Hyeongchan Kim a0b2657497 Use `torch.repeat_interleave()` to generate repeated indices faster (#1058) ... * update: use numpy to generate repeated indices faster * update: use torch.repeat_interleave() instead of np.repeat() * refactor: remove unused import, numpy * refactor: torch.range to torch.arange * update: tensor to list before appending the extra samples * update: concatenate the paddings with torch.cat		2022-01-02 14:01:06 -08:00
..
parsers	Matching two bits_and_tpu changes for TFDs wrapper	2021-11-14 12:52:19 -08:00
__init__.py	More dataset work including factories and a tensorflow datasets (TFDS) wrapper	2021-01-15 17:26:20 -08:00
auto_augment.py	Add repr to auto_augment and random_erasing impl	2021-10-28 17:33:36 -07:00
config.py	Add epoch-repeats arg to multiply the number of dataset passes per epoch. Currently for iterable datasets (read TFDS wrapper) only.	2021-02-23 17:31:42 -08:00
constants.py	…
dataset.py	Dataset work	2021-11-09 22:34:15 -08:00
dataset_factory.py	Places365 doesn't exist in some still used torchvision version	2021-11-18 14:59:51 -08:00
distributed_sampler.py	Use `torch.repeat_interleave()` to generate repeated indices faster (#1058)	2022-01-02 14:01:06 -08:00
loader.py	Add worker_seeding arg to allow selecting old vs updated data loader worker seed for (old) experiment repeatability	2021-09-28 16:37:45 -07:00
mixup.py	Fix bugs that Mixup does not work device=cpu	2021-10-12 23:51:46 +09:00
random_erasing.py	Add repr to auto_augment and random_erasing impl	2021-10-28 17:33:36 -07:00
real_labels.py	…
tf_preprocessing.py	Remove some old __future__ imports	2021-01-03 11:24:16 -08:00
transforms.py	Add interpolation mode handling to transforms. Removes InterpolationMode warning. Works for torchvision versions w/ and w/o InterpolationMode enum. Fix #738.	2021-10-28 17:35:01 -07:00
transforms_factory.py	Add interpolation mode handling to transforms. Removes InterpolationMode warning. Works for torchvision versions w/ and w/o InterpolationMode enum. Fix #738.	2021-10-28 17:35:01 -07:00