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.
pytorch-image-models/timm
Ross Wightman 61200db0ab
in_chans=1 working w/ pretrained weights for vision_transformer
4 years ago
..
data More models in sotabench, more control over sotabench run, dataset filename extraction consistency 4 years ago
loss asymmetric_loss 4 years ago
models in_chans=1 working w/ pretrained weights for vision_transformer 4 years ago
optim Fix #262, num_classes arg mixup. Make vision_transformers a bit closer to other models wrt get/reset classfier/forward_features. Fix torchscript for ViT. 4 years ago
scheduler Merge branch 'logger' into features. Change 'logger' to '_logger'. 4 years ago
utils Fix topn metric view regression on PyTorch 1.7 4 years ago
__init__.py Monster commit, activation refactor, VoVNet, norm_act improvements, more 5 years ago
version.py Add missing leaky_relu layer factory defn, update Apex/Native loss scaler interfaces to support unscaled grad clipping. Bump ver to 0.2.2 for pending release. 4 years ago