search

tensorlayer / SRGAN

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
https://github.com/tensorlayer/tensorlayerx
3.29k stars 810 forks source link

Does the "batch_size" influence the effect of model? #26

Open jiaozixian opened 6 years ago

jiaozixian commented 6 years ago

@zsdonghao ，thanks for your code. I run the code, it works well when loading the images.But when running the conv2d,it raises "resource exhaust error".So I modify the "batch_size" from "16" to "4",it works well。After finish the 2000 epoch training，I get the model.But when I evaluate my own images.it seems not good as I wished。My question1：Does the “batch_size” will influence the effect of training？ question2：Could you send me the model you trained，I want to compare it with mine.Thank you very much. 345239728@qq.com valid_gen valid_lr

luckyboysmith commented 6 years ago

Hello, i meet the same problem did u solve this problem? hoping to get your reply

zsdonghao commented 6 years ago

question1：Does the “batch_size” will influence the effect of training？

Larger batch size need more GPU memory, nothing else.

question2：Could you send me the model you trained，I want to compare it with mine.Thank you very much. 345239728@qq.com

Pls leave a message in the trained model issue.