search

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
918 stars 200 forks source link

which module including the attention map produce #17

Closed hhelicopter closed 5 years ago

hhelicopter commented 5 years ago

I want to know the attention map and its use in this project. Could you point the location（which module and .py files） of code？

UtopiaHu commented 5 years ago

I guess it's in unaligned_dataset.py, A_gray is the self-regularized attention map.

Ir1d commented 5 years ago

I think the attention map is the grayscale version of the image

hhelicopter commented 5 years ago

I guess it's in unaligned_dataset.py, A_gray is the self-regularized attention map. I think the attention map is the grayscale version of the image

thank you for your answer.But the red box in the image attached make me confused. Do you know how to achieve it? 20190716113536

Ir1d commented 5 years ago

it is skip connection in the code