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
0ca687f224
Make 'regnetz' model experiments closer to actual RegNetZ, bottleneck expansion, expand from in_chs, no shortcut on stride 2, tweak model sizes
2021-09-30 21:49:38 -07:00
6478bcd02c
Fix regnetz_d conv layer name, use inception mean/std
2021-09-26 14:54:17 -07:00
8e11da0ce3
Add experimental RegNetZ(ish) models for training / perf trials.
2021-09-23 15:42:57 -07:00
4027412757
Add resnet33ts weights, update resnext26ts baseline weights
2021-09-09 14:46:41 -07:00
5bd04714e4
Cleanup weight init for byob/byoanet and related
2021-09-05 15:34:05 -07:00
484e61648d
Adding the attn series weights, tweaking model names, comments...
2021-09-03 18:09:42 -07:00
8449ba210c
Improve performance of HaloAttn, change default dim calc. Some cleanup / fixes for byoanet. Rename resnet26ts to tfs to distinguish (extra fc).
2021-08-26 21:56:44 -07:00
a8b65695f1
Add resnet26ts and resnext26ts models for non-attn baselines
2021-08-21 12:42:10 -07:00
a5a542f17d
Fix typo
2021-08-20 17:47:23 -07:00
925e102982
Update attention / self-attn based models from a series of experiments:
...
* remove dud attention, involution + my swin attention adaptation don't seem worth keeping
* add or update several new 26/50 layer ResNe(X)t variants that were used in experiments
* remove models associated with dead-end or uninteresting experiment results
* weights coming soon...
2021-08-20 16:13:11 -07:00
392368e210
Add efficientnetv2_rw_t defs w/ weights, and gc variant, as well as gcresnet26ts for experiments. Version 0.4.13
2021-07-09 16:46:52 -07:00
d17b374f0f
Minimum input_size needed to be higher
2021-06-08 21:31:39 -07:00
b3b90d944d
Add min_input_size to bat_resnext to prevent test breakage.
2021-06-08 17:32:08 -07:00
10d8fa4620
Add gc and bat attention resnext26ts variants to byob for test.
2021-06-08 14:21:07 -07:00
307a935b79
Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.
2021-05-31 13:18:11 -07:00
9611458e19
Throw in some FBNetV3 code I had lying around, some refactoring of SE reduction channel calcs for all EffNet archs.
2021-05-28 20:47:24 -07:00
02f9d4bc34
Add weights for resnet51q model, add 61q def.
2021-05-28 09:53:16 -07:00
f615474be3
Fix broken test, repvgg block doesn't have attn_last attr.
2021-05-27 18:12:22 -07:00
742c2d5247
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
2021-05-27 18:03:29 -07:00
9a3ae97311
Another set of byoanet models w/ ECA channel + SA + groups
2021-05-15 22:56:51 -07:00
b3d7580df1
Update ByoaNet comments. Fix first Steam feat chs for ByobNet.
2021-04-12 12:11:35 -07:00
7c97e66f7c
Remove commented code, add more consistent seed fn
2021-04-12 09:51:36 -07:00
ce62f96d4d
ByoaNet with bottleneck transformer, lambda resnet, and halo net experiments
2021-04-12 09:38:02 -07:00
6853b07bbd
Improve RegVGG block identity/vs non for clariy and fix attn usage. Add comments.
2021-02-10 14:40:29 -08:00
dc85e5a237
Add ByobNet w/ GPU-EfficientNets and RepVGG. Also add classic vgg models.
2021-02-09 16:22:52 -08:00
Ross Wightman