维度3的张量的索引过多

Question

我正在尝试对自己的数据进行微调。这是我正在尝试的repository。我收到以下错误消息。这是什么意思？我是python和深度学习编程的新手。

Traceback (most recent call last):
  File "finetune.py", line 254, in <module>
    main()
  File "finetune.py", line 127, in main
    train(TrainImgLoader, model, optimizer, log, epoch)
  File "finetune.py", line 171, in train
    for x in range(num_out)]
  File "finetune.py", line 171, in <listcomp>
    for x in range(num_out)]
IndexError: too many indices for tensor of dimension 3

代码部分在下面。

>     
>     for batch_idx, (imgL, imgR, disp_L) in enumerate(dataloader):
>         imgL = imgL.float()#.cuda()
>         imgR = imgR.float()#.cuda()
>         disp_L = disp_L.float()#.cuda()
> 
>         optimizer.zero_grad()
>         mask = disp_L > 0
>         mask.detach_()
>         outputs = model(imgL, imgR)
> 
>         if args.with_spn:
>             if epoch >= args.start_epoch_for_spn:
>                 num_out = len(outputs)
>             else:
>                 num_out = len(outputs) - 1
>         else:
>             num_out = len(outputs)
> 
>         outputs = [torch.squeeze(output, 1) for output in outputs]
>         loss = [args.loss_weights[x] * F.smooth_l1_loss(outputs[x][mask], disp_L[mask], size_average=True)
>                 for x in range(num_out)]
>         sum(loss).backward()
>         optimizer.step()
> 
>         for idx in range(num_out):
>             losses[idx].update(loss[idx].item())
> 
>         if batch_idx % args.print_freq:
>             info_str = ['Stage {} = {:.2f}({:.2f})'.format(x, losses[x].val, losses[x].avg) for x in range(num_out)]
>             info_str = '\t'.join(info_str)
> 
>             log.info('Epoch{} [{}/{}] {}'.format(
>                 epoch, batch_idx, length_loader, info_str))
>     info_str = '\t'.join(['Stage {} = {:.2f}'.format(x, losses[x].avg) for x in range(stages)])
>     log.info('Average train loss = ' + info_str)

请让我知道该怎么做。

预先感谢：）