[404218]: / Code / PennyLane / Time Cost Efficiency / TL 44 Class CPU 19.50 Efficiency kkawchak.ipynb

Download this file

782 lines (781 with data), 361.1 kB

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "id": "U8_09H0pzhFZ"
      },
      "outputs": [],
      "source": [
        "# For tips on running notebooks in Google Colab, see\n",
        "# https://pytorch.org/tutorials/beginner/colab\n",
        "%matplotlib inline\n",
        "\n",
        "# from google.colab import drive\n",
        "# drive.mount('/content/drive')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "82ypZxUgzhFd",
        "outputId": "bbe45cda-3f70-4895-c7d7-deecf98ebed8"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<contextlib.ExitStack at 0x7e1d0fb1c670>"
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ],
      "source": [
        "# License: BSD\n",
        "# Author: Sasank Chilamkurthy\n",
        "\n",
        "import torch\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "from torch.optim import lr_scheduler\n",
        "import torch.backends.cudnn as cudnn\n",
        "import numpy as np\n",
        "import torchvision\n",
        "from torchvision import datasets, models, transforms\n",
        "import matplotlib.pyplot as plt\n",
        "import time\n",
        "import os\n",
        "from PIL import Image\n",
        "from tempfile import TemporaryDirectory\n",
        "\n",
        "cudnn.benchmark = True\n",
        "plt.ion()   # interactive mode"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ko98w4r7zhFe"
      },
      "source": [
        "## Load Data\n",
        "\n",
        "We will use torchvision and torch.utils.data packages for loading the\n",
        "data.\n",
        "\n",
        "The problem we're going to solve today is to train a model to classify\n",
        "**ants** and **bees**. We have about 120 training images each for ants and bees.\n",
        "There are 75 validation images for each class. Usually, this is a very\n",
        "small dataset to generalize upon, if trained from scratch. Since we\n",
        "are using transfer learning, we should be able to generalize reasonably\n",
        "well.\n",
        "\n",
        "This dataset is a very small subset of imagenet.\n",
        "\n",
        ".. Note ::\n",
        "   Download the data from\n",
        "   [here](https://download.pytorch.org/tutorial/hymenoptera_data.zip)\n",
        "   and extract it to the current directory.\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "id": "LWDOibNFzhFe"
      },
      "outputs": [],
      "source": [
        "# Data augmentation and normalization for training\n",
        "# Just normalization for validation\n",
        "data_transforms = {\n",
        "    'train': transforms.Compose([\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",
        "    'val': transforms.Compose([\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",
        "data_dir = '/content/drive/MyDrive/Colab Notebooks/data/44 Class 4478 Brain Tumor Images Split 0.627 Shuffle Rename'\n",
        "image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),\n",
        "                                          data_transforms[x])\n",
        "                  for x in ['train', 'val']}\n",
        "dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=17,\n",
        "                                             shuffle=True, num_workers=4)\n",
        "              for x in ['train', 'val']}\n",
        "dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}\n",
        "class_names = image_datasets['train'].classes\n",
        "\n",
        "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "162cgfnXzhFf"
      },
      "source": [
        "### Visualize a few images\n",
        "Let's visualize a few training images so as to understand the data\n",
        "augmentations.\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 289
        },
        "id": "uGGqqCoEzhFf",
        "outputId": "7f98902d-6c8b-499a-804c-fe363af07e27"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "def imshow(inp, title=None):\n",
        "    \"\"\"Display image 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",
        "    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)  # pause a bit so that plots are updated\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])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EtqiyYuNzhFf"
      },
      "source": [
        "## Training the model\n",
        "\n",
        "Now, let's write a general function to train a model. Here, we will\n",
        "illustrate:\n",
        "\n",
        "-  Scheduling the learning rate\n",
        "-  Saving the best model\n",
        "\n",
        "In the following, parameter ``scheduler`` is an LR scheduler object from\n",
        "``torch.optim.lr_scheduler``.\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "id": "9ORJI2wpzhFg"
      },
      "outputs": [],
      "source": [
