search

RaphaelMeudec / deblur-gan

Keras implementation of "DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks"
590 stars 245 forks source link

d_loss_fake always ZERO？ #21

Open Jaswers opened 6 years ago

Jaswers commented 6 years ago

https://github.com/RaphaelMeudec/deblur-gan/blob/0c0c0296f143b7a070a0969cb64a8774f8e79f1d/train.py#L43 https://github.com/RaphaelMeudec/deblur-gan/blob/0c0c0296f143b7a070a0969cb64a8774f8e79f1d/train.py#L62

d_loss_fake always be ZERO？

LuShuaie commented 6 years ago

Hi, d_loss_fake = d.train_on_batch(generated_images, output_false_batch) d_loss_fake always be ZERO？