Pytorch基础：数据读取与预处理——调用PyTorch官方数据集

MechMaster

已于 2024-01-12 18:35:15 修改

阅读量643

点赞数 7

分类专栏：深度学习文章标签： pytorch 人工智能 python

于 2024-01-10 22:58:42 首次发布

本文链接：https://blog.csdn.net/weixin_38566632/article/details/135512442

版权

深度学习专栏收录该内容

14 篇文章 0 订阅

订阅专栏

本文介绍了如何从网络下载FashionMNIST数据集，并使用PyTorch库进行数据预处理，包括使用ToTensor转换，最后展示了数据集中的样本及其对应的标签进行可视化。

摘要由CSDN通过智能技术生成

1. 从网络端下载 FashionMNIST 数据集到本地

(base) PS C:\Users\孙明阳> conda activate yang
(yang) PS C:\Users\孙明阳> python
Python 3.11.5 | packaged by Anaconda, Inc. | (main, Sep 11 2023, 13:26:23) [MSC v.1916 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> from torchvision import datasets
>>> from torch.utils.data import Dataset
>>> from torchvision.transforms import ToTensor
>>> import matplotlib.pyplot as plt
>>> import numpy as np
>>>
>>> training_data = datasets.FashionMNIST(
...     root="data/FashionMNIST/",
...     train=True,
...     download=True,
...     transform=ToTensor()
... )
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to data/FashionMNIST/FashionMNIST\raw\train-images-idx3-ubyte.gz
100.0%
Extracting data/FashionMNIST/FashionMNIST\raw\train-images-idx3-ubyte.gz to data/FashionMNIST/FashionMNIST\raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to data/FashionMNIST/FashionMNIST\raw\train-labels-idx1-ubyte.gz
100.0%
Extracting data/FashionMNIST/FashionMNIST\raw\train-labels-idx1-ubyte.gz to data/FashionMNIST/FashionMNIST\raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to data/FashionMNIST/FashionMNIST\raw\t10k-images-idx3-ubyte.gz
100.0%
Extracting data/FashionMNIST/FashionMNIST\raw\t10k-images-idx3-ubyte.gz to data/FashionMNIST/FashionMNIST\raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/FashionMNIST\raw\t10k-labels-idx1-ubyte.gz
100.0%
Extracting data/FashionMNIST/FashionMNIST\raw\t10k-labels-idx1-ubyte.gz to data/FashionMNIST/FashionMNIST\raw

在这里插入图片描述

2. 数据集可视化

(base) PS C:\Users\阳> conda activate yang
(yang) PS C:\Users\阳> python
Python 3.11.5 | packaged by Anaconda, Inc. | (main, Sep 11 2023, 13:26:23) [MSC v.1916 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> from torchvision import datasets
>>> from torch.utils.data import Dataset
>>> from torchvision.transforms import ToTensor
>>> import matplotlib.pyplot as plt
>>> import numpy as np
>>> training_data = datasets.FashionMNIST(
...     root="data/FashionMNIST/",
...     train=True,
...     download=True,
...     transform=ToTensor()
... )
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to data/FashionMNIST/FashionMNIST\raw\train-images-idx3-ubyte.gz
100.0%
Extracting data/FashionMNIST/FashionMNIST\raw\train-images-idx3-ubyte.gz to data/FashionMNIST/FashionMNIST\raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to data/FashionMNIST/FashionMNIST\raw\train-labels-idx1-ubyte.gz
100.0%
Extracting data/FashionMNIST/FashionMNIST\raw\train-labels-idx1-ubyte.gz to data/FashionMNIST/FashionMNIST\raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to data/FashionMNIST/FashionMNIST\raw\t10k-images-idx3-ubyte.gz
100.0%
Extracting data/FashionMNIST/FashionMNIST\raw\t10k-images-idx3-ubyte.gz to data/FashionMNIST/FashionMNIST\raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/FashionMNIST\raw\t10k-labels-idx1-ubyte.gz
100.0%
Extracting data/FashionMNIST/FashionMNIST\raw\t10k-labels-idx1-ubyte.gz to data/FashionMNIST/FashionMNIST\raw

>>> labels_map = {
...     0: "T-Shirt",
...     1: "Trouser",
...     2: "Pullover",
...     3: "Dress",
...     4: "Coat",
...     5: "Sandal",
...     6: "Shirt",
...     7: "Sneaker",
...     8: "Bag",
...     9: "Ankle Boot",
... }
>>> figure = plt.figure(figsize=(7, 7))
>>> cols, rows = 3, 3
>>> # 根据数据集的数据量len(training_data)，随机生成9个位置坐标
>>> positions = np.random.randint(0, len(training_data), (9,))
>>> for i in range(9):
...     img, label = training_data[positions[i]]
...     plt.subplot(rows, cols, i + 1)
...     plt.tight_layout(pad=0.05)
...     # 每个子图的标题设置为对应图像的标签
...     plt.title(labels_map[label])
...     plt.axis("off")
...     plt.imshow(img.squeeze(), cmap="gray")
>>> plt.savefig("D:\\fashion_mnist2.png")
>>> plt.show()