Inoperative lines of code in the training file

[tmondalvogo]

Hello,
Thank you for sharing the code. I find that there are some inoperative lines of code in the training file. The use of these operations is not clear and it seems that these operations are not needed for training.

KpSFR/train_nn.py

Line 236 in 3d4b796

# TODO: random pick 4

The array prev_v[ ] doesn't have any participation in the training. It is created and then deleted.
The variable is created in line :

KpSFR/train_nn.py

Line 237 in 3d4b796

prev_hm = prev_heatmap.clone().detach()

Then it is only used to check an assert condition :

KpSFR/train_nn.py

Line 269 in 3d4b796

prev_v = torch.stack(prev_v, dim=1) # b*k*c*t*h*w

Then it is used for prev_hm [], which is not used further:
https://github.com/ericsujw/KpSFR/blob/3d4b7968e2ab34239bf4c175f17a29efa46a691f/train_nn.py#L267C24-L267C24

Hence all the operations done
From line:

KpSFR/train_nn.py

Line 237 in 3d4b796

prev_hm = prev_heatmap.clone().detach()

To line:

KpSFR/train_nn.py

Line 269 in 3d4b796

prev_v = torch.stack(prev_v, dim=1) # b*k*c*t*h*w

has no use in the training code i.e. these operations are not used in any sort of loss calculation etc.

Then why they are done in this code? What is the use of it?