{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "# For tips on running notebooks in Google Colab, see\n# https://pytorch.org/tutorials/beginner/colab\n%matplotlib inline"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "[Learn the Basics](intro.html) \\|\\|\n[Quickstart](quickstart_tutorial.html) \\|\\|\n[Tensors](tensorqs_tutorial.html) \\|\\| [Datasets &\nDataLoaders](data_tutorial.html) \\|\\| **Transforms** \\|\\| [Build\nModel](buildmodel_tutorial.html) \\|\\|\n[Autograd](autogradqs_tutorial.html) \\|\\|\n[Optimization](optimization_tutorial.html) \\|\\| [Save & Load\nModel](saveloadrun_tutorial.html)\n\nTransforms\n==========\n\nData does not always come in its final processed form that is required\nfor training machine learning algorithms. We use **transforms** to\nperform some manipulation of the data and make it suitable for training.\n\nAll TorchVision datasets have two parameters -`transform` to modify the\nfeatures and `target_transform` to modify the labels - that accept\ncallables containing the transformation logic. The\n[torchvision.transforms](https://pytorch.org/vision/stable/transforms.html)\nmodule offers several commonly-used transforms out of the box.\n\nThe FashionMNIST features are in PIL Image format, and the labels are\nintegers. For training, we need the features as normalized tensors, and\nthe labels as one-hot encoded tensors. To make these transformations, we\nuse `ToTensor` and `Lambda`.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "import torch\nfrom torchvision import datasets\nfrom torchvision.transforms import ToTensor, Lambda\n\nds = datasets.FashionMNIST(\n    root=\"data\",\n    train=True,\n    download=True,\n    transform=ToTensor(),\n    target_transform=Lambda(lambda y: torch.zeros(10, dtype=torch.float).scatter_(0, torch.tensor(y), value=1))\n)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "ToTensor()\n==========\n\n[ToTensor](https://pytorch.org/vision/stable/transforms.html#torchvision.transforms.ToTensor)\nconverts a PIL image or NumPy `ndarray` into a `FloatTensor`. and scales\nthe image\\'s pixel intensity values in the range \\[0., 1.\\]\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Lambda Transforms\n=================\n\nLambda transforms apply any user-defined lambda function. Here, we\ndefine a function to turn the integer into a one-hot encoded tensor. It\nfirst creates a zero tensor of size 10 (the number of labels in our\ndataset) and calls\n[scatter\\_](https://pytorch.org/docs/stable/generated/torch.Tensor.scatter_.html)\nwhich assigns a `value=1` on the index as given by the label `y`.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "target_transform = Lambda(lambda y: torch.zeros(\n    10, dtype=torch.float).scatter_(dim=0, index=torch.tensor(y), value=1))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "------------------------------------------------------------------------\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Further Reading\n===============\n\n-   [torchvision.transforms\n    API](https://pytorch.org/vision/stable/transforms.html)\n"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "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": "3.10.12"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}