torch加载数据集：Dataset not found or corrupted. You can use download=True to download it

骑鱼过江的猫

已于 2022-02-09 16:19:35 修改

阅读量1.9k

点赞数 2

文章标签：深度学习 pytorch 机器学习

于 2022-02-09 16:11:53 首次发布

本文链接：https://blog.csdn.net/weixin_44249471/article/details/122844008

版权

使用离线下载的CIFAR数据集压缩包报错。

解决办法：

step1：解压CIFAR压缩包生成文件夹cifar-10-batches-py

step2：新建data/cifar_data文件夹，将cifar-10-batches-py放到cifar_data文件夹下

1.目录层级如下：

2.加载数据格式如下，download=False

import torch
import torchvision
import torchvision.transforms as transforms

transform = transforms.Compose(
    [transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
)
trainset = torchvision.datasets.CIFAR10(
    root="./data/cifar_data/",
    train=True,
    download=False,
    transform=transform,
)
trainloader = torch.utils.data.DataLoader(
    trainset, batch_size=4, shuffle=False, num_workers=2
)

classes = (
    "plane",
    "car",
    "bird",
    "cat",
    "deer",
    "dog",
    "frog",
    "horse",
    "ship",
    "truck",)

(data, label) = trainset[1]
print(classes[label])

>>>
truck