tomar840 / two-stream-fusion-for-action-recognition-in-videos

90 stars 28 forks source link

I have some problems in conv_fusion.py #12

Open Kaptainz1 opened 1 year ago

Kaptainz1 commented 1 year ago

When I run conv_fusion.py it has problems: ==> (Training video, Validation video):( 11 0 ) Eligible videos for training : 10 videos Eligible videos for validation: 0 videos Epoch 0/19

Traceback (most recent call last): File "conv_fusion.py", line 349, in model = train_model(model, criterion, optimizer,scheduler, num_epochs=20) File "conv_fusion.py", line 167, in train_model outputs = model(spat_data, temp_data) File "/home/el304/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, *kwargs) File "conv_fusion.py", line 266, in forward y[:,(2i),:,:] = x1[:,i,:,:]

IndexError: too many indices for tensor of dimension 2

Can someone help me?

kevio33 commented 6 months ago

hi, i got the same probliem,did you solve it?