ff21fdb41d
Update README.md ready for merge
2 years ago
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
2 years ago
b049a5c5c6
Merge remote-tracking branch 'origin/master' into norm_norm_norm
2 years ago
7cdd164d77
Fix #1184 , scheduler noise bug during merge madness
2 years ago
9440a50c95
Merge branch 'mrT23-master'
2 years ago
d98aa47d12
Revert ml-decoder changes to model factory and train script
2 years ago
04db5833eb
Merge pull request #986 from hankyul2/master
...
fix: typo of argment parser desc in train.py
2 years ago
b20665d379
Merge pull request #1007 from qwertyforce/patch-1
...
update arxiv link
2 years ago
d66b4c2355
Merge pull request #801 from developer0hye/patch-1
...
fix a typo in ### Select specific feature levels or limit the stride
2 years ago
7a0994f581
Merge pull request #1150 from ChristophReich1996/master
...
Swin Transformer V2
2 years ago
d757fecaac
Merge pull request #1112 from ayasyrev/sched_noise_dup_code
...
sched noise dup code remove
2 years ago
61d3493f87
Fix hf-hub handling when hf-hub is config source
2 years ago
5f47518f27
Fix pit implementation to be clsoer to deit/levit re distillation head handling
2 years ago
0862e6ebae
Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet
2 years ago
94bcdebd73
Add latest weights trained on TPU-v3 VM instances
2 years ago
0557c8257d
Fix bug introduced in non layer_decay weight_decay application. Remove debug print, fix arg desc.
2 years ago
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
2 years ago
1420c118df
Missed comitting outstanding changes to default_cfg keys and test exclusions for swin v2
2 years ago
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
2 years ago
67d140446b
Fix bug in classification head
2 years ago
29add820ac
Refactor (back to relative imports)
2 years ago
74a04e0016
Add parameter to change normalization type
2 years ago
2a4f6c13dd
Create model functions
2 years ago
87b4d7a29a
Add get and reset classifier method
2 years ago
ff5f6bcd6c
Check input resolution
2 years ago
81bf0b4033
Change parameter names to match Swin V1
2 years ago
f227b88831
Add initials (CR) to model and file
2 years ago
90dc74c450
Add code from https://github.com/ChristophReich1996/Swin-Transformer-V2 and change docstring style to match timm
2 years ago
7c67d6aca9
Update README.md
2 years ago
2c3870e107
semobilevit_s for good measure
2 years ago
bcaeb91b03
Version to 0.6.0, possible interface incompatibilities vs 0.5.x
2 years ago
58ba49c8ef
Add MobileViT models (w/ ByobNet base). Close #1038 .
2 years ago
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...
2 years ago
cf57695938
sched noise dup code remove
2 years ago
95cfc9b3e8
Merge remote-tracking branch 'origin/master' into norm_norm_norm
2 years ago
abc9ba2544
Transitioning default_cfg -> pretrained_cfg. Improving handling of pretrained_cfg source (HF-Hub, files, timm config, etc). Checkpoint handling tweaks.
2 years ago
07379c6d5d
Add vit_base2_patch32_256 for a model between base_patch16 and patch32 with a slightly larger img size and width
2 years ago
cf4334391e
Update benchmark and validate scripts to output results in JSON with a fixed delimiter for use in multi-process launcher
2 years ago
1331c145a3
Add train benchmark results, adjust name scheme for inference and train benchmark files.
2 years ago
a517bf6a7a
Merge pull request #1105 from kozistr/refactor/remove-condition
...
Remove checking `smoothing` parameter
2 years ago
56a6b38f76
refactor: remove if-condition
2 years ago
447677616f
version 0.5.5
2 years ago
499c4749d7
Add update NCHW and NHWC inference benchmark numbers for current models. Flip name of 'sam' vit models in results files
2 years ago
83b40c5a58
Last batch of small model weights (for now). mobilenetv3_small 050/075/100 and updated mnasnet_small with lambc/lamb optimizer.
2 years ago
7f73252716
Merge pull request #1094 from Mi-Peng/lars
...
fix lars
2 years ago
cdcd0a92ca
fix lars
2 years ago
2d4b7e7080
Update results csvs for latest release
2 years ago
1aa617cb3b
Add AvgPool2d anti-aliasing support to ResNet arch (as per OpenAI CLIP models), add a few blur aa models as well
2 years ago
f0f9eccda8
Add --fuser arg to train/validate/benchmark scripts to select jit fuser type
2 years ago
010b486590
Add Dino pretrained weights (no head) for vit models. Add support to tests and helpers for models w/ no classifier (num_classes=0 in pretrained cfg)
2 years ago
Ross Wightman
Ross Wightman
Christoph Reich
ayasyrev
kozistr
Mi-Peng