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.
Edoardo Debenedetti
c76d772670
Add support for different TFDS `BuilderConfig`s
|
3 years ago |
| .. |
|
parsers
|
Add support for different TFDS `BuilderConfig`s
|
3 years ago |
|
__init__.py
|
Fixes and improvements for metrics, tfds parser, loader / transform handling
|
3 years ago |
|
auto_augment.py
|
Merge branch 'norm_norm_norm' into bits_and_tpu
|
3 years ago |
|
collate.py
|
Transforms, augmentation work for bits, add RandomErasing support for XLA (pushing into transforms), revamp of transform/preproc config, etc ongoing...
|
3 years ago |
|
config.py
|
Transforms, augmentation work for bits, add RandomErasing support for XLA (pushing into transforms), revamp of transform/preproc config, etc ongoing...
|
3 years ago |
|
constants.py
|
Big re-org, working towards making pip/module as 'timm'
|
6 years ago |
|
dataset.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 |
|
dataset_factory.py
|
Add webdataset (WDS) support, update TFDS to make some naming in parsers more similar. Fix workers=0 compatibility. Add ImageNet22k/12k synset defs.
|
3 years ago |
|
distributed_sampler.py
|
Significant model refactor and additions:
|
3 years ago |
|
fetcher.py
|
Remove print, arg order
|
3 years ago |
|
loader.py
|
Significant model refactor and additions:
|
3 years ago |
|
mixup.py
|
Merge branch 'norm_norm_norm' into bits_and_tpu
|
3 years ago |
|
prefetcher_cuda.py
|
device arg wasn't removed from PrefetcherCuda instantiation of RE
|
3 years ago |
|
random_erasing.py
|
Merge branch 'norm_norm_norm' into bits_and_tpu
|
3 years ago |
|
real_labels.py
|
Fix a bug with accuracy retrieving from RealLabels
|
4 years ago |
|
tf_preprocessing.py
|
First timm.bits commit, add initial abstractions, WIP updates to train, val... some of it working
|
4 years ago |
|
transforms.py
|
Add interpolation mode handling to transforms. Removes InterpolationMode warning. Works for torchvision versions w/ and w/o InterpolationMode enum. Fix #738.
|
3 years ago |
|
transforms_factory.py
|
Merge branch 'norm_norm_norm' into bits_and_tpu
|
3 years ago |
