search

MaybeShewill-CV / attentive-gan-derainnet

Unofficial tensorflow implemention of "Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (CVPR 2018) " model https://maybeshewill-cv.github.io/attentive-gan-derainnet/
MIT License
262 stars 83 forks source link

th #41

Closed jilner closed 5 years ago

jilner commented 5 years ago

thanks for your good job, when I run the author's code which in pytorch, and out of memory in a 1080 gpu,but you can run in 1070gpu,what's the problem in pytorch, and the train image is resized to hou much, will different train image inifluence the reslut? thanks

MaybeShewill-CV commented 5 years ago

@jilner I'm not familiar with pytorch. But the problem you meet may be caused by the image scale.You may read config/global_config.py file for hyperparameters that used in the model:)

jilner commented 5 years ago

thanks for reply, what's the scale in your training? if I used image in small scale, is it going to get worse in reslut?

MaybeShewill-CV commented 5 years ago

@jilner You may check this https://github.com/MaybeShewill-CV/attentive-gan-derainnet/blob/master/config/global_config.py for image size:)

jilner commented 5 years ago

thanks