diff --git a/TD/TD7/ML-TD7.ipynb b/TD/TD7/ML-TD7.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..b946c8f85331b20d7613342c9dbad4038a55934f
--- /dev/null
+++ b/TD/TD7/ML-TD7.ipynb
@@ -0,0 +1,735 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "7edf7168",
+ "metadata": {},
+ "source": [
+ "### **_Introduction au Machine Learning - Enise - Centrale Lyon_**\n",
+ "\n",
+ "2024-2025\n",
+ "\n",
+ "Emmanuel Dellandréa\t \n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "4c69d182",
+ "metadata": {},
+ "source": [
+ "# TD7 – Convolutional Neural Networks"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "fa71eda4",
+ "metadata": {},
+ "source": [
+ "The objective of this tutorial is to use the PyTorch library for building, training, and evaluating CNN models."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "23f266da",
+ "metadata": {},
+ "source": [
+ "## Sequence 1: Training a CNN to classify CIFAR10 images\n",
+ "\n",
+ "The goal is to apply a Convolutional Neural Net (CNN) model on the CIFAR10 image dataset and test the accuracy of the model on the basis of image classification. \n",
+ "\n",
+ "Be sure to check the PyTorch tutorials and documentation when needed:\n",
+ "\n",
+ "https://pytorch.org/tutorials/\n",
+ "\n",
+ "https://pytorch.org/docs/stable/index.html\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "4ba1c82d",
+ "metadata": {},
+ "source": [
+ "You can test if GPU is available on your machine and thus train on it to speed up the process"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "6e18f2fd",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import torch\n",
+ "\n",
+ "# check if CUDA is available\n",
+ "train_on_gpu = torch.cuda.is_available()\n",
+ "\n",
+ "if not train_on_gpu:\n",
+ " print(\"CUDA is not available. Training on CPU ...\")\n",
+ "else:\n",
+ " print(\"CUDA is available! Training on GPU ...\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "5cf214eb",
+ "metadata": {},
+ "source": [
+ "Next we load the CIFAR10 dataset"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "462666a2",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import numpy as np\n",
+ "from torchvision import datasets, transforms\n",
+ "from torch.utils.data.sampler import SubsetRandomSampler\n",
+ "\n",
+ "# number of subprocesses to use for data loading\n",
+ "num_workers = 0\n",
+ "# how many samples per batch to load\n",
+ "batch_size = 20\n",
+ "# percentage of training set to use as validation\n",
+ "valid_size = 0.2\n",
+ "\n",
+ "# convert data to a normalized torch.FloatTensor\n",
+ "transform = transforms.Compose(\n",
+ " [transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]\n",
+ ")\n",
+ "\n",
+ "# choose the training and test datasets\n",
+ "train_data = datasets.CIFAR10(\"data\", train=True, download=True, transform=transform)\n",
+ "test_data = datasets.CIFAR10(\"data\", train=False, download=True, transform=transform)\n",
+ "\n",
+ "# obtain training indices that will be used for validation\n",
+ "num_train = len(train_data)\n",
+ "indices = list(range(num_train))\n",
+ "np.random.shuffle(indices)\n",
+ "split = int(np.floor(valid_size * num_train))\n",
+ "train_idx, valid_idx = indices[split:], indices[:split]\n",
+ "\n",
+ "# define samplers for obtaining training and validation batches\n",
+ "train_sampler = SubsetRandomSampler(train_idx)\n",
+ "valid_sampler = SubsetRandomSampler(valid_idx)\n",
+ "\n",
+ "# prepare data loaders (combine dataset and sampler)\n",
+ "train_loader = torch.utils.data.DataLoader(\n",
+ " train_data, batch_size=batch_size, sampler=train_sampler, num_workers=num_workers\n",
+ ")\n",
+ "valid_loader = torch.utils.data.DataLoader(\n",
+ " train_data, batch_size=batch_size, sampler=valid_sampler, num_workers=num_workers\n",
+ ")\n",
+ "test_loader = torch.utils.data.DataLoader(\n",
+ " test_data, batch_size=batch_size, num_workers=num_workers\n",
+ ")\n",
+ "\n",
+ "# specify the image classes\n",
+ "classes = [\n",
+ " \"airplane\",\n",
+ " \"automobile\",\n",
+ " \"bird\",\n",
+ " \"cat\",\n",
+ " \"deer\",\n",
+ " \"dog\",\n",
+ " \"frog\",\n",
+ " \"horse\",\n",
+ " \"ship\",\n",