        "def train_model(model, criterion, optimizer, scheduler, num_epochs=10):\n",
        "    since = time.time()\n",
        "\n",
        "    # Create a temporary directory to save training checkpoints\n",
        "    with TemporaryDirectory() as tempdir:\n",
        "        best_model_params_path = os.path.join(tempdir, 'best_model_params.pt')\n",
        "\n",
        "        torch.save(model.state_dict(), best_model_params_path)\n",
        "        best_acc = 0.0\n",
        "\n",
        "        for epoch in range(num_epochs):\n",
        "            print(f'Epoch {epoch}/{num_epochs - 1}')\n",
        "            print('-' * 10)\n",
        "\n",
        "            # Each epoch has a training and validation phase\n",
        "            for phase in ['train', 'val']:\n",
        "                if phase == 'train':\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 train\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",
        "                if phase == 'train':\n",
        "                    scheduler.step()\n",
        "\n",
        "                epoch_loss = running_loss / dataset_sizes[phase]\n",
        "                epoch_acc = running_corrects.double() / dataset_sizes[phase]\n",
        "\n",
        "                print(f'{phase} Loss: {epoch_loss:.4f} Acc: {epoch_acc:.4f}')\n",
        "\n",
        "                # deep copy the model\n",
        "                if phase == 'val' and epoch_acc > best_acc:\n",
        "                    best_acc = epoch_acc\n",
        "                    torch.save(model.state_dict(), best_model_params_path)\n",
        "\n",
        "            print()\n",
        "\n",
        "        time_elapsed = time.time() - since\n",
        "        print(f'Training complete in {time_elapsed // 60:.0f}m {time_elapsed % 60:.0f}s')\n",
        "        print(f'Best val Acc: {best_acc:4f}')\n",
        "\n",
        "        # load best model weights\n",
        "        model.load_state_dict(torch.load(best_model_params_path))\n",
        "    return model"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6YCmfkSizhFg"
      },
      "source": [
        "### Visualizing the model predictions\n",
        "\n",
        "Generic function to display predictions for a few images\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "id": "JtYakW-kzhFg"
      },
      "outputs": [],
      "source": [
        "def visualize_model(model, num_images=6):\n",
        "    was_training = model.training\n",
        "    model.eval()\n",
        "    images_so_far = 0\n",
        "    fig = plt.figure()\n",
        "\n",
        "    with torch.no_grad():\n",
        "        for i, (inputs, labels) in enumerate(dataloaders['val']):\n",
        "            inputs = inputs.to(device)\n",
        "            labels = labels.to(device)\n",
        "\n",
        "            outputs = model(inputs)\n",
        "            _, preds = torch.max(outputs, 1)\n",
        "\n",
        "            for j in range(inputs.size()[0]):\n",
        "                images_so_far += 1\n",
        "                ax = plt.subplot(num_images//2, 2, images_so_far)\n",
        "                ax.axis('off')\n",
        "                ax.set_title(f'predicted: {class_names[preds[j]]}')\n",
        "                imshow(inputs.cpu().data[j])\n",
        "\n",
        "                if images_so_far == num_images:\n",
        "                    model.train(mode=was_training)\n",
        "                    return\n",
        "        model.train(mode=was_training)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "b9bKXGG7zhFh"
      },
      "source": [
        "## Finetuning the ConvNet\n",
        "\n",
        "Load a pretrained model and reset final fully connected layer.\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "QqkwG_MmzhFh",
        "outputId": "982a958d-a3a8-468f-e5bc-2874dd3e0516"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/resnet50-0676ba61.pth\" to /root/.cache/torch/hub/checkpoints/resnet50-0676ba61.pth\n",
            "100%|██████████| 97.8M/97.8M [00:01<00:00, 69.4MB/s]\n"
          ]
        }
      ],
      "source": [
        "model_ft = models.resnet50(weights='IMAGENET1K_V1')\n",
        "num_ftrs = model_ft.fc.in_features\n",
        "# Here the size of each output sample is set to 2.\n",
        "# Alternatively, it can be generalized to ``nn.Linear(num_ftrs, len(class_names))``.\n",
        "model_ft.fc = nn.Linear(num_ftrs, 44)\n",
        "\n",
        "model_ft = model_ft.to(device)\n",
        "\n",
        "criterion = nn.CrossEntropyLoss()\n",
        "\n",
        "# Observe that all parameters are being optimized\n",
        "optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)\n",
        "\n",
        "# Decay LR by a factor of 0.1 every 7 epochs\n",
        "exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "IJBze7TnzhFh"
      },
      "source": [
        "### Train and evaluate\n",
        "\n",
