search

ryanxingql / stdf-pytorch

Implementation of "Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement" (AAAI'20).
https://www.aiide.org/ojs/index.php/AAAI/article/view/6697
Apache License 2.0
155 stars 20 forks source link

About batchsize #17

Closed doudoublues closed 2 years ago

doudoublues commented 2 years ago

Hello Ryan，why batchsize==32？ Because I notice that if i use 4 GPUs , maybe only 2~3GB memory is used on each GPU. Can I make batchsize or patch size(like 256 * 256 ) larger and will it decrease the performance?

ryanxingql commented 2 years ago

Hi, I haven't tried. I guess the performance will not decrease, unless you use a small data-set.

doudoublues commented 2 years ago

thx