abnormal output during training

Ha0Tang / C2GAN

[ACM MM 2019 Oral] Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation

http://disi.unitn.it/~hao.tang/project/C2GAN.html

Other

69 stars 5 forks source link

abnormal output during training #7

Closed sitadivon closed 4 years ago

sitadivon commented 4 years ago

Hi, I met a problem during training the network.

At train phase, due to opt.display_freq=1, at each step, 8 images are generated, where real_A, real_B, input_C, input_D should correspond to the input of the network. But I observed that they did not form a pair. See the 12th epoch output. In this picture, real_A and real_B are obviously not the same person.

I have read the code carefully, but I can’t find the reason. Do you know why this happened?

Ha0Tang commented 4 years ago

How about the outputs of the 11th epoch?

sitadivon commented 4 years ago

Only current training epoch is abnormal. All the previous outputs are normal.

Ha0Tang commented 4 years ago

I think it should be ok since the visualization is a bit delayed.

sitadivon commented 4 years ago

Sure. I can get right result at the end of every epoch. Thank you!