Ross Wightman
e1e037ba52
Fix bad tuple typing fix that was on XLA branch bust missed on master merge
2022-03-21 22:00:33 -07:00
Ross Wightman
341b464a5a
Remove redundant noise attr from Plateau scheduler (use parent)
2022-03-21 22:00:03 -07:00
Ross Wightman
7514439573
Merge pull request #1014 from rwightman/norm_norm_norm
...
Normalization layer additions, model API updates, new models, new weights, and enhancements
2022-03-21 21:51:21 -07:00
Ross Wightman
ff21fdb41d
Update README.md ready for merge
2022-03-21 16:38:36 -07:00
Ross Wightman
fe457c1996
Update SwinTransformerV2Cr post-merge, update with grad checkpointing / grad matcher
...
* weight compat break, activate norm3 for final block of final stage (equivalent to pre-head norm, but while still in BLC shape)
* remove fold/unfold for TPU compat, add commented out roll code for TPU
* add option for end of stage norm in all stages
* allow weight_init to be selected between pytorch default inits and xavier / moco style vit variant
2022-03-21 14:50:28 -07:00
Ross Wightman
b049a5c5c6
Merge remote-tracking branch 'origin/master' into norm_norm_norm
2022-03-21 13:41:43 -07:00
Ross Wightman
7cdd164d77
Fix #1184 , scheduler noise bug during merge madness
2022-03-21 13:35:45 -07:00
Ross Wightman
9440a50c95
Merge branch 'mrT23-master'
2022-03-21 12:30:02 -07:00
Ross Wightman
d98aa47d12
Revert ml-decoder changes to model factory and train script
2022-03-21 12:29:02 -07:00
Ross Wightman
04db5833eb
Merge pull request #986 from hankyul2/master
...
fix: typo of argment parser desc in train.py
2022-03-21 12:13:51 -07:00
Ross Wightman
b20665d379
Merge pull request #1007 from qwertyforce/patch-1
...
update arxiv link
2022-03-21 12:12:58 -07:00
Ross Wightman
d66b4c2355
Merge pull request #801 from developer0hye/patch-1
...
fix a typo in ### Select specific feature levels or limit the stride
2022-03-21 12:11:53 -07:00
Ross Wightman
7a0994f581
Merge pull request #1150 from ChristophReich1996/master
...
Swin Transformer V2
2022-03-21 11:56:57 -07:00
Ross Wightman
d757fecaac
Merge pull request #1112 from ayasyrev/sched_noise_dup_code
...
sched noise dup code remove
2022-03-21 11:52:37 -07:00
Ross Wightman
61d3493f87
Fix hf-hub handling when hf-hub is config source
2022-03-21 11:12:55 -07:00
Ross Wightman
5f47518f27
Fix pit implementation to be clsoer to deit/levit re distillation head handling
2022-03-21 11:12:14 -07:00
Ross Wightman
0862e6ebae
Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet
2022-03-19 14:58:54 -07:00
Ross Wightman
94bcdebd73
Add latest weights trained on TPU-v3 VM instances
2022-03-18 21:35:41 -07:00
Ross Wightman
0557c8257d
Fix bug introduced in non layer_decay weight_decay application. Remove debug print, fix arg desc.
2022-02-28 17:06:32 -08:00
Ross Wightman
372ad5fa0d
Significant model refactor and additions:
...
* All models updated with revised foward_features / forward_head interface
* Vision transformer and MLP based models consistently output sequence from forward_features (pooling or token selection considered part of 'head')
* WIP param grouping interface to allow consistent grouping of parameters for layer-wise decay across all model types
* Add gradient checkpointing support to a significant % of models, especially popular architectures
* Formatting and interface consistency improvements across models
* layer-wise LR decay impl part of optimizer factory w/ scale support in scheduler
* Poolformer and Volo architectures added
2022-02-28 13:56:23 -08:00
Ross Wightman
1420c118df
Missed comitting outstanding changes to default_cfg keys and test exclusions for swin v2
2022-02-23 19:50:26 -08:00
Ross Wightman
c6e4b7895a
Swin V2 CR impl refactor.
...