        "It should take around 15-25 min on CPU. On GPU though, it takes less than a\n",
        "minute.\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "ycl4sxdzzhFh",
        "outputId": "26310e8b-a045-40ae-e563-6477d76c0646"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 0/9\n",
            "----------\n",
            "train Loss: 2.9154 Acc: 0.2618\n",
            "val Loss: 2.1220 Acc: 0.4297\n",
            "\n",
            "Epoch 1/9\n",
            "----------\n",
            "train Loss: 1.9503 Acc: 0.4685\n",
            "val Loss: 1.3712 Acc: 0.6206\n",
            "\n",
            "Epoch 2/9\n",
            "----------\n",
            "train Loss: 1.4989 Acc: 0.5753\n",
            "val Loss: 1.1371 Acc: 0.6667\n",
            "\n",
            "Epoch 3/9\n",
            "----------\n",
            "train Loss: 1.2557 Acc: 0.6519\n",
            "val Loss: 0.9315 Acc: 0.7115\n",
            "\n",
            "Epoch 4/9\n",
            "----------\n",
            "train Loss: 1.0840 Acc: 0.6950\n",
            "val Loss: 0.7908 Acc: 0.7642\n",
            "\n",
            "Epoch 5/9\n",
            "----------\n",
            "train Loss: 0.9350 Acc: 0.7268\n",
            "val Loss: 0.7824 Acc: 0.7648\n",
            "\n",
            "Epoch 6/9\n",
            "----------\n",
            "train Loss: 0.8268 Acc: 0.7670\n",
            "val Loss: 0.6462 Acc: 0.8109\n",
            "\n",
            "Epoch 7/9\n",
            "----------\n",
            "train Loss: 0.7013 Acc: 0.8137\n",
            "val Loss: 0.5207 Acc: 0.8492\n",
            "\n",
            "Epoch 8/9\n",
            "----------\n",
            "train Loss: 0.6500 Acc: 0.8336\n",
            "val Loss: 0.5067 Acc: 0.8516\n",
            "\n",
            "Epoch 9/9\n",
            "----------\n",
            "train Loss: 0.6132 Acc: 0.8418\n",
            "val Loss: 0.5082 Acc: 0.8498\n",
            "\n",
            "Training complete in 99m 14s\n",
            "Best val Acc: 0.851586\n"
          ]
        }
      ],
      "source": [
        "model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,\n",
        "                       num_epochs=10)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "id": "c80qeSpIzhFi",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 923
        },
        "outputId": "c98bced8-c4b4-4f01-ee6c-56a01126932e"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "visualize_model(model_ft)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vJTTbA44zhFi"
      },
      "source": [
        "## ConvNet as fixed feature extractor\n",
        "\n",
        "Here, we need to freeze all the network except the final layer. We need\n",
        "to set ``requires_grad = False`` to freeze the parameters so that the\n",
        "gradients are not computed in ``backward()``.\n",
        "\n",
        "You can read more about this in the documentation\n",
        "[here](https://pytorch.org/docs/notes/autograd.html#excluding-subgraphs-from-backward)_.\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "id": "EJnsmCCozhFi"
      },
      "outputs": [],
      "source": [
        "model_conv = torchvision.models.resnet50(weights='IMAGENET1K_V1')\n",
        "for param in model_conv.parameters():\n",
        "    param.requires_grad = False\n",
        "\n",
        "# Parameters of newly constructed modules have requires_grad=True by default\n",
        "num_ftrs = model_conv.fc.in_features\n",
        "model_conv.fc = nn.Linear(num_ftrs, 44)\n",
        "\n",
        "model_conv = model_conv.to(device)\n",
        "\n",
        "criterion = nn.CrossEntropyLoss()\n",
        "\n",
        "# Observe that only parameters of final layer are being optimized as\n",
        "# opposed to before.\n",
        "optimizer_conv = optim.SGD(model_conv.fc.parameters(), lr=0.001, momentum=0.9)\n",
        "\n",
        "# Decay LR by a factor of 0.1 every 7 epochs\n",
        "exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "dUP9Jp1EzhFi"
      },
      "source": [
        "### Train and evaluate\n",
        "\n",
        "On CPU this will take about half the time compared to previous scenario.\n",
        "This is expected as gradients don't need to be computed for most of the\n",
        "network. However, forward does need to be computed.\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "metadata": {
        "id": "E3W00L61zhFi",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 500
        },
        "outputId": "ae05511d-f2ca-47bd-f93e-720b4d76d1ce"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 0/9\n",
            "----------\n",
            "train Loss: 3.2638 Acc: 0.1664\n",
            "val Loss: 2.8623 Acc: 0.2591\n",
            "\n",
            "Epoch 1/9\n",
            "----------\n",
            "train Loss: 2.8310 Acc: 0.2854\n"
          ]
        },
        {
          "output_type": "error",
