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

mobilenet-v2vision-transformer-modelsresnetrandaugmentpytorchpretrained-weightspretrained-modelsnormalization-free-trainingnfnetsmobilenetv3augmixmobile-deep-learningmnasnetmixnetimagenet-classifierefficientnet-trainingefficientnetdual-path-networksdistributed-trainingcnn-classification

You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Ross Wightman 0562b91c38 Add per model crop pct, interpolation defaults, tie it all together ... * create one resolve fn to pull together model defaults + cmd line args * update attribution comments in some models * test update train/validation/inference scripts		6 years ago
data	Add per model crop pct, interpolation defaults, tie it all together	6 years ago
loss	Add smooth loss	6 years ago
models	Add per model crop pct, interpolation defaults, tie it all together	6 years ago
optim	Uniform pretrained model handling.	6 years ago
scheduler	Uniform pretrained model handling.	6 years ago
distributed_train.sh	Fix distributed train script	6 years ago
inference.py	Add per model crop pct, interpolation defaults, tie it all together	6 years ago
train.py	Add per model crop pct, interpolation defaults, tie it all together	6 years ago
utils.py	Cleanup CheckpointSaver, add support for increasing or decreasing metric, switch to prec1 metric in train loop	6 years ago
validate.py	Add per model crop pct, interpolation defaults, tie it all together	6 years ago