Computer_Vision/Chapter05/Implementing_VGG16_for_image_classification.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Implementing_VGG16_for_image_classification.ipynb",
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/PacktPublishing/Hands-On-Computer-Vision-with-PyTorch/blob/master/Chapter05/Implementing_VGG16_for_image_classification.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "X1mQ8Y9ERCpa"
      },
      "source": [
        "import torchvision\n",
        "import torch.nn as nn\n",
        "import torch\n",
        "import torch.nn.functional as F\n",
        "from torchvision import transforms,models,datasets\n",
        "import matplotlib.pyplot as plt\n",
        "from PIL import Image\n",
        "import numpy as np\n",
        "from torch import optim\n",
        "device = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
        "import cv2, glob, numpy as np, pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "from glob import glob\n",
        "import torchvision.transforms as transforms\n",
        "from torch.utils.data import DataLoader, Dataset"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CQcFhpxVRNev",
        "outputId": "87230d9b-ab1d-4b8e-ab5f-f2b0a916c338",
        "colab": {
          "resources": {
            "http://localhost:8080/nbextensions/google.colab/files.js": {
              "data": "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",
              "ok": true,
              "headers": [
                [
                  "content-type",
                  "application/javascript"
                ]
              ],
              "status": 200,
              "status_text": ""
            }
          },
          "base_uri": "https://localhost:8080/",
          "height": 91
        }
      },
      "source": [
        "!pip install -q kaggle\n",
        "from google.colab import files\n",
        "files.upload()\n",
        "!mkdir -p ~/.kaggle\n",
        "!cp kaggle.json ~/.kaggle/\n",
        "!ls ~/.kaggle\n",
        "!chmod 600 /root/.kaggle/kaggle.json"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-954feacf-38d2-4ef8-8541-5b2f2491ae93\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-954feacf-38d2-4ef8-8541-5b2f2491ae93\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script src=\"/nbextensions/google.colab/files.js\"></script> "
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Saving kaggle.json to kaggle.json\n",
            "kaggle.json\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FAYvATjiRPep"
      },
      "source": [
        "!kaggle datasets download -d tongpython/cat-and-dog\n",
        "!unzip cat-and-dog.zip"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "nCvdJ9U-RWb3"
      },
      "source": [
        "train_data_dir = 'training_set/training_set'\n",
        "test_data_dir = 'test_set/test_set'"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NDfNnADpRYAV"
      },
      "source": [
        "class CatsDogs(Dataset):\n",
        "    def __init__(self, folder):\n",
        "        cats = glob(folder+'/cats/*.jpg')\n",
        "        dogs = glob(folder+'/dogs/*.jpg')\n",
        "        self.fpaths = cats[:500] + dogs[:500]\n",
        "        self.normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225])\n",
        "        from random import shuffle, seed; seed(10); shuffle(self.fpaths)\n",
        "        self.targets = [fpath.split('/')[-1].startswith('dog') for fpath in self.fpaths] \n",
        "    def __len__(self): return len(self.fpaths)\n",
        "    def __getitem__(self, ix):\n",
        "        f = self.fpaths[ix]\n",
        "        target = self.targets[ix]\n",
        "        im = (cv2.imread(f)[:,:,::-1])\n",
        "        im = cv2.resize(im, (224,224))\n",
        "        im = torch.tensor(im/255)\n",
        "        im = im.permute(2,0,1)\n",
        "        im = self.normalize(im) \n",
        "        return im.float().to(device), torch.tensor([target]).float().to(device)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-90fyHONRah5"
      },
      "source": [
        "data = CatsDogs(train_data_dir)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4VvoZixHRcNM",
        "outputId": "3cc48845-a8b7-432e-cc4a-1e64eab13e58",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 305
        }
      },
      "source": [
        "im, label = data[200]\n",
        "plt.imshow(im.permute(1,2,0).cpu())\n",
        "print(label)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "tensor([0.], device='cuda:0')\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JwhHv9VYRfhj"
      },
      "source": [
        "def get_model():\n",
        "    model = models.vgg16(pretrained=True)\n",
        "    for param in model.parameters():\n",
        "        param.requires_grad = False\n",
        "    model.avgpool = nn.AdaptiveAvgPool2d(output_size=(1,1))\n",
        "    model.classifier = nn.Sequential(nn.Flatten(),\n",
        "    nn.Linear(512, 128),\n",
        "    nn.ReLU(),\n",
        "    nn.Dropout(0.2),\n",
        "    nn.Linear(128, 1),\n",
        "    nn.Sigmoid())\n",
        "    loss_fn = nn.BCELoss()\n",
        "    optimizer = torch.optim.Adam(model.parameters(), lr= 1e-3)\n",
        "    return model.to(device), loss_fn, optimizer"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WEodSA2URqK8",
        "outputId": "6b602eff-94f6-4013-bde2-531571b75349",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        }
      },
      "source": [
        "!pip install torch_summary\n",
        "from torchsummary import summary\n",
        "model, criterion, optimizer = get_model()\n",
        "summary(model, torch.zeros(1,3,224,224))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Requirement already satisfied: torch_summary in /usr/local/lib/python3.6/dist-packages (1.4.3)\n",
            "==========================================================================================\n",
            "Layer (type:depth-idx)                   Output Shape              Param #\n",
            "==========================================================================================\n",
            "├─Sequential: 1-1                        [-1, 512, 7, 7]           --\n",
            "|    └─Conv2d: 2-1                       [-1, 64, 224, 224]        (1,792)\n",
            "|    └─ReLU: 2-2                         [-1, 64, 224, 224]        --\n",
            "|    └─Conv2d: 2-3                       [-1, 64, 224, 224]        (36,928)\n",
            "|    └─ReLU: 2-4                         [-1, 64, 224, 224]        --\n",
            "|    └─MaxPool2d: 2-5                    [-1, 64, 112, 112]        --\n",
            "|    └─Conv2d: 2-6                       [-1, 128, 112, 112]       (73,856)\n",
            "|    └─ReLU: 2-7                         [-1, 128, 112, 112]       --\n",
            "|    └─Conv2d: 2-8                       [-1, 128, 112, 112]       (147,584)\n",
            "|    └─ReLU: 2-9                         [-1, 128, 112, 112]       --\n",
            "|    └─MaxPool2d: 2-10                   [-1, 128, 56, 56]         --\n",
            "|    └─Conv2d: 2-11                      [-1, 256, 56, 56]         (295,168)\n",
            "|    └─ReLU: 2-12                        [-1, 256, 56, 56]         --\n",
            "|    └─Conv2d: 2-13                      [-1, 256, 56, 56]         (590,080)\n",
            "|    └─ReLU: 2-14                        [-1, 256, 56, 56]         --\n",
            "|    └─Conv2d: 2-15                      [-1, 256, 56, 56]         (590,080)\n",
            "|    └─ReLU: 2-16                        [-1, 256, 56, 56]         --\n",
            "|    └─MaxPool2d: 2-17                   [-1, 256, 28, 28]         --\n",
            "|    └─Conv2d: 2-18                      [-1, 512, 28, 28]         (1,180,160)\n",
            "|    └─ReLU: 2-19                        [-1, 512, 28, 28]         --\n",
            "|    └─Conv2d: 2-20                      [-1, 512, 28, 28]         (2,359,808)\n",
            "|    └─ReLU: 2-21                        [-1, 512, 28, 28]         --\n",
            "|    └─Conv2d: 2-22                      [-1, 512, 28, 28]         (2,359,808)\n",
            "|    └─ReLU: 2-23                        [-1, 512, 28, 28]         --\n",
            "|    └─MaxPool2d: 2-24                   [-1, 512, 14, 14]         --\n",
            "|    └─Conv2d: 2-25                      [-1, 512, 14, 14]         (2,359,808)\n",
            "|    └─ReLU: 2-26                        [-1, 512, 14, 14]         --\n",
            "|    └─Conv2d: 2-27                      [-1, 512, 14, 14]         (2,359,808)\n",
            "|    └─ReLU: 2-28                        [-1, 512, 14, 14]         --\n",
            "|    └─Conv2d: 2-29                      [-1, 512, 14, 14]         (2,359,808)\n",
            "|    └─ReLU: 2-30                        [-1, 512, 14, 14]         --\n",
            "|    └─MaxPool2d: 2-31                   [-1, 512, 7, 7]           --\n",
            "├─AdaptiveAvgPool2d: 1-2                 [-1, 512, 1, 1]           --\n",
            "├─Sequential: 1-3                        [-1, 1]                   --\n",
            "|    └─Flatten: 2-32                     [-1, 512]                 --\n",
            "|    └─Linear: 2-33                      [-1, 128]                 65,664\n",
            "|    └─ReLU: 2-34                        [-1, 128]                 --\n",
            "|    └─Dropout: 2-35                     [-1, 128]                 --\n",
            "|    └─Linear: 2-36                      [-1, 1]                   129\n",
            "|    └─Sigmoid: 2-37                     [-1, 1]                   --\n",
