res-loglikelihood-regression icon indicating copy to clipboard operation
res-loglikelihood-regression copied to clipboard

Published 20 hours ago • verified publisher icon Jeff-sjtu

Why fc_coord is Linear() Instead of nn.linear in Regression_nf_3d.py?

Open 2015wan opened this issue 1 year ago • 1 comments

  1. Why design a separate linear layer for the output of the coordinate mean, and what is the difference between it and the ordinary fully connected layer?
  3. Why is this happening? x_norm = torch.norm(x, dim=1, keepdim=True) y = y / x_norm

2015wan avatar Jul 31 '23 08:07 2015wan

In this class RegressFlow3D(nn.Module) Why when testing pred_jts[:, :, 2] = pred_jts[:, :, 2] - pred_jts[:, self.root_idx:self.root_idx + 1, 2] Why do you have to subtract like this

2015wan avatar Aug 03 '23 07:08 2015wan