          "ename": "KeyboardInterrupt",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-12-ebe829d78418>\u001b[0m in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m model_conv = train_model(model_conv, criterion, optimizer_conv,\n\u001b[0m\u001b[1;32m      2\u001b[0m                          exp_lr_scheduler, num_epochs=10)\n",
            "\u001b[0;32m<ipython-input-6-5dea89373802>\u001b[0m in \u001b[0;36mtrain_model\u001b[0;34m(model, criterion, optimizer, scheduler, num_epochs)\u001b[0m\n\u001b[1;32m     34\u001b[0m                     \u001b[0;31m# track history if only in train\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     35\u001b[0m                     \u001b[0;32mwith\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_grad_enabled\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mphase\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m'train'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 36\u001b[0;31m                         \u001b[0moutputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     37\u001b[0m                         \u001b[0m_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpreds\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmax\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     38\u001b[0m                         \u001b[0mloss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcriterion\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1499\u001b[0m                 \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1500\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1501\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1502\u001b[0m         \u001b[0;31m# Do not call functions when jit is used\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1503\u001b[0m         \u001b[0mfull_backward_hooks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnon_full_backward_hooks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torchvision/models/resnet.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m    283\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    284\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mTensor\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mTensor\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 285\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_forward_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    286\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    287\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torchvision/models/resnet.py\u001b[0m in \u001b[0;36m_forward_impl\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m    272\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    273\u001b[0m         \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlayer1\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 274\u001b[0;31m         \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlayer2\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    275\u001b[0m         \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlayer3\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    276\u001b[0m         \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlayer4\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1499\u001b[0m                 \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1500\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1501\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1502\u001b[0m         \u001b[0;31m# Do not call functions when jit is used\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1503\u001b[0m         \u001b[0mfull_backward_hooks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnon_full_backward_hooks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/container.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    215\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    216\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0mmodule\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 217\u001b[0;31m             \u001b[0minput\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodule\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    218\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    219\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1499\u001b[0m                 \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1500\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1501\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1502\u001b[0m         \u001b[0;31m# Do not call functions when jit is used\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1503\u001b[0m         \u001b[0mfull_backward_hooks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnon_full_backward_hooks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torchvision/models/resnet.