fname), os.path.join( os.path.join(\"hymenoptera_data_2\",\"test\",\"ants\"), fname ))\n",
+    "\n",
+    "path = list_ants[1]\n",
+    "list_ants_train = os.listdir(path).copy()\n",
+    "for fname in list_ants_train:\n",
+    "   os.rename(os.path.join(path,fname), os.path.join( os.path.join(\"hymenoptera_data_2\",\"train\",\"ants\"), fname ))\n",
+    "\n",
+    "path = list_ants[2]\n",
+    "list_ants_val = os.listdir(path).copy()\n",
+    "for fname in list_ants_val:\n",
+    "   os.rename(os.path.join(path,fname), os.path.join( os.path.join(\"hymenoptera_data_2\",\"val\",\"ants\"), fname ))\n",
+    "   \n",
+    "path = list_bees[0]\n",
+    "list_bees_test = os.listdir(path).copy()\n",
+    "for fname in list_bees_test:\n",
+    "   os.rename(os.path.join(path,fname), os.path.join( os.path.join(\"hymenoptera_data_2\",\"test\",\"bees\"), fname ))\n",
+    "\n",
+    "path = list_bees[1]\n",
+    "list_bees_train = os.listdir(path).copy()\n",
+    "for fname in list_bees_train:\n",
+    "   os.rename(os.path.join(path,fname), os.path.join( os.path.join(\"hymenoptera_data_2\",\"train\",\"bees\"), fname ))\n",
+    "\n",
+    "path = list_bees[2]\n",
+    "list_bees_val = os.listdir(path).copy()\n",
+    "for fname in list_bees_val:\n",
+    "   os.rename(os.path.join(path,fname), os.path.join( os.path.join(\"hymenoptera_data_2\",\"val\",\"bees\"), fname ))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Finally we end up with a folder `hymenoptera_data_2\\test` which contains 40 images, a folder `hymenoptera_data_2\\train` which contains 318 images and a folder `hymenoptera_data_2\\val` which contains 40 images."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 93,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "test subfolder contains 40 images\n",
+      "train subfolder contains 318 images\n",
+      "val subfolder contains 40 images\n"
+     ]
+    }
+   ],
+   "source": [
+    "test_a = os.path.join(\"hymenoptera_data_2\",\"test\",\"ants\")\n",
+    "test_b = os.path.join(\"hymenoptera_data_2\",\"test\",\"bees\")\n",
+    "list_test_a = os.listdir(test_a)\n",
+    "list_test_b = os.listdir(test_b)\n",
+    "train_a = os.path.join(\"hymenoptera_data_2\",\"train\",\"ants\")\n",
+    "train_b = os.path.join(\"hymenoptera_data_2\",\"train\",\"bees\")\n",
+    "list_train_a = os.listdir(train_a)\n",
+    "list_train_b = os.listdir(train_b)\n",
+    "val_a = os.path.join(\"hymenoptera_data_2\",\"val\",\"ants\")\n",
+    "val_b = os.path.join(\"hymenoptera_data_2\",\"val\",\"bees\")\n",
+    "list_val_a = os.listdir(val_a)\n",
+    "list_val_b = os.listdir(val_b)\n",
+    "print(f\"test subfolder contains {len(list_test_a)+len(list_test_b)} images\\ntrain subfolder contains {len(list_train_a)+len(list_train_b)} images\\nval subfolder contains {len(list_val_a)+len(list_val_b)} images\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 2. Evaluation function\n",
+    "\n",
+    "Function eval_model() to evaluate the model on the test set"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 94,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# evaluation function : evaluate the model on a test set\n",
+    "\n",
+    "def eval_model(model):\n",
+    "\n",
+    "    criterion = nn.CrossEntropyLoss()\n",
+    "\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[\"test\"]:\n",
+    "\n",
+    "        inputs = inputs.to(device)\n",
+    "        labels = labels.to(device)\n",
+    "        outputs = model(inputs)\n",
+    "        _, preds = torch.max(outputs, 1)\n",
+    "        loss = criterion(outputs, labels)\n",
+    "\n",
+    "    # Statistics\n",
+    "        running_loss += loss.item() * inputs.size(0)\n",
+    "        running_corrects += torch.sum(preds == labels.data)\n",
+    "\n",
+    "    tot_test = dataset_sizes[\"test\"]\n",
+    "\n",
+    "    loss = running_loss / tot_test\n",
+    "    acc = running_corrects.double() / tot_test\n",
+    "\n",
+    "    print(\"{} Loss: {:.4f} Acc: {:.4f}\".format(\"test\", loss, acc))\n",
+    "\n",
+    "    print(f\"Total items tested : {tot_test} \\n Number of correct Results : {running_corrects.double()}\")\n",
+    "  \n",
+    "    return"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 3. Training and validation\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 96,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "----------\n",
+      "train Loss: 0.7477 Acc: 0.5597\n",
+      "val Loss: 0.3545 Acc: 0.9487\n",
+      "\n",
+      "Epoch 2/10\n",
+      "----------\n",
+      "train Loss: 0.5886 Acc: 0.6730\n",
+      "val Loss: 0.2765 Acc: 0.9231\n",
+      "\n",
+      "Epoch 3/10\n",
+      "----------\n",
+      "train Loss: 0.5664 Acc: 0.6792\n",
+      "val Loss: 0.2616 Acc: 0.8974\n",
+      "\n",
