BUG: SemiSupCompletionModel do not flip back the output['inv_depths_rgbd']

[chenjx1005]

Bug appears when I train SemiSupCompletionModel. The DEPTH_PP_GT metric is much worse than DEPTH_GT of my re-trained model.

I check the traning code. In

packnet-sfm/packnet_sfm/models/SfmModel.py

Line 75 in f59b1d6

output = flip_output(output)

, I found if flip is True, you do flip back the output['inv_depths'] but not output['inv_depths_rgbd']. see:

packnet-sfm/packnet_sfm/models/model_utils.py

Line 127 in f59b1d6

def flip_output(output):

, 'inv_depths_rgbd' key in not in the fliter_dict. As a result, it causes the model can not handle fliped input.

[VitorGuizilini-TRI]

Thank you for pointing that out! And thank you for your PR, I will take a look and merge soon.