center_crop_pytorch.ipynb

center_crop_pytorch.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "center_crop_pytorch.ipynb",
      "private_outputs": true,
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyNZKjQBZ+CftFRO+N5GNybc",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/vinothpandian/0bbeed954dade522d020d04186f7b6f2/center_crop_pytorch.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "9PqgsCzeUEO7"
      },
      "outputs": [],
      "source": [
        "import torch\n",
        "import torchvision\n",
        "\n",
        "import matplotlib.pyplot as plt"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset = torchvision.datasets.FashionMNIST(\n",
        "    root=\"data\",\n",
        "    train=True,\n",
        "    download=True,\n",
        "    transform=torchvision.transforms.ToTensor()\n",
        ")\n",
        "\n",
        "dataloader = torch.utils.data.DataLoader(dataset, batch_size=8, shuffle=True)"
      ],
      "metadata": {
        "id": "OYkjwV-vke_7"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "img_batch, _ = next(iter(dataloader))"
      ],
      "metadata": {
        "id": "ebBok7Vil1lM"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def show_grid(img_batch):\n",
        "    print(img_batch.shape)\n",
        "    img = torchvision.utils.make_grid(img_batch, nrow=4)\n",
        "    plt.imshow(img.permute(1, 2, 0))"
      ],
      "metadata": {
        "id": "A8TDRXvamBXt"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "show_grid(img_batch)"
      ],
      "metadata": {
        "id": "DHIrkDaJnueG"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Center crop image"
      ],
      "metadata": {
        "id": "RindpqrRe7yx"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "center_cropped_img_batch = torchvision.transforms.functional.center_crop(img_batch, 14)\n",
        "show_grid(center_cropped_img_batch)"
      ],
      "metadata": {
        "id": "ZcamZmd1edAp"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "transform = torchvision.transforms.CenterCrop(14)\n",
        "show_grid(transform(img_batch))"
      ],
      "metadata": {
        "id": "UmWwRG6XqITZ"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}