            "==========================================================================================\n",
            "Total params: 14,780,481\n",
            "Trainable params: 65,793\n",
            "Non-trainable params: 14,714,688\n",
            "Total mult-adds (G): 15.36\n",
            "==========================================================================================\n",
            "Input size (MB): 0.57\n",
            "Forward/backward pass size (MB): 103.36\n",
            "Params size (MB): 56.38\n",
            "Estimated Total Size (MB): 160.32\n",
            "==========================================================================================\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "==========================================================================================\n",
              "Layer (type:depth-idx)                   Output Shape              Param #\n",
              "==========================================================================================\n",
              "├─Sequential: 1-1                        [-1, 512, 7, 7]           --\n",
              "|    └─Conv2d: 2-1                       [-1, 64, 224, 224]        (1,792)\n",
              "|    └─ReLU: 2-2                         [-1, 64, 224, 224]        --\n",
              "|    └─Conv2d: 2-3                       [-1, 64, 224, 224]        (36,928)\n",
              "|    └─ReLU: 2-4                         [-1, 64, 224, 224]        --\n",
              "|    └─MaxPool2d: 2-5                    [-1, 64, 112, 112]        --\n",
              "|    └─Conv2d: 2-6                       [-1, 128, 112, 112]       (73,856)\n",
              "|    └─ReLU: 2-7                         [-1, 128, 112, 112]       --\n",
              "|    └─Conv2d: 2-8                       [-1, 128, 112, 112]       (147,584)\n",
              "|    └─ReLU: 2-9                         [-1, 128, 112, 112]       --\n",
              "|    └─MaxPool2d: 2-10                   [-1, 128, 56, 56]         --\n",
              "|    └─Conv2d: 2-11                      [-1, 256, 56, 56]         (295,168)\n",
              "|    └─ReLU: 2-12                        [-1, 256, 56, 56]         --\n",
              "|    └─Conv2d: 2-13                      [-1, 256, 56, 56]         (590,080)\n",
              "|    └─ReLU: 2-14                        [-1, 256, 56, 56]         --\n",
              "|    └─Conv2d: 2-15                      [-1, 256, 56, 56]         (590,080)\n",
              "|    └─ReLU: 2-16                        [-1, 256, 56, 56]         --\n",
              "|    └─MaxPool2d: 2-17                   [-1, 256, 28, 28]         --\n",
              "|    └─Conv2d: 2-18                      [-1, 512, 28, 28]         (1,180,160)\n",
              "|    └─ReLU: 2-19                        [-1, 512, 28, 28]         --\n",
              "|    └─Conv2d: 2-20                      [-1, 512, 28, 28]         (2,359,808)\n",
              "|    └─ReLU: 2-21                        [-1, 512, 28, 28]         --\n",
              "|    └─Conv2d: 2-22                      [-1, 512, 28, 28]         (2,359,808)\n",
              "|    └─ReLU: 2-23                        [-1, 512, 28, 28]         --\n",
              "|    └─MaxPool2d: 2-24                   [-1, 512, 14, 14]         --\n",
              "|    └─Conv2d: 2-25                      [-1, 512, 14, 14]         (2,359,808)\n",
              "|    └─ReLU: 2-26                        [-1, 512, 14, 14]         --\n",
              "|    └─Conv2d: 2-27                      [-1, 512, 14, 14]         (2,359,808)\n",
              "|    └─ReLU: 2-28                        [-1, 512, 14, 14]         --\n",
              "|    └─Conv2d: 2-29                      [-1, 512, 14, 14]         (2,359,808)\n",
              "|    └─ReLU: 2-30                        [-1, 512, 14, 14]         --\n",
              "|    └─MaxPool2d: 2-31                   [-1, 512, 7, 7]           --\n",
              "├─AdaptiveAvgPool2d: 1-2                 [-1, 512, 1, 1]           --\n",
              "├─Sequential: 1-3                        [-1, 1]                   --\n",
              "|    └─Flatten: 2-32                     [-1, 512]                 --\n",
              "|    └─Linear: 2-33                      [-1, 128]                 65,664\n",
              "|    └─ReLU: 2-34                        [-1, 128]                 --\n",
              "|    └─Dropout: 2-35                     [-1, 128]                 --\n",
              "|    └─Linear: 2-36                      [-1, 1]                   129\n",
              "|    └─Sigmoid: 2-37                     [-1, 1]                   --\n",
              "==========================================================================================\n",
              "Total params: 14,780,481\n",
