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
621e1b2182
Add ideas from 'Scaling ViT to 22-B Params', testing PyTorch 2.0 fused F.scaled_dot_product_attention impl in vit, vit_relpos, maxxvit / coatnet.
|
2 years ago |
| .. |
|
data
|
Improve support for custom dataset label name/description through HF hub export, via pretrained_cfg
|
2 years ago |
|
layers
|
Add ideas from 'Scaling ViT to 22-B Params', testing PyTorch 2.0 fused F.scaled_dot_product_attention impl in vit, vit_relpos, maxxvit / coatnet.
|
2 years ago |
|
loss
|
Remove inplace operators when calculating the loss
|
2 years ago |
|
models
|
Add ideas from 'Scaling ViT to 22-B Params', testing PyTorch 2.0 fused F.scaled_dot_product_attention impl in vit, vit_relpos, maxxvit / coatnet.
|
2 years ago |
|
optim
|
Add multi-tensor (foreach) version of Lion in style of upcoming PyTorch 2.0 optimizers
|
2 years ago |
|
scheduler
|
Scheduler update, add v2 factory method, support scheduling on updates instead of just epochs. Add LR to summary csv. Add lr_base scaling calculations to train script. Fix #1168
|
2 years ago |
|
utils
|
Davit update formatting and fix grad checkpointing (#7)
|
2 years ago |
|
__init__.py
|
Major module / path restructure, timm.models.layers -> timm.layers, add _ prefix to all non model modules in timm.models
|
2 years ago |
|
version.py
|
Version 0.8.12dev0
|
2 years ago |
