{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# 3.5 图像分类数据集（Fashion-MNIST）" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.4.1\n", "0.2.1\n" ] } ], "source": [ "import torch\n", "import torchvision\n", "import torchvision.transforms as transforms\n", "import matplotlib.pyplot as plt\n", "import time\n", "import sys\n", "sys.path.append(\"..\") # 为了导入上层目录的d2lzh_pytorch\n", "import d2lzh_pytorch as d2l\n", "\n", "print(torch.__version__)\n", "print(torchvision.__version__)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 3.5.1 获取数据集" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true }, "outputs": [], "source": [ "mnist_train = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=True, download=True, transform=transforms.ToTensor())\n", "mnist_test = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=False, download=True, transform=transforms.ToTensor())" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "60000 10000\n" ] } ], "source": [ "print(type(mnist_train))\n", "print(len(mnist_train), len(mnist_test))" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "torch.Size([1, 28, 28]) torch.float32\n", "tensor(9)\n" ] } ], "source": [ "feature, label = mnist_train[0]\n", "print(feature.shape, feature.dtype) # Channel x Height X Width\n", "print(label)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n" ] } ], "source": [ "mnist_PIL = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=True, download=True)\n", "PIL_feature, label = mnist_PIL[0]\n", "print(PIL_feature)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# 本函数已保存在d2lzh包中方便以后使用\n", "def get_fashion_mnist_labels(labels):\n", " text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat',\n", " 'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']\n", " return [text_labels[int(i)] for i in labels]" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# 本函数已保存在d2lzh包中方便以后使用\n", "def show_fashion_mnist(images, labels):\n", " d2l.use_svg_display()\n", " # 这里的_表示我们忽略（不使用）的变量\n", " _, figs = plt.subplots(1, len(images), figsize=(12, 12))\n", " for f, img, lbl in zip(figs, images, labels):\n", " f.imshow(img.view((28, 28)).numpy())\n", " f.set_title(lbl)\n", " f.axes.get_xaxis().set_visible(False)\n", " f.axes.get_yaxis().set_visible(False)\n", " plt.show()" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "image/svg+xml": [ "\n", "\n", "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "X, y = [], []\n", "for i in range(10):\n", " X.append(mnist_train[i][0])\n", " y.append(mnist_train[i][1])\n", "show_fashion_mnist(X, get_fashion_mnist_labels(y))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 3.5.2 读取小批量" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": true }, "outputs": [], "source": [ "batch_size = 256\n", "if sys.platform.startswith('win'):\n", " num_workers = 0 # 0表示不用额外的进程来加速读取数据\n", "else:\n", " num_workers = 4\n", "train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)\n", "test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1.57 sec\n" ] } ], "source": [ "start = time.time()\n", "for X, y in train_iter:\n", " continue\n", "print('%.2f sec' % (time.time() - start))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python [default]", "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": "3.6.3" } }, "nbformat": 4, "nbformat_minor": 2 }