search

GuoShi28 / CBDNet

Code for "Toward Convolutional Blind Denoising of Real Photographs", CVPR 2019
Apache License 2.0
501 stars 92 forks source link

Do you train your model with multi-gpus by using matconvnet? #14

Closed XSLXANDY closed 5 years ago

XSLXANDY commented 5 years ago

I found using 1 single gpu is very time consuming. But I have some trouble using multi-gpus with matconvnet. I wonder if you can show me how to modify the code to adapt multi-gpus settings?

GuoShi28 commented 5 years ago

I also use only one GPU to train the model and it takes me about 3 days for about 40 epoch. I did not change my code to multi-GPUs. Setting a larger stride size (when cutting training patches from a whole image) is an effective way to save training time but not greatly affect performance.

XSLXANDY commented 5 years ago

I got it, thank you!