I met an issue when I run the train.py

[haimeilv]

I met an issue when I run the train.py

当我用train.py训练WHU数据集时，遇到了下面的问题：

`
epoch 0/99
0%| | 0/539 [00:00<?, ?it/s]/root/miniconda3/lib/python3.8/site-packages/torch/nn/functional.py:3454: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
warnings.warn(
d2_out.shape torch.Size([4, 2, 256, 256])
labels.shape torch.Size([4, 3, 256, 256])
0%| | 0/539 [00:01<?, ?it/s]
Traceback (most recent call last):
File "/tmp/pycharm_project_524/my_yaogan/train_EGRCNN.py", line 86, in
val_acc, train_loss = UNet_mloss_train.train_model(UNet_mlstm, dataloaders_dict, criterion, criterion1, optimizer, sc_plt, device, num_epochs=num_epochs)
File "/tmp/pycharm_project_524/my_yaogan/UNet_mloss_train.py", line 60, in train_model
loss_seg_2 = criterion(d2_out, labels)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/tmp/pycharm_project_524/my_yaogan/losses.py", line 23, in forward
logpt = logpt.gather(1, target)
RuntimeError: Size does not match at dimension 0 expected index [786432, 1] to be smaller than src [262144, 2] apart from dimension 1

Process finished with exit code 1

Excuse me, can you upload some training datasets? What can I do to solve this problem？