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
40457e5691
Transforms, augmentation work for bits, add RandomErasing support for XLA (pushing into transforms), revamp of transform/preproc config, etc ongoing...
|
4 years ago |
| .. |
|
bits
|
Transforms, augmentation work for bits, add RandomErasing support for XLA (pushing into transforms), revamp of transform/preproc config, etc ongoing...
|
4 years ago |
|
data
|
Transforms, augmentation work for bits, add RandomErasing support for XLA (pushing into transforms), revamp of transform/preproc config, etc ongoing...
|
4 years ago |
|
loss
|
asymmetric_loss
|
5 years ago |
|
models
|
Transforms, augmentation work for bits, add RandomErasing support for XLA (pushing into transforms), revamp of transform/preproc config, etc ongoing...
|
4 years ago |
|
optim
|
Fix adabelief imports, remove prints, preserve memory format is the default arg for zeros_like
|
4 years ago |
|
scheduler
|
Major timm.bits update. Updater and DeviceEnv now dataclasses, after_step closure used, metrics base impl w/ distributed reduce, many tweaks/fixes.
|
4 years ago |
|
utils
|
Add proper TrainState checkpoint save/load. Some reorg/refactoring and other cleanup. More to go...
|
4 years ago |
|
__init__.py
|
Add default_cfg options for min_input_size / fixed_input_size, queries in model registry, and use for testing self-attn models
|
4 years ago |
|
version.py
|
Bump version to 0.4.11
|
4 years ago |
