pytorch数据预处理错误

出错：

Traceback (most recent call last):

  File "train.py", line , in <module>

    train_model(model_conv, criterion, optimizer_conv, exp_lr_scheduler)

  File "train.py", line , in train_model

    for inputs, age_labels, gender_labels in dataloaders[phase]:

  File "/home/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line , in __next__

    return self._process_next_batch(batch)

  File "/home/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line , in _process_next_batch

    raise batch.exc_type(batch.exc_msg)

RuntimeError: Traceback (most recent call last):

  File "/home/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line , in _worker_loop

    samples = collate_fn([dataset[i] for i in batch_indices])

  File "/home/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line , in default_collate

    return [default_collate(samples) for samples in transposed]

  File "/home/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line , in <listcomp>

    return [default_collate(samples) for samples in transposed]

  File "/home/home/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line , in default_collate

    return torch.stack(batch, , out=out)

RuntimeError: invalid argument : Sizes of tensors must match except in dimension . Got  and  in dimension  at /pytorch/aten/src/TH/generic/THTensorMoreMath.cpp:

这是因为输入的大小不匹配，跟数据集有关，也跟数据预处理中的函数相关：

transforms.Resize(input_size)

该函数是按比例缩放，可能是因为该数据集的分辨率不同，所以出来的结果不是(224,224)的，解决办法是改为使用：

transforms.Resize((input_size, input_size))

即可

巴特西

pytorch数据预处理错误

最新文章

热门文章