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.
pytorch-image-models/timm/data
Ross Wightman 9c14654a0d
Improve support for custom dataset label name/description through HF hub export, via pretrained_cfg
2 years ago
..
_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. 2 years 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. 2 years ago
__init__.py Improve support for custom dataset label name/description through HF hub export, via pretrained_cfg 2 years ago
auto_augment.py Remove print from auto_augment 2 years ago
config.py Cleanup resolve data config fns, add 'model' variant that takes model as first arg, make 'args' arg optional in original fn 2 years ago
constants.py Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate 2 years 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. 2 years ago
dataset_info.py Improve support for custom dataset label name/description through HF hub export, via pretrained_cfg 2 years ago
distributed_sampler.py Significant model refactor and additions: 3 years ago
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. 2 years ago
loader.py Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate 2 years ago
mixup.py Fix MobileNetV2 head conv size for multiplier < 1.0. Add some missing modification copyrights, fix starting date of some old ones. 3 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 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. 2 years ago
tf_preprocessing.py Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate 2 years ago
transforms.py Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate 2 years 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 2 years ago