+ " \"truck\",\n",
+ "]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "58ec3903",
+ "metadata": {},
+ "source": [
+ "CNN definition (this one is an example)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "317bf070",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import torch.nn as nn\n",
+ "import torch.nn.functional as F\n",
+ "\n",
+ "# define the CNN architecture\n",
+ "\n",
+ "\n",
+ "class Net(nn.Module):\n",
+ " def __init__(self):\n",
+ " super(Net, self).__init__()\n",
+ " self.conv1 = nn.Conv2d(3, 6, 5)\n",
+ " self.pool = nn.MaxPool2d(2, 2)\n",
+ " self.conv2 = nn.Conv2d(6, 16, 5)\n",
+ " self.fc1 = nn.Linear(16 * 5 * 5, 120)\n",
+ " self.fc2 = nn.Linear(120, 84)\n",
+ " self.fc3 = nn.Linear(84, 10)\n",
+ "\n",
+ " def forward(self, x):\n",
+ " x = self.pool(F.relu(self.conv1(x)))\n",
+ " x = self.pool(F.relu(self.conv2(x)))\n",
+ " x = x.view(-1, 16 * 5 * 5)\n",
+ " x = F.relu(self.fc1(x))\n",
+ " x = F.relu(self.fc2(x))\n",
+ " x = self.fc3(x)\n",
+ " return x\n",
+ "\n",
+ "\n",
+ "# create a complete CNN\n",
+ "model = Net()\n",
+ "print(model)\n",
+ "# move tensors to GPU if CUDA is available\n",
+ "if train_on_gpu:\n",
+ " model.cuda()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "a2dc4974",
+ "metadata": {},
+ "source": [
+ "Loss function and training using SGD (Stochastic Gradient Descent) optimizer"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "4b53f229",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import torch.optim as optim\n",
+ "\n",
+ "criterion = nn.CrossEntropyLoss() # specify loss function\n",
+ "optimizer = optim.SGD(model.parameters(), lr=0.01) # specify optimizer\n",
+ "\n",
+ "n_epochs = 30 # number of epochs to train the model\n",
+ "train_loss_list = [] # list to store loss to visualize\n",
+ "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",
+ " model.train()\n",
+ " for data, target in train_loader:\n",
+ " # Move tensors to GPU if CUDA is available\n",
+ " if train_on_gpu:\n",
+ " data, target = data.cuda(), target.cuda()\n",
+ " # Clear the gradients of all optimized variables\n",
+ " optimizer.zero_grad()\n",
+ " # Forward pass: compute predicted outputs by passing inputs to the model\n",
+ " output = model(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.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(data)\n",
+ " # Calculate the batch loss\n",
+ " loss = criterion(output, target)\n",
+ " # Update average validation loss\n",
+ " valid_loss += loss.item() * data.size(0)\n",
+ "\n",
+ " # Calculate average losses\n",
+ " train_loss = train_loss / len(train_loader)\n",
+ " valid_loss = valid_loss / len(valid_loader)\n",
+ " train_loss_list.append(train_loss)\n",
+ "\n",
+ " # Print training/validation statistics\n",
+ " print(\n",
+ " \"Epoch: {} \\tTraining Loss: {:.6f} \\tValidation Loss: {:.6f}\".format(\n",
+ " epoch, train_loss, valid_loss\n",
+ " )\n",
+ " )\n",
+ "\n",
+ " # Save model if validation loss has decreased\n",
+ " if valid_loss <= valid_loss_min:\n",
+ " print(\n",
+ " \"Validation loss decreased ({:.6f} --> {:.6f}). Saving model ...\".format(\n",
+ " valid_loss_min, valid_loss\n",
+ " )\n",
+ " )\n",
+ " torch.save(model.state_dict(), \"model_cifar.pt\")\n",
+ " valid_loss_min = valid_loss"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "13e1df74",
+ "metadata": {},
+ "source": [
+ "Does overfit occur? If so, do an early stopping."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "d39df818",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import matplotlib.pyplot as plt\n",
+ "\n",
+ "plt.plot(range((len(train_loss_list))), train_loss_list)\n",
+ "plt.xlabel(\"Epoch\")\n",
+ "plt.ylabel(\"Loss\")\n",
+ "plt.title(\"Performance of Model 1\")\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "11df8fd4",
+ "metadata": {},
+ "source": [
+ "Now loading the model with the lowest validation loss value\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "e93efdfc",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model.load_state_dict(torch.load(\"./model_cifar.pt\"))\n",
+ "\n",
+ "# track test loss\n",
+ "test_loss = 0.0\n",
