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
475ecdfa3d
cast env var args for dataset readers to int
|
2 years ago |
.. |
readers
|
cast env var args for dataset readers to int
|
2 years ago |
__init__.py
|
Rename dataset/parsers -> dataset/readers, create_parser to create_reader, etc
|
2 years ago |
auto_augment.py
|
Follow up to #1256, fix interpolation warning in auto_autoaugment as well
|
3 years ago |
config.py
|
support test_crop_size in data config resolve
|
3 years ago |
constants.py
|
Add hf hub entries for laion2b clip models, add huggingface_hub dependency, update some setup/reqs, torch >= 1.7
|
2 years ago |
dataset.py
|
Rename dataset/parsers -> dataset/readers, create_parser to create_reader, etc
|
2 years ago |
dataset_factory.py
|
Rename dataset/parsers -> dataset/readers, create_parser to create_reader, etc
|
2 years ago |
distributed_sampler.py
|
Significant model refactor and additions:
|
3 years ago |
loader.py
|
Set num_workers in Iterable WDS/TFDS datasets early so sample estimate is correct
|
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
|
Fix a bug with accuracy retrieving from RealLabels
|
4 years ago |
tf_preprocessing.py
|
Remove some old __future__ imports
|
4 years ago |
transforms.py
|
use `Image.Resampling` namespace for PIL mapping (#1256)
|
3 years ago |
transforms_factory.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 |