Ross Wightman
78a04a0e7d
Merge pull request #1911 from dsuess/1910-fixes-batchnormact-fx
...
Register norm_act layers as leaf modules
2023-08-11 14:34:16 -07:00
Yonghye Kwon
2048f6f20f
set self.num_features to neck_chans if neck_chans > 0
2023-08-11 13:45:06 +09:00
Ross Wightman
3a44e6c602
Fix #1912 CoaT model not loading w/ return_interm_layers
2023-08-10 11:15:58 -07:00
Daniel Suess
986de90360
Register orm_act layers as leaf modules
2023-08-10 15:37:26 +10:00
Ross Wightman
c692715388
Some RepVit tweaks
...
* add head dropout to RepVit as all models have that arg
* default train to non-distilled head output via distilled_training flag (set_distilled_training) so fine-tune works by default w/o distillation script
* camel case naming tweaks to match other models
2023-08-09 12:41:12 -07:00
alec.tu
bb2b6b5f09
fix num_classes not found
2023-08-07 15:16:03 +08:00
Ross Wightman
81089b10a2
Remove unecessary LongTensor in EfficientFormer. Possibly maybe fix #1878
2023-08-03 16:38:53 -07:00
Ross Wightman
4224529ebe
Version 0.9.5 prep for release. README update
2023-08-03 15:16:46 -07:00
Ross Wightman
d138a9bf88
Add gluon hrnet small weights, fix #1895
2023-08-03 12:15:04 -07:00
Ross Wightman
76d166981d
Fix missing norm call in Mlp forward (not used by default, but can be enabled for normformer MLP scale). Fix #1851 fix #1852
2023-08-03 11:36:30 -07:00
Ross Wightman
8e4480e4b6
Patch and pos embed resample done in float32 always (cast to float and back). Fix #1811
2023-08-03 11:32:17 -07:00
Ross Wightman
150356c493
Fix unfortunate selecsls case bug caused by aggressive IDE rename
2023-08-03 10:37:06 -07:00
Ross Wightman
6e8c53d0d3
Comment out beit url, no longer valid as now require long query string, leave for reference, must use HF hub now.
2023-08-03 10:00:46 -07:00
Sepehr Sameni
40a518c194
use float in resample_abs_pos_embed_nhwc
...
since F.interpolate doesn't always support BFloat16
2023-07-28 16:01:42 -07:00
Ross Wightman
8cb0ddac45
Update README, version 0.9.4dev0
2023-07-27 17:07:31 -07:00
Ross Wightman
a9d0615f42
Fix ijepa vit issue with 448 model, minor formatting fixes
2023-07-26 20:46:27 -07:00
alec.tu
942726db31
import lion in __init__.py
2023-07-27 09:26:57 +08:00
Ross Wightman
5874d1bfc7
Merge pull request #1876 from jameslahm/main
...
Add RepViT models
2023-07-26 14:38:41 -07:00
Ross Wightman
b10310cc27
Add proper pool size for new resnexts
2023-07-26 14:36:03 -07:00
Ross Wightman
b71d60cdb7
Two small fixes, num_classes in base class, add model tag
2023-07-26 13:18:49 -07:00
Ross Wightman
3561f8e885
Add seresnextaa201d_32x8d 12k and 1k weights
2023-07-26 13:17:05 -07:00
jameslahm
3318e7614d
Add RepViT models
2023-07-21 14:56:53 +08:00
Ruslan Baikulov
158bf129c4
Replace deprecated NumPy aliases of builtin types
2023-07-03 22:24:25 +03:00
Ross Wightman
c241081251
Merge pull request #1850 from huggingface/effnet_improve_features_only
...
Support other features only modes for EfficientNet. Fix #1848 fix #1849
2023-06-23 22:56:08 -07:00
Ross Wightman
47517dbefd
Clean more feature extract issues
...
* EfficientNet/MobileNetV3/HRNetFeatures cls and FX mode support -ve index
* MobileNetV3 allows feature_cfg mode to bypass MobileNetV3Features
2023-06-14 14:46:22 -07:00
Ross Wightman
a09c88ed0f
Support other features only modes for EfficientNet
2023-06-14 12:57:39 -07:00
SeeFun
c3f24a5ae5
‘add ViT weight from I-JEPA pretrain’
2023-06-14 22:30:31 +08:00
Ross Wightman
2d597b126d
Missed extra nadam algo step for capturable path
2023-06-13 20:51:31 -07:00
Ross Wightman
4790c0fa16
Missed nadamw.py
2023-06-13 20:45:58 -07:00
Ross Wightman
dab0360e00
Add NadamW based on mlcommons algorithm, added multi-tensor step
2023-06-13 20:45:17 -07:00
Ross Wightman
700aebcdc4
Fix Pytorch 2.0 breakage for Lookahead optimizer adapter
2023-06-02 08:39:07 -07:00
Lengyue
c308dbc6f2
update dinov2 layerscale init values
2023-05-24 12:20:17 -04:00
Ross Wightman
7cea88e2c4
Pop eps for lion optimizer
2023-05-21 15:20:03 -07:00
Ross Wightman
e9373b1b92
Cleanup before samvit merge. Resize abs posembed on the fly, undo some line-wraps, remove redundant unbind, fix HF hub weight load
2023-05-18 16:43:48 -07:00
方曦
c1c6eeb909
fix loading pretrained weight for samvit
2023-05-18 08:49:29 +08:00
方曦
15de561f2c
fix unit test for samvit
2023-05-17 12:51:12 +08:00
方曦
ea1f52df3e
add ViT for Segment-Anything Model
2023-05-17 11:39:29 +08:00
Ross Wightman
960202cfcc
Dev version 0.9.3 for main
2023-05-16 11:28:00 -07:00
Ross Wightman
c5d3ee47f3
Add B/16 datacompxl CLIP weights
2023-05-16 11:27:20 -07:00
Ross Wightman
3d05c0e86f
Version 0.9.2
2023-05-14 08:03:04 -07:00
Philip Keller
fc77e9ecc5
Update hub.py
...
fixed import of _hub modules
2023-05-12 21:48:46 +02:00
Ross Wightman
cc77096350
Version 0.9.1
2023-05-12 09:47:47 -07:00
Ross Wightman
f744bda994
use torch.jit.Final instead of Final for beit, eva
2023-05-12 09:12:14 -07:00
Ross Wightman
2e99bcaedd
Update README, prep for version 0.9.0 release
2023-05-11 15:22:50 -07:00
Ross Wightman
3eaf729f3f
F.sdpa for visformer fails w/o contiguous on qkv, make experimental
2023-05-11 11:37:37 -07:00
Ross Wightman
cf1884bfeb
Add 21k maxvit tf weights
2023-05-10 18:23:32 -07:00
Ross Wightman
6c2edf4d74
Missed hub_id entries for byoanet models
2023-05-10 15:58:55 -07:00
Ross Wightman
cf101b0097
Version 0.8.23dev0 and README update
2023-05-10 14:41:22 -07:00
Ross Wightman
850ab4931f
Missed a few pretrained tags...
2023-05-10 12:16:30 -07:00
Ross Wightman
ff2464e2a0
Throw when pretrained weights not available and pretrained=True (principle of least surprise).
2023-05-10 10:44:34 -07:00
