jahdiel

The use of split in the loss function? What is it for?

1

This code is in core/loss.py: `heatmaps_pred = output.reshape((batch_size, num_joints, -1)).split(1, 1)` I was just wondering what is the `split(1,1)` for? I From my understanding it splits the tensor into equally...

Is the RoIConvPooling the same as an RPN? Are any of this layers synonymous to an RPN (Region Proposal Network) ?