Open cszy98 opened 3 years ago
Have you solved this problem? I also met the same problem.
I filter out the optical flow network and tune down my learning rate. After that, the results seem to be reasonable but still unsatisfactory.
I filter out the optical flow network and tune down my learning rate. After that, the results seem to be reasonable but still unsatisfactory.
I used the same method as you, and the results were not satisfactory,especially in the facial area. In addition, did you set the "--add_face_D" option? After I use this option to train for a while, the synthesised facial area will collapse.
Sorry for the late replay. I didn't set the "--add_face_D" option.
In the "Few-shot Video-to-Video Synthesis":
But in the code:
and
During testing, I get the output:
In fact, the "flow_network_ref" and "flow_network_temp" are also finetuned. The result is completely collapsed.