Ross Wightman a435ea1327 Change reduce_bn to distribute_bn, add ability to choose between broadcast and reduce (mean). Add crop_pct arg to allow selecting validation crop while training.

2019-12-19 22:56:54 -08:00

..

data

Switch RandoErasing back to on GPU normal sampling

2019-12-05 22:35:08 -08:00

loss

…

models

New PyTorch trained EfficientNet-B2 weights with my RandAugment impl

2019-12-04 11:09:47 -08:00

optim

Add Nvidia's NovogGrad impl from Jasper (cleaner/faster than current) and Apex Fused optimizers

2019-08-29 15:21:38 -07:00

scheduler

…

__init__.py

…

utils.py

Change reduce_bn to distribute_bn, add ability to choose between broadcast and reduce (mean). Add crop_pct arg to allow selecting validation crop while training.

2019-12-19 22:56:54 -08:00

version.py

…