Ross Wightman e2b8d44ff0 Halo, bottleneck attn, lambda layer additions and cleanup along w/ experimental model defs ...

* align interfaces of halo, bottleneck attn and lambda layer
* add qk_ratio to all of above, control q/k dim relative to output dim
* add experimental haloregnetz, and trionet (lambda + halo + bottle) models

2021-10-06 16:32:48 -07:00

..

data

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

loss

Update binary cross ent impl to use thresholding as an option (convert soft targets from mixup/cutmix to 0, 1)

2021-09-23 15:45:39 -07:00

models

Halo, bottleneck attn, lambda layer additions and cleanup along w/ experimental model defs

2021-10-06 16:32:48 -07:00

optim

Add lamb/lars to optim init imports, remove stray comment

2021-08-18 22:55:02 -07:00

scheduler

LR scheduler update:

2021-09-01 17:33:11 -07:00

utils

Tweak accuracy topk safety. Fix #807

2021-08-19 14:18:53 -07:00

__init__.py

…

version.py

Version bump to 0.5.0 for pending release post RSB and ATTN updates

2021-10-03 17:34:57 -07:00