Ross Wightman 7266c5c716 Merge branch 'main' into focalnet_and_swin_refactor

2023-02-17 09:20:14 -08:00

..

_info

Move ImageNet metadata (aka info) files to timm/data/_info. Add helper classes to make info available for labelling. Update inference.py for first use.

2023-02-06 17:45:03 -08:00

readers

Allow using class_map functionality w/ IterableDataset (TFDS/WDS) to remap class labels

2023-01-09 16:28:47 -08:00

__init__.py

Improve support for custom dataset label name/description through HF hub export, via pretrained_cfg

2023-02-08 08:29:20 -08:00

auto_augment.py

Remove print from auto_augment

2022-12-28 17:11:35 -08:00

config.py

Cleanup resolve data config fns, add 'model' variant that takes model as first arg, make 'args' arg optional in original fn

2023-01-20 14:47:55 -08:00

constants.py

Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate

2022-12-05 10:21:34 -08:00

dataset_factory.py

Allow using class_map functionality w/ IterableDataset (TFDS/WDS) to remap class labels

2023-01-09 16:28:47 -08:00

dataset_info.py

Improve support for custom dataset label name/description through HF hub export, via pretrained_cfg

2023-02-08 08:29:20 -08:00

dataset.py

Allow using class_map functionality w/ IterableDataset (TFDS/WDS) to remap class labels

2023-01-09 16:28:47 -08:00

distributed_sampler.py

Significant model refactor and additions:

2022-02-28 13:56:23 -08:00

imagenet_info.py

Move ImageNet metadata (aka info) files to timm/data/_info. Add helper classes to make info available for labelling. Update inference.py for first use.

2023-02-06 17:45:03 -08:00

loader.py

Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate

2022-12-05 10:21:34 -08:00

mixup.py

Fix MobileNetV2 head conv size for multiplier < 1.0. Add some missing modification copyrights, fix starting date of some old ones.

2022-01-14 16:28:27 -08:00

random_erasing.py

Refactor device handling in scripts, distributed init to be less 'cuda' centric. More device args passed through where needed.

2022-09-23 16:08:59 -07:00

real_labels.py

Move ImageNet metadata (aka info) files to timm/data/_info. Add helper classes to make info available for labelling. Update inference.py for first use.

2023-02-06 17:45:03 -08:00

tf_preprocessing.py

Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate

2022-12-05 10:21:34 -08:00

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

2022-12-10 16:25:50 -08:00

transforms.py

Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate

2022-12-05 10:21:34 -08:00