+      "Epoch 4/10\n",
+      "----------\n",
+      "train Loss: 0.5402 Acc: 0.7516\n",
+      "val Loss: 0.2461 Acc: 0.9231\n",
+      "\n",
+      "Epoch 5/10\n",
+      "----------\n",
+      "train Loss: 0.5886 Acc: 0.7044\n",
+      "val Loss: 0.4632 Acc: 0.7179\n",
+      "\n",
+      "Epoch 6/10\n",
+      "----------\n",
+      "train Loss: 0.5657 Acc: 0.6855\n",
+      "val Loss: 0.2118 Acc: 0.9231\n",
+      "\n",
+      "Epoch 7/10\n",
+      "----------\n",
+      "train Loss: 0.5017 Acc: 0.6918\n",
+      "val Loss: 0.2565 Acc: 0.8974\n",
+      "\n",
+      "Epoch 8/10\n",
+      "----------\n",
+      "train Loss: 0.4605 Acc: 0.7075\n",
+      "val Loss: 0.2278 Acc: 0.9231\n",
+      "\n",
+      "Epoch 9/10\n",
+      "----------\n",
+      "train Loss: 0.4964 Acc: 0.7296\n",
+      "val Loss: 0.2040 Acc: 0.9231\n",
+      "\n",
+      "Epoch 10/10\n",
+      "----------\n",
+      "train Loss: 0.4516 Acc: 0.7233\n",
+      "val Loss: 0.2103 Acc: 0.9231\n",
+      "\n",
+      "Training complete in 6m 36s\n",
+      "Best val Acc: 0.948718\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Now modify the code to replace the current classification layer with a set of two layers using a \"relu\" activation function for the middle \n",
+    "# layer, and the \"dropout\" mechanism for both layers. Renew the experiments and study the results obtained.\n",
+    "\n",
+    "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",
+    "    \"test\": 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_2\"\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",
+    "    for x in [\"train\", \"val\",\"test\"]\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\",\"test\"]\n",
+    "}\n",
+    "dataset_sizes = {x: len(image_datasets[x]) for x in [\"train\", \"val\",\"test\"]}\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",
+    "    \"\"\"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",
+    "\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",
+    "\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",
+    "# 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 : replace the current classification layer with a set of two layers using a \"relu\" activation function \n",
+    "# for the middle layer, and the \"dropout\" mechanism for both layers\n",
+    "# Parameters of newly constructed modules have requires_grad=True by default\n",
+    "\n",
+    "num_ftrs = model.fc.in_features\n",
+    "\n",
+    "class newlayers(nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super(newlayers, self).__init__()\n",
+    "        self.fc1 = nn.Linear(num_ftrs,num_ftrs)\n",
+    "        self.fc2 = nn.Linear(num_ftrs,2)        \n",
+    "        self.dropout = nn.Dropout(p = 0.5)\n",
+    "    \n",
+    "    def forward(self, x):\n",
+    "\n",
+    "        x = self.dropout(F.relu(self.fc1(x)))\n",
+    "        x = self.dropout(self.fc2(x))\n",
+    "        \n",
+    "        return x\n",
+    "        \n",
+    "model.fc = newlayers()\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"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 97,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "model:  fp32  \t Size (KB): 45831.183\n",
+      "test Loss: 0.4210 Acc: 0.9000\n",
+      "Total items tested : 40 \n",
+      " Number of correct Results : 36.0\n",
+      "model:  int8  \t Size (KB): 45043.195\n",
+      "test Loss: 0.4206 Acc: 0.9250\n",
+      "Total items tested : 40 \n",
+      " Number of correct Results : 37.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "model_size = print_size_of_model(model, \"fp32\")\n",
+    "eval_model(model)\n",
+    "quantized_model = torch.quantization.quantize_dynamic(model, dtype=torch.qint8)\n",
+    "q_size = print_size_of_model(quantized_model, \"int8\")\n",
+    "eval_model(quantized_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "***\n",
+    "Conclusion :\n",
+    "\n",
+    "The quantized model has a similar size compared to the initial model.\n",
+    "They both have a good accuracy (36/40 for the initial model and 37/40 for the quantized one).\n",
+    "***"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "04a263f0",
diff --git a/hymenoptera_data/train/ants/formica.jpeg b/hymenoptera_data/train/ants/formica.jpeg
deleted file mode 100644
index af83327233be73099c700fce654749842aad4a9d..0000000000000000000000000000000000000000
Binary files a/hymenoptera_data/train/ants/formica.jpeg and /dev/null differ
diff --git a/hymenoptera_data/train/ants/imageNotFound.gif b/hymenoptera_data/train/ants/imageNotFound.gif
deleted file mode 100644
index bdeaae94004e06c6a35d147ec58fb35062076b52..0000000000000000000000000000000000000000
Binary files a/hymenoptera_data/train/ants/imageNotFound.gif and /dev/null differ