what is the parameters used for linear classification in resnet50 experiment?

facebookresearch / moco-v3

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

Other

1.22k stars 161 forks source link

what is the parameters used for linear classification in resnet50 experiment? #11

Closed yxchng closed 3 years ago

yxchng commented 3 years ago

specifically, what are the parameters for

python main_lincls.py \
  -a [architecture] --lr [learning rate] \
  --dist-url 'tcp://localhost:10001' \
  --multiprocessing-distributed --world-size 1 --rank 0 \
  --pretrained [your checkpoint path]/[your checkpoint file].pth.tar \
  [your imagenet-folder with train and val folders]

in resnet50 experiment?

endernewton commented 3 years ago

It is listed in: https://github.com/facebookresearch/moco-v3/blob/main/CONFIG.md