JiahuiYu / generative_inpainting

DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
http://jiahuiyu.com/deepfill/
Other
3.27k stars 787 forks source link

AE_LOSS, L1 LOSS #458

Closed nhutthanh340 closed 4 years ago

nhutthanh340 commented 4 years ago

Hi, can you explain and help me with a problem? If I do not use ae_loss to measure the error of background and l1 for the foreground, but I only use l1 for the generated image, what is the problem? Thanks.

Laputa-tu commented 4 years ago

Hi, can you explain and help me with a problem? If I do not use ae_loss to measure the error of background and l1 for the foreground, but I only use l1 for the generated image, what is the problem? Thanks.

How to show l1_loss on Tensorboard?

JiahuiYu commented 4 years ago

42