You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for a very nice project.
When scanning through lib/train.py, I found two possible bugs:
L#78coords[:, :3] += (torch.rand(3) * 100).type_as(coords) should be coords[:, 1:] += (torch.rand(3) * 100).type_as(coords) since first coords is the batch index
L#83input[:, 1:] = input[:, 1:] / 255. - 0.5 should be input[:, :3] = input[:, :3] / 255. - 0.5
The text was updated successfully, but these errors were encountered:
Thank you for a very nice project.
When scanning through lib/train.py, I found two possible bugs:
coords[:, :3] += (torch.rand(3) * 100).type_as(coords)
should becoords[:, 1:] += (torch.rand(3) * 100).type_as(coords)
since first coords is the batch indexinput[:, 1:] = input[:, 1:] / 255. - 0.5
should beinput[:, :3] = input[:, :3] / 255. - 0.5
The text was updated successfully, but these errors were encountered: