Question about attention map

VITA-Group / EnlightenGAN

[IEEE TIP] "EnlightenGAN: Deep Light Enhancement without Paired Supervision" by Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang

Other

890 stars 198 forks source link

Question about attention map #86

Closed Icy-green closed 3 years ago

Icy-green commented 3 years ago

When I was executing the code, I noticed that A_Gray was the attention map mentioned in the paper, but A_Gray was not sent to the network for training. Could you please help me to answer the question?

yifanjiang19 commented 3 years ago

attention map is used in here https://github.com/VITA-Group/EnlightenGAN/blob/90903c3f9086583baf450474505d4dd1d5495ae0/models/networks.py#L736

McFly-Jia commented 3 years ago

Although this line of code was present,it was not called because your which_model_netG selected 'unet_256' instead of 'sid_unet_resize'. Could you please help me to answer the question?