Why is the shape of global output different during training and evaluation for the same input video?
I have passed the same vid input to train.py and test.py, but the global output shape differs for both of these cases.
vid_id : 01KML
global_output (train.py): torch.Size([38, 1936])
global_output (test.py): torch.Size([272, 1936])
I am unable to understand this requirement. Can you please help me with this?
Why is the shape of global output different during training and evaluation for the same input video?
I have passed the same vid input to train.py and test.py, but the global output shape differs for both of these cases.
vid_id : 01KML
global_output (train.py): torch.Size([38, 1936])
global_output (test.py): torch.Size([272, 1936])
I am unable to understand this requirement. Can you please help me with this?