              "Trainable params: 65,793\n",
              "Non-trainable params: 14,714,688\n",
              "Total mult-adds (G): 15.36\n",
              "==========================================================================================\n",
              "Input size (MB): 0.57\n",
              "Forward/backward pass size (MB): 103.36\n",
              "Params size (MB): 56.38\n",
              "Estimated Total Size (MB): 160.32\n",
              "=========================================================================================="
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "wRSbFt3BRr5B"
      },
      "source": [
        "def train_batch(x, y, model, opt, loss_fn):\n",
        "    model.train()\n",
        "    prediction = model(x)\n",
        "    batch_loss = loss_fn(prediction, y)\n",
        "    batch_loss.backward()\n",
        "    optimizer.step()\n",
        "    optimizer.zero_grad()\n",
        "    return batch_loss.item()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Fp2yASc_RuO2"
      },
      "source": [
        "@torch.no_grad()\n",
        "def accuracy(x, y, model):\n",
        "    model.eval()\n",
        "    prediction = model(x)\n",
        "    is_correct = (prediction > 0.5) == y\n",
        "    return is_correct.cpu().numpy().tolist()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tbOeDzCPSVfj"
      },
      "source": [
        "def get_data():\n",
        "    train = CatsDogs(train_data_dir)\n",
        "    trn_dl = DataLoader(train, batch_size=32, shuffle=True, drop_last = True)\n",
        "    val = CatsDogs(test_data_dir)\n",
        "    val_dl = DataLoader(val, batch_size=32, shuffle=True, drop_last = True)\n",
        "    return trn_dl, val_dl"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "hz7QoetLSXNI"
      },
      "source": [
        "trn_dl, val_dl = get_data()\n",
        "model, loss_fn, optimizer = get_model()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "X_vtpUGRSYvZ",
        "outputId": "342455c8-4da3-49c4-cec3-62b1e04aeb60",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 108
        }
      },
      "source": [
        "train_losses, train_accuracies = [], []\n",
        "val_accuracies = []\n",
        "for epoch in range(5):\n",
        "    print(f\" epoch {epoch + 1}/5\")\n",
        "    train_epoch_losses, train_epoch_accuracies = [], []\n",
        "    val_epoch_accuracies = []\n",
        "\n",
        "    for ix, batch in enumerate(iter(trn_dl)):\n",
        "        x, y = batch\n",
        "        batch_loss = train_batch(x, y, model, optimizer, loss_fn)\n",
        "        train_epoch_losses.append(batch_loss) \n",
        "    train_epoch_loss = np.array(train_epoch_losses).mean()\n",
        "\n",
        "    for ix, batch in enumerate(iter(trn_dl)):\n",
        "        x, y = batch\n",
        "        is_correct = accuracy(x, y, model)\n",
        "        train_epoch_accuracies.extend(is_correct)\n",
        "    train_epoch_accuracy = np.mean(train_epoch_accuracies)\n",
        "\n",
        "    for ix, batch in enumerate(iter(val_dl)):\n",
        "        x, y = batch\n",
        "        val_is_correct = accuracy(x, y, model)\n",
        "        val_epoch_accuracies.extend(val_is_correct)\n",
        "    val_epoch_accuracy = np.mean(val_epoch_accuracies)\n",
        "\n",
        "    train_losses.append(train_epoch_loss)\n",
        "    train_accuracies.append(train_epoch_accuracy)\n",
        "    val_accuracies.append(val_epoch_accuracy)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            " epoch 1/5\n",
            " epoch 2/5\n",
            " epoch 3/5\n",
            " epoch 4/5\n",
            " epoch 5/5\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5aFfpJGZSb5v",
        "outputId": "017f433d-0176-4144-b2a3-42d883f28fa3",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 310
        }
      },
      "source": [
        "epochs = np.arange(5)+1\n",
        "import matplotlib.ticker as mtick\n",
        "import matplotlib.pyplot as plt\n",
        "import matplotlib.ticker as mticker\n",
        "%matplotlib inline\n",
        "plt.plot(epochs, train_accuracies, 'bo', label='Training accuracy')\n",
        "plt.plot(epochs, val_accuracies, 'r', label='Validation accuracy')\n",
        "plt.gca().xaxis.set_major_locator(mticker.MultipleLocator(1))\n",
        "plt.title('Training and validation accuracy with VGG16 \\nand 1K training data points')\n",
        "plt.xlabel('Epochs')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.ylim(0.95,1)\n",
        "plt.gca().set_yticklabels(['{:.0f}%'.format(x*100) for x in plt.gca().get_yticks()]) \n",
        "plt.legend()\n",
        "plt.grid('off')\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jc88Ywn8TA67"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}