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
e9f1376cde
Cleanup resolve data config fns, add 'model' variant that takes model as first arg, make 'args' arg optional in original fn
|
1 year ago |
.. |
readers
|
Support HF datasets and TFSD w/ a sub-path by fixing split, fix #1598 ... add class mapping support to HF datasets in case class label isn't in info.
|
1 year ago |
__init__.py
|
Cleanup resolve data config fns, add 'model' variant that takes model as first arg, make 'args' arg optional in original fn
|
1 year ago |
auto_augment.py
|
Remove print from auto_augment
|
1 year ago |
config.py
|
Cleanup resolve data config fns, add 'model' variant that takes model as first arg, make 'args' arg optional in original fn
|
1 year ago |
constants.py
|
Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate
|
1 year ago |
dataset.py
|
Rename dataset/parsers -> dataset/readers, create_parser to create_reader, etc
|
2 years ago |
dataset_factory.py
|
Support HF datasets and TFSD w/ a sub-path by fixing split, fix #1598 ... add class mapping support to HF datasets in case class label isn't in info.
|
1 year ago |
distributed_sampler.py
|
Significant model refactor and additions:
|
2 years ago |
loader.py
|
Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate
|
1 year ago |
mixup.py
|
Fix MobileNetV2 head conv size for multiplier < 1.0. Add some missing modification copyrights, fix starting date of some old ones.
|
2 years ago |
random_erasing.py
|
Refactor device handling in scripts, distributed init to be less 'cuda' centric. More device args passed through where needed.
|
2 years ago |
real_labels.py
|
Fix a bug with accuracy retrieving from RealLabels
|
4 years ago |
tf_preprocessing.py
|
Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate
|
1 year ago |
transforms.py
|
Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate
|
1 year ago |
transforms_factory.py
|
Add 3-Augment support to auto_augment.py, clean up weighted choice handling, and allow adjust per op prob via arg string
|
1 year ago |