Skip to content

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

License

Notifications You must be signed in to change notification settings

dydjw9/pytorch-image-models

 
 

Repository files navigation

example script

CUDA_VISIBLE_DEVICES=0,1,2,3 ./distributed_train.sh 4 path/to/imagenet --model resnet50 --weight_dropout 0.5 --opt_dropout 0.3 --nograd_cutoff 0.01 --temperature 3 --rho 0.05 --epochs 300 --batch-size 256 --lr 0.4 --sched cosine --weight-decay 1e-4 --smoothing 0.0 --model-ema

--weight_dropout = 1 - beta --opt_dropoout = 1 - gamma

About

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 99.9%
  • Shell 0.1%