search

nihaomiao / CVPR23_LFDM

The pytorch implementation of our CVPR 2023 paper "Conditional Image-to-Video Generation with Latent Flow Diffusion Models"
BSD 2-Clause "Simplified" License
432 stars 43 forks source link

KeyError: 'photometric' #5

Closed Yueming6568 closed 1 year ago

Yueming6568 commented 1 year ago

Hi, haomiao. When I run "python -u LFAE/run_mhad.py" to train the LFAE model, I have the bug : File "CVPR23_LFDM/LFAE/modules/model.py", line 217, in forward if self.loss_weights['photometric'] != 0: KeyError: 'photometric'

May be the loss_weights of 'photometric' should be provided in config/xxx128.yaml . Looking forward to your reply : )

nihaomiao commented 1 year ago

Hi, @Yueming6568, thanks a lot for letting me know! I have fixed the bug. The "photometric" loss is useless. I have deleted some useless codes in model.py. You can try it again. Please feel free to let me know if you find any other problems.

Yueming6568 commented 1 year ago

Thank you a lot for your reply ! The LFAE model can be trained now !