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
43aa84e861
Add 'fast' layer norm that doesn't cast to float32, support APEX LN impl for slight speed gain, update norm and act factories, tweak SE for ability to disable bias (needed by GCVit)
|
2 years ago |
.. |
data
|
Change set -> dict w/ None keys for dataset split synonym search, so always consistent if more than 1 exists. Fix #1224
|
2 years ago |
loss
|
Update binary cross ent impl to use thresholding as an option (convert soft targets from mixup/cutmix to 0, 1)
|
3 years ago |
models
|
Add 'fast' layer norm that doesn't cast to float32, support APEX LN impl for slight speed gain, update norm and act factories, tweak SE for ability to disable bias (needed by GCVit)
|
2 years ago |
optim
|
Fix bug introduced in non layer_decay weight_decay application. Remove debug print, fix arg desc.
|
3 years ago |
scheduler
|
fix: change milestones to decay-milestones
|
3 years ago |
utils
|
Add bulk_runner script and updates to benchmark.py and validate.py for better error handling in bulk runs (used for benchmark and validation result runs). Improved batch size decay stepping on retry...
|
2 years ago |
__init__.py
|
Transitioning default_cfg -> pretrained_cfg. Improving handling of pretrained_cfg source (HF-Hub, files, timm config, etc). Checkpoint handling tweaks.
|
3 years ago |
version.py
|
Add timm ConvNeXt 'atto' weights, change test resolution for FB ConvNeXt 224x224 weights, add support for different dw kernel_size
|
2 years ago |