DataLoader问题解决:RuntimeError: stack expects each tensor to be equal size, but got [3, 200, 200]entry1

        最近,在数据集处理并载入DataLoader进行训练的时候出现了问题:

RuntimeError: stack expects each tensor to be equal size, 
but got [3, 200, 200] at entry 0 and [1, 200, 200] at entry 1

        我看了一下,大意就是维度也就是通道数不匹配,所以我觉得应该是数据集图片出现了问题。以下是我的普通数据集处理代码:

import torch
import torchvision.transforms as transforms
from torch.utils.data import Dataset, DataLoader
import os
from PIL import Image

transform = transforms.Compose([
            transforms.RandomCrop((200, 200)),    #需要进行同意大小,不然会报错
            transforms.ToTensor(),
])

class PreprocessDataset(Dataset):
    """预处理数据集类"""

    def __init__(self, HRPath):
        """初始化预处理数据集类"""
        img_names = os.listdir(HRPath)
        self.HR_imgs = [HRPath + "/" + img_name for img_name in img_names]

    def __len__(self):
        """获取数据长度"""
        return len(self.HR_imgs)

    def __getitem__(self, index):
        """获取数据"""
        HR_img = self.HR_imgs[index]

        HR_img = Image.open(HR_img)

        HR_img = transform(HR_img)

        return HR_img     

if __name__ == '__main__':
    HRPath = r"D:\datasets\ImageNet\train"
    datasets = PreprocessDataset(HRPath)
    trainData = DataLoader(datasets, batch_size=1, shuffle=False)
    for i, HR_img in enumerate(trainData):
        print(i, HR_img.shape)

          我一张一张图片放入DataLoader,然后按顺序一张一张的查看它们的维度,然后出现如下错误:

'''结果'''
146 torch.Size([1, 3, 200, 200])
147 torch.Size([1, 3, 200, 200])

ValueError: empty range for randrange() (0,-55, -55)

        我找到出错前按顺序查到了第149(从0开始)张图片的维度,点开发现这张图片的最短边小于200,不能进行随机裁剪transforms.RandomCrop((200, 200)),所以我进行了transforms.Resize(400),把图片最短边放大到400。

transform = transforms.Compose([
            transforms.Resize(400),
            transforms.RandomCrop((200, 200)),    #需要进行同意大小,不然会报错
            transforms.ToTensor(),
])

        在次运行并不发生错误,但这是在DataLoader的batch_size=1张图片的情况下。所以把batch_size改成多张图片再次运行:

if __name__ == '__main__':
    HRPath = r"D:\datasets\ImageNet\train"
    # os.listdir(HRPath)
    datasets = PreprocessDataset(HRPath)
    a = datasets[89]
    print(a.shape)
    trainData = DataLoader(datasets, batch_size=16, shuffle=False)
    for i, HR_img in enumerate(trainData):
        print(i, HR_img.shape)

        发生错误:

'''结果'''
0 torch.Size([16, 3, 200, 200])
1 torch.Size([16, 3, 200, 200])
2 torch.Size([16, 3, 200, 200])
3 torch.Size([16, 3, 200, 200])
4 torch.Size([16, 3, 200, 200])

RuntimeError: stack expects each tensor to be equal size, 
but got [3, 200, 200] at entry 0 and [1, 200, 200] at entry 9

        从不出错的结果上看,定位图片问题所在的索引应该在80-96之间,那么缩小问题图片的方位,把batch_size=2:

if __name__ == '__main__':
    HRPath = r"D:\datasets\ImageNet\train"
    # os.listdir(HRPath)
    datasets = PreprocessDataset(HRPath)
    a = datasets[89]
    print(a.shape)
    trainData = DataLoader(datasets, batch_size=2, shuffle=False)
    for i, HR_img in enumerate(trainData):
        print(i, HR_img.shape)

        错误定位到第89或者第90张图片:

'''结果'''
0 torch.Size([2, 3, 200, 200])
...
...
43 torch.Size([2, 3, 200, 200])

RuntimeError: stack expects each tensor to be equal size, but got [3, 200, 200] at entry 0 and [1, 200, 200] at entry 1

        输出第89张图片的维度:

if __name__ == '__main__':
    HRPath = r"D:\datasets\ImageNet\train"
    # os.listdir(HRPath)
    datasets = PreprocessDataset(HRPath)
    a = datasets[89]
    print(a.shape)

        结果:

torch.Size([1, 200, 200])

        真的是通道数不统一,醉了啊!

        解决方法,在图片预处理的时候,将所有图片都转成"RGB"三通道的模式:

HR_img = Image.open(HR_img).convert('RGB')   #全部以三通道形式打开

        解决完成!!!!

DataLoader问题解决:RuntimeError: stack expects each tensor to be equal size, but got [3, 200, 200]entry1_第1张图片

 

 

你可能感兴趣的:(深度学习,pytorch,python)