本文共 1553 字，大约阅读时间需要 5 分钟。

报错如下：

Traceback (most recent call last): File “6_database_deal_.py”, line 73, in for i, data in enumerate(test_loader): File “/home/muli/anaconda3/lib/python3.5/site-packages/torch/utils/data/dataloader.py”, line 560, in next batch = self.collate_fn([self.dataset[i] for i in indices]) File “/home/muli/anaconda3/lib/python3.5/site-packages/torch/utils/data/_utils/collate.py”, line 68, in default_collate return [default_collate(samples) for samples in transposed] File “/home/muli/anaconda3/lib/python3.5/site-packages/torch/utils/data/_utils/collate.py”, line 68, in return [default_collate(samples) for samples in transposed] File “/home/muli/anaconda3/lib/python3.5/site-packages/torch/utils/data/_utils/collate.py”, line 43, in default_collate return torch.stack(batch, 0, out=out) RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 309 and 580 in dimension 2 at /pytorch/aten/src/TH/generic/THTensor.cpp:711

数据集图像大小不一，加载训练集时进行了RandomResizedCrop ,

但是在测试时忘记了，因此出现了以下报错信息： RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 309 and 580 in dimension 2 at /pytorch/aten/src/TH/generic/THTensor.cpp:711

解决办法：

testTransform部分加入 transforms.Resize((224, 224))

# 训练trainTransform = transforms.Compose([    transforms.RandomResizedCrop(224), # 随机裁剪,    transforms.RandomHorizontalFlip(), # 随机水平翻转    transforms.ToTensor(),    normTransform # 正则化])# 测试testTransform = transforms.Compose([    transforms.Resize((224, 224)), # 调整图像大小    transforms.ToTensor(),    normTransform # 正则化])

转载地址：https://mymuli.blog.csdn.net/article/details/100566783 如侵犯您的版权，请留言回复原文章的地址，我们会给您删除此文章，给您带来不便请您谅解！