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m    144\u001b[0m         \u001b[0midentity\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    145\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 146\u001b[0;31m         \u001b[0mout\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconv1\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    147\u001b[0m         \u001b[0mout\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbn1\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    148\u001b[0m         \u001b[0mout\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrelu\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1499\u001b[0m                 \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1500\u001b[0m                 or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1501\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1502\u001b[0m         \u001b[0;31m# Do not call functions when jit is used\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1503\u001b[0m         \u001b[0mfull_backward_hooks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnon_full_backward_hooks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    461\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    462\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mTensor\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mTensor\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 463\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_conv_forward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mweight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbias\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    464\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    465\u001b[0m \u001b[0;32mclass\u001b[0m \u001b[0mConv3d\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_ConvNd\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py\u001b[0m in \u001b[0;36m_conv_forward\u001b[0;34m(self, input, weight, bias)\u001b[0m\n\u001b[1;32m    457\u001b[0m                             \u001b[0mweight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbias\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstride\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    458\u001b[0m                             _pair(0), self.dilation, self.groups)\n\u001b[0;32m--> 459\u001b[0;31m         return F.conv2d(input, weight, bias, self.stride,\n\u001b[0m\u001b[1;32m    460\u001b[0m                         self.padding, self.dilation, self.groups)\n\u001b[1;32m    461\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
          ]
        }
      ],
      "source": [
        "model_conv = train_model(model_conv, criterion, optimizer_conv,\n",
        "                         exp_lr_scheduler, num_epochs=10)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "xI_eFV3rzhFj"
      },
      "outputs": [],
      "source": [
        "visualize_model(model_conv)\n",
        "\n",
        "plt.ioff()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "oGyX6XpFzhFj"
      },
      "source": [
        "## Inference on custom images\n",
        "\n",
        "Use the trained model to make predictions on custom images and visualize\n",
        "the predicted class labels along with the images.\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "PSVIq1DLzhFj"
      },
      "outputs": [],
      "source": [
        "def visualize_model_predictions(model,img_path):\n",
        "    was_training = model.training\n",
        "    model.eval()\n",
        "\n",
        "    img = Image.open(img_path)\n",
        "    img = data_transforms['val'](img)\n",
        "    img = img.unsqueeze(0)\n",
        "    img = img.to(device)\n",
        "\n",
        "    with torch.no_grad():\n",
        "        outputs = model(img)\n",
        "        _, preds = torch.max(outputs, 1)\n",
        "\n",
        "        ax = plt.subplot(2,2,1)\n",
        "        ax.axis('off')\n",
        "        ax.set_title(f'Predicted: {class_names[preds[0]]}')\n",
        "        imshow(img.cpu().data[0])\n",
        "\n",
        "        model.train(mode=was_training)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "5vggKlbTzhFj"
      },
      "outputs": [],
      "source": [
        "visualize_model_predictions(\n",
        "    model_conv,\n",
        "    img_path='/content/drive/MyDrive/Colab Notebooks/data/44 Class 4478 Brain Tumor Images Split 0.627 Shuffle Rename/val/Astrocitoma T1C+/150 - IMG-0007-00014_big_gallery.jpeg'\n",
        ")\n",
        "\n",
        "plt.ioff()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "HtpVRKGBzhFj"
      },
      "source": [
        "## Further Learning\n",
        "\n",
        "If you would like to learn more about the applications of transfer learning,\n",
        "checkout our [Quantized Transfer Learning for Computer Vision Tutorial](https://pytorch.org/tutorials/intermediate/quantized_transfer_learning_tutorial.html).\n",
        "\n",
        "\n",
        "\n"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "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": "3.10.12"
    },
    "colab": {
      "provenance": [],
      "machine_shape": "hm"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}