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 fb94350896
Update training script and loader factory to allow use of scheduler updates, repeat augment, and bce loss
3 years ago
..
parsers Fix tf.data options setting for newer TF versions 4 years ago
__init__.py More dataset work including factories and a tensorflow datasets (TFDS) wrapper 4 years ago
auto_augment.py Add `mmax` config key to auto_augment for increasing upper bound of RandAugment magnitude beyond 10. Make AugMix uniform sampling default not override config setting. 3 years ago
config.py Add epoch-repeats arg to multiply the number of dataset passes per epoch. Currently for iterable datasets (read TFDS wrapper) only. 4 years ago
constants.py
dataset.py Add epoch-repeats arg to multiply the number of dataset passes per epoch. Currently for iterable datasets (read TFDS wrapper) only. 4 years ago
dataset_factory.py Add epoch-repeats arg to multiply the number of dataset passes per epoch. Currently for iterable datasets (read TFDS wrapper) only. 4 years ago
distributed_sampler.py Add RepeatAugSampler as per DeiT RASampler impl, showing promise for current (distributed) training experiments. 3 years ago
loader.py Update training script and loader factory to allow use of scheduler updates, repeat augment, and bce loss 3 years ago
mixup.py More flexible mixup mode, add 'half' mode. 4 years ago
random_erasing.py
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 Support for huggingface hub via create_model and default_cfgs. 4 years ago
transforms_factory.py Support for huggingface hub via create_model and default_cfgs. 4 years ago