+ "class_correct = list(0.0 for i in range(10))\n",
+ "class_total = list(0.0 for i in range(10))\n",
+ "\n",
+ "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 = 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": "944991a2",
+ "metadata": {},
+ "source": [
+ "### Experiments:\n",
+ "\n",
+ "Build a new network with the following structure.\n",
+ "\n",
+ "- It has 3 convolutional layers of kernel size 3 and padding of 1.\n",
+ "- The first convolutional layer must output 16 channels, the second 32 and the third 64.\n",
+ "- At each convolutional layer output, we apply a ReLU activation then a MaxPool with kernel size of 2.\n",
+ "- Then, three fully connected layers, the first two being followed by a ReLU activation.\n",
+ "- The first fully connected layer will have an output size of 512.\n",
+ "- The second fully connected layer will have an output size of 64.\n",
+ "\n",
+ "Compare the results obtained with this new network to those obtained previously."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "201470f9",
+ "metadata": {},
+ "source": [
+ "## Sequence 2: 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": "code",
+ "execution_count": null,
+ "id": "b4d13080",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import json\n",
+ "from PIL import Image\n",
+ "from torchvision import models\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",
+ "\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",
+ "\n",
+ "image = Image.open(test_image)\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",
+ "# 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",
+ "# Get the 1000-dimensional model output\n",
+ "out = model(image)\n",
+ "# Find the predicted class\n",
+ "print(\"Predicted class is: {}\".format(labels[out.argmax()]))"
+ ]
+ },
+ {
+ "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",
+ "Experiment with other pre-trained CNN models.\n",
+ "\n",
+ " \n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "5d57da4b",
+ "metadata": {},
+ "source": [
+ "## Sequence 3: 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": [
+ "import os\n",
+ "\n",
+ "import matplotlib.pyplot as plt\n",
+ "import numpy as np\n",
+ "import torch\n",
+ "import torchvision\n",
+ "from torchvision import datasets, transforms\n",
+ "import torch.nn as nn\n",
+ "import torch.optim as optim\n",
+ "from torch.optim import lr_scheduler\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",
+ "\n",
+ "data_dir = \"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",
+ " 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=0\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",
+ " \"\"\"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"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "bbd48800",
+ "metadata": {},
+ "source": [
+ "Now, execute the following code which uses a pre-trained model ResNet18 having replaced the output layer for the ants/bees classification and performs the model training by only changing the weights of this output layer."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "572d824c",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import copy\n",
+ "import time\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\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",
+ ")\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "bbd48800",
+ "metadata": {},
+ "source": [
+ "### Experiments:\n",
+ "\n",
+ "Study the code and the results obtained.\n",
+ "\n",
+ "Modify the code and add an \"eval_model\" function to allow\n",
+ "the evaluation of the model on a test set (different from the learning and validation sets used during the learning phase). Study the results obtained.\n",
+ "\n",
+ "Now modify the code to replace the current classification layer with a set of two layers using a \"relu\" activation function for the middle layer. Renew the experiments and study the results obtained.\n",
+ "\n",
+ "Experiment with other models and datasets."
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "base",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.9.20"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}