search

WXinlong / DenseCL

Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.
GNU General Public License v3.0
549 stars 70 forks source link

GPU training problem #36

Open nightmareisme opened 2 years ago

nightmareisme commented 2 years ago

Are the weights trained by 2 gpus different from those trained by 8 gpus in downstream tasks?? Because the overall batch size is different. Hope to get a reply.