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
d23a2697d0
Working on feature extraction, interfaces refined, a number of models working, some in progress.
|
5 years ago |
| .. |
|
__init__.py
|
Working on feature extraction, interfaces refined, a number of models working, some in progress.
|
5 years ago |
|
auto_augment.py
|
Update AugMix, JSD, etc comments and references
|
5 years ago |
|
config.py
|
Remove old mean/std helper, rely fully on cmd line or default_cfg now. Fixes #126
|
5 years ago |
|
constants.py
|
…
|
|
|
dataset.py
|
Add support to Dataset for class id mapping file, clean up a bit of old logic. Add results file arg for validation and update script.
|
5 years ago |
|
distributed_sampler.py
|
…
|
|
|
loader.py
|
added MultiEpochsDataLoader
|
5 years ago |
|
mixup.py
|
Working on an implementation of AugMix with JensenShannonDivergence loss that's compatible with my AutoAugment and RandAugment impl
|
5 years ago |
|
random_erasing.py
|
Add SplitBatchNorm. AugMix, Rand/AutoAugment, Split (Aux) BatchNorm, Jensen-Shannon Divergence, RandomErasing all working together
|
5 years ago |
|
real_labels.py
|
Working on feature extraction, interfaces refined, a number of models working, some in progress.
|
5 years ago |
|
tf_preprocessing.py
|
Add MixNet (https://arxiv.org/abs/1907.09595) with pretrained weights converted from Tensorflow impl
|
5 years ago |
|
transforms.py
|
Working on an implementation of AugMix with JensenShannonDivergence loss that's compatible with my AutoAugment and RandAugment impl
|
5 years ago |
|
transforms_factory.py
|
Indentation mistake. Fixes #81
|
5 years ago |
