39b725e1c9
Fix tests for rank-4 output where feature channels dim is -1 (3) and not 1
3 years ago
d79f3d9d1e
Fix torchscript use for sequencer, add group_matcher, forward_head support, minor formatting
3 years ago
93a79a3dd9
Fix num_features in Sequencer
3 years ago
2fec08e923
Add Sequencer to non std filters
3 years ago
578d52e752
Add Sequencer
3 years ago
7d235c5a5f
Merge pull request #1230 from donglixp/patch-1
...
migrate azure blob for beit checkpoints
3 years ago
09e9f3defb
migrate azure blob for beit checkpoints
...
## Motivation
We are going to use a new blob account to store the checkpoints.
## Modification
Modify the azure blob storage URLs for BEiT checkpoints.
3 years ago
52ac881402
Missed first_conv in latest seresnext 'D' default_cfgs
3 years ago
7629d8264d
Add two new SE-ResNeXt101-D 32x8d weights, one anti-aliased and one not. Reshuffle default_cfgs vs model entrypoints for resnet.py so they are better aligned.
3 years ago
fbf597049c
Update README and change timmdocs link in documentation
3 years ago
01a0e25a67
Merge pull request #1208 from seefun/master
3 years ago
8f0bc0591e
fix convnext args
3 years ago
b0d2fcf647
Merge branch 'rwightman:master' into master
3 years ago
eac2df3d2c
Update PyTorch 1.10 benchmark numbers for latest code
3 years ago
c5a8e929fb
Add initial swinv2 tiny / small weights
3 years ago
83d7a11eec
Update .gitignore, remove out of date notebooks
3 years ago
02b806e00a
Add PyTorch 1.11 train benchmark numbers
3 years ago
c9f208f7f8
Update eval results and add latest PyTorch 1.11 inference benchmarks
3 years ago
f670d98cb8
Make a few more layers symbolically traceable (remove from FX leaf modules)
...
* remove dtype kwarg from .to() calls in EvoNorm as it messed up script + trace combo
* BatchNormAct2d always uses custom forward (cut & paste from original) instead of super().forward. Fixes #1176
* BlurPool groups==channels, no need to use input.dim[1]
3 years ago
a9ecb880e5
Merge pull request #1190 from seefun/ConvNeXt-pretrain
...
Add ConvNeXt tiny and small pretrain in22k
3 years ago
5f4de2334b
Merge pull request #1 from seefun/ConvNeXt-pretrain
...
Add ConvNeXt tiny and small pretrain in22k
3 years ago
ec4e9aa5a0
Add ConvNeXt tiny and small pretrain in22k
...
Add ConvNeXt tiny and small pretrain in22k from ConvNeXt repo:
06f7b05f92
3 years ago
73ffade1f8
Update README.md
3 years ago
575924ed60
Update test crop for new RegNet-V weights to match Y
3 years ago
8f6d638887
Update README.md
3 years ago
1618527098
Add layer scale and parallel blocks to vision_transformer
3 years ago
c42be74621
Add attrib / comments about Swin-S3 (AutoFormerV2) weights
3 years ago
474ac906a2
Add 'head norm first' convnext_tiny_hnf weights
3 years ago
dc51334cdc
Fix pruned adapt for EfficientNet models that are now using BatchNormAct layers
3 years ago
024fc4d9ab
version 0.6.1 for master
3 years ago
e1e037ba52
Fix bad tuple typing fix that was on XLA branch bust missed on master merge
3 years ago
341b464a5a
Remove redundant noise attr from Plateau scheduler (use parent)
3 years ago
7514439573
Merge pull request #1014 from rwightman/norm_norm_norm
...
Normalization layer additions, model API updates, new models, new weights, and enhancements
3 years ago
ff21fdb41d
Update README.md ready for merge
3 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
3 years ago
b049a5c5c6
Merge remote-tracking branch 'origin/master' into norm_norm_norm
3 years ago
7cdd164d77
Fix #1184 , scheduler noise bug during merge madness
3 years ago
9440a50c95
Merge branch 'mrT23-master'
3 years ago
d98aa47d12
Revert ml-decoder changes to model factory and train script
3 years ago
04db5833eb
Merge pull request #986 from hankyul2/master
...
fix: typo of argment parser desc in train.py
3 years ago
b20665d379
Merge pull request #1007 from qwertyforce/patch-1
...
update arxiv link
3 years ago
d66b4c2355
Merge pull request #801 from developer0hye/patch-1
...
fix a typo in ### Select specific feature levels or limit the stride
3 years ago
7a0994f581
Merge pull request #1150 from ChristophReich1996/master
...
Swin Transformer V2
3 years ago
d757fecaac
Merge pull request #1112 from ayasyrev/sched_noise_dup_code
...
sched noise dup code remove
3 years ago
61d3493f87
Fix hf-hub handling when hf-hub is config source
3 years ago
5f47518f27
Fix pit implementation to be clsoer to deit/levit re distillation head handling
3 years ago
0862e6ebae
Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet
3 years ago
94bcdebd73
Add latest weights trained on TPU-v3 VM instances
3 years ago
0557c8257d
Fix bug introduced in non layer_decay weight_decay application. Remove debug print, fix arg desc.
3 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
3 years ago
Ross Wightman