Why d_container.trainable is set to False in the train.py? about image_completion_tf2 HOT 3 CLOSED

Hi @zhengzibing2011 ,

Thanks for the good question.
The discriminator(d_container) is compiled in two models: "d_model" and "all_model".
According to the paper, the discriminator is trained in the "d_model", so I set the flag for training in the "all_model" to False.

from image_completion_tf2.

Hi @zhengzibing2011 ,

Thanks for the good question.
The discriminator(d_container) is compiled in two models: "d_model" and "all_model".
According to the paper, the discriminator is trained in the "d_model", so I set the flag for training in the "all_model" to False.

Thanks a lot for your timely response! The code provides me with great reference value. Thanks you again. I still have the question about "d_container.trainable = False" in the trian.py. Is its function to keep the all model (i.e., the combination of the completion network and the discriminator network) from being trained while training the discriminator when tc<n<tc+td? If my guess is true, the conditional statement "if n<tc: ..., else: ..., if n>tc+td:..." has already achieved this goal. When I comment "d_container.trainable = False" , the training-loss log seems unchanged. The training log is given as follows, in which the above the results from the original code and the bottom is the results after commenting "d_container.trainable = False" . Looking forward to your reply again.
training loss log.docx

from image_completion_tf2.

It seems strange that commenting out "d_container.trainable = False" would have the same behavior.
I think it would be better to look at the change in the weight of the discriminator before and after training with all_model, not loss.

from image_completion_tf2.