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
b57a03bd0d
Merge branch 'master' into bits_and_tpu
|
3 years ago |
| .. |
|
parsers
|
Merge branch 'master' into bits_and_tpu
|
3 years ago |
|
__init__.py
|
More dataset work including factories and a tensorflow datasets (TFDS) wrapper
|
3 years ago |
|
auto_augment.py
|
Enable uniform augmentation magnitude sampling and set AugMix default
|
3 years ago |
|
collate.py
|
First timm.bits commit, add initial abstractions, WIP updates to train, val... some of it working
|
3 years ago |
|
config.py
|
First timm.bits commit, add initial abstractions, WIP updates to train, val... some of it working
|
3 years ago |
|
constants.py
|
Big re-org, working towards making pip/module as 'timm'
|
5 years ago |
|
dataset.py
|
Add epoch-repeats arg to multiply the number of dataset passes per epoch. Currently for iterable datasets (read TFDS wrapper) only.
|
3 years ago |
|
dataset_factory.py
|
Add epoch-repeats arg to multiply the number of dataset passes per epoch. Currently for iterable datasets (read TFDS wrapper) only.
|
3 years ago |
|
distributed_sampler.py
|
Big re-org, working towards making pip/module as 'timm'
|
5 years ago |
|
fetcher.py
|
Major timm.bits update. Updater and DeviceEnv now dataclasses, after_step closure used, metrics base impl w/ distributed reduce, many tweaks/fixes.
|
3 years ago |
|
loader.py
|
Add proper TrainState checkpoint save/load. Some reorg/refactoring and other cleanup. More to go...
|
3 years ago |
|
mixup.py
|
More flexible mixup mode, add 'half' mode.
|
4 years ago |
|
prefetcher_cuda.py
|
First timm.bits commit, add initial abstractions, WIP updates to train, val... some of it working
|
3 years ago |
|
random_erasing.py
|
Fix some attributions, add copyrights to some file docstrings
|
4 years ago |
|
real_labels.py
|
Fix a bug with accuracy retrieving from RealLabels
|
4 years ago |
|
tf_preprocessing.py
|
First timm.bits commit, add initial abstractions, WIP updates to train, val... some of it working
|
3 years ago |
|
transforms.py
|
Support for huggingface hub via create_model and default_cfgs.
|
3 years ago |
|
transforms_factory.py
|
First timm.bits commit, add initial abstractions, WIP updates to train, val... some of it working
|
3 years ago |
