BUG

[sun744-cmd]

Traceback (most recent call last):
File "main.py", line 149, in
train_loss = train(Data, Data.train[0], Data.train[1], model, criterion, optim, args.batch_size)
File "main.py", line 60, in train
total_loss += loss.data[0];
IndexError: invalid index of a 0-dim tensor. Use tensor.item() in Python or tensor.item<T>() in C++ to convert a 0-dim tensor to a number

[RiekeZoe]

I had the same problem. This can be solved by simply removing the [0], as suggested by @huangbiubiu here NVIDIA/flownet2-pytorch#113. When you implement this and run the code, you will encounter a few more errors of the same origin, so you probably have to do the same again. Alternatively you could also use an old version of PyTorch that still uses the 0-index.

Old code: total_loss += loss.data[0];
New code: total_loss += loss.data