Ross Wightman
|
007bc39323
|
Some halo and bottleneck attn code cleanup, add halonet50ts weights, use optimal crop ratios
|
2021-10-02 15:51:42 -07:00 |
|
Ross Wightman
|
b81e79aae9
|
Fix bottleneck attn transpose typo, hopefully these train better now..
|
2021-09-28 16:38:41 -07:00 |
|
Ross Wightman
|
5bd04714e4
|
Cleanup weight init for byob/byoanet and related
|
2021-09-05 15:34:05 -07:00 |
|
Ross Wightman
|
8642401e88
|
Swap botnet 26/50 weights/models after realizing a mistake in arch def, now figuring out why they were so low...
|
2021-09-05 15:17:19 -07:00 |
|
Ross Wightman
|
0721559511
|
Improved (hopefully) init for SA/SA-like layers used in ByoaNets
|
2021-05-04 21:40:39 -07:00 |
|
Ross Wightman
|
ce62f96d4d
|
ByoaNet with bottleneck transformer, lambda resnet, and halo net experiments
|
2021-04-12 09:38:02 -07:00 |
|