* reformat and change some naming so closer to existing timm vision transformers
* remove typing that wasn't adding clarity (or causing torchscript issues)
* support non-square windows
* auto window size adjust from image size
* post-norm + main-branch no
2022-02-23 17:28:52 -08:00
Christoph Reich
67d140446b
Fix bug in classification head
2022-02-20 22:28:05 +01:00
Christoph Reich
29add820ac
Refactor (back to relative imports)
2022-02-20 00:46:48 +01:00
Christoph Reich
74a04e0016
Add parameter to change normalization type
2022-02-20 00:46:00 +01:00
Christoph Reich
2a4f6c13dd
Create model functions
2022-02-20 00:40:22 +01:00
Christoph Reich
87b4d7a29a
Add get and reset classifier method
2022-02-19 22:47:02 +01:00
Christoph Reich
ff5f6bcd6c
Check input resolution
2022-02-19 22:42:02 +01:00
Christoph Reich
81bf0b4033
Change parameter names to match Swin V1
2022-02-19 22:37:22 +01:00
Christoph Reich
f227b88831
Add initials (CR) to model and file
2022-02-19 22:14:38 +01:00
Christoph Reich
90dc74c450
Add code from https://github.com/ChristophReich1996/Swin-Transformer-V2 and change docstring style to match timm
2022-02-19 22:12:11 +01:00
Ross Wightman
7c67d6aca9
Update README.md
2022-02-02 09:15:20 -08:00
Ross Wightman
2c3870e107
semobilevit_s for good measure
2022-01-31 22:36:09 -08:00
Ross Wightman
bcaeb91b03
Version to 0.6.0, possible interface incompatibilities vs 0.5.x
2022-01-31 15:42:14 -08:00
Ross Wightman
58ba49c8ef
Add MobileViT models (w/ ByobNet base). Close #1038 .
2022-01-31 15:39:34 -08:00
Ross Wightman
5f81d4de23
Move DeiT to own file, vit getting crowded. Working towards fixing #1029 , make pooling interface for transformers and mlp closer to convnets. Still working through some details...
2022-01-26 22:53:57 -08:00
ayasyrev
cf57695938
sched noise dup code remove
2022-01-26 11:53:08 +03:00
Ross Wightman
95cfc9b3e8
Merge remote-tracking branch 'origin/master' into norm_norm_norm
2022-01-25 22:20:45 -08:00
Ross Wightman
abc9ba2544
Transitioning default_cfg -> pretrained_cfg. Improving handling of pretrained_cfg source (HF-Hub, files, timm config, etc). Checkpoint handling tweaks.
2022-01-25 21:54:13 -08:00
Ross Wightman
07379c6d5d
Add vit_base2_patch32_256 for a model between base_patch16 and patch32 with a slightly larger img size and width
2022-01-24 14:46:47 -08:00
Ross Wightman
cf4334391e
Update benchmark and validate scripts to output results in JSON with a fixed delimiter for use in multi-process launcher
2022-01-24 14:46:47 -08:00
Ross Wightman
1331c145a3
Add train benchmark results, adjust name scheme for inference and train benchmark files.
2022-01-23 14:08:30 -08:00
Ross Wightman
a517bf6a7a
Merge pull request #1105 from kozistr/refactor/remove-condition
...
Remove checking `smoothing` parameter
2022-01-21 13:40:22 -08:00
kozistr
56a6b38f76
refactor: remove if-condition
2022-01-21 14:19:11 +09:00
Ross Wightman
447677616f
version 0.5.5
2022-01-20 21:18:30 -08:00
Ross Wightman
499c4749d7
Add update NCHW and NHWC inference benchmark numbers for current models. Flip name of 'sam' vit models in results files
2022-01-20 10:40:04 -08:00
Ross Wightman
83b40c5a58
Last batch of small model weights (for now). mobilenetv3_small 050/075/100 and updated mnasnet_small with lambc/lamb optimizer.
2022-01-19 10:02:02 -08:00
Ross Wightman
7f73252716
Merge pull request #1094 from Mi-Peng/lars
...
fix lars
2022-01-19 08:39:49 -08:00
Mi-Peng
cdcd0a92ca
fix lars
2022-01-19 17:49:43 +08:00
Ross Wightman
2d4b7e7080
Update results csvs for latest release
2022-01-18 22:56:45 -08:00
