search

sthalles / SimCLR

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
https://sthalles.github.io/simple-self-supervised-learning/
MIT License
2.19k stars 458 forks source link

batch size affect #49

Open VietHoang1512 opened 2 years ago

VietHoang1512 commented 2 years ago

Hi, I'm trying to experiment with CIFAR-10 with the default hyper-params, and it seems to yield a better score when using smaller batch size (e.g. 72% with batch size 256 yet 78% with batch size 128). Anyone in the same situation, here?

VietHoang1512 commented 2 years ago

STL10 with default hyper-params experients yields the similar results (90.8203% with batch size 256 yet 91.7969% with batch size 128)