92b91af3bb
version 0.6.6
2 years ago
05313940e2
Add cs3darknet_x, cs3sedarknet_l, and darknetaa53 weights from TPU sessions. Move SE btwn conv1 & conv2 in DarkBlock. Improve SE/attn handling in Csp/DarkNet. Fix leaky_relu bug on older csp models.
2 years ago
51cca82aa1
👽 use hf_hub_download instead of cached_download
2 years ago
324a4e58b6
disable nvfuser for jit te/legacy modes (for PT 1.12+)
2 years ago
2898cf6e41
version 0.6.5 for pypi release
2 years ago
a45b4bce9a
x and xx small edgenext models do benefit from larger test input size
2 years ago
a8e34051c1
Unbreak gamma remap impacting beit checkpoint load, version bump to 0.6.4
2 years ago
1c5cb819f9
bump version to 0.6.3 before merge
2 years ago
a1cb25066e
Add edgnext_small_rw weights trained with swin like recipe. Better than original 'small' but not the recent 'USI' distilled weights.
2 years ago
7c7ecd2492
Add --use-train-size flag to force use of train input_size (over test input size) for validation. Default test-time pooling to use train input size (fixes issues).
2 years ago
ce65a7b29f
Update vit_relpos w/ some additional weights, some cleanup to match recent vit updates, more MLP log coord experiments.
2 years ago
58621723bd
Add CrossStage3 DarkNet (cs3) weights
2 years ago
9be0c84715
Change set -> dict w/ None keys for dataset split synonym search, so always consistent if more than 1 exists. Fix #1224
2 years ago
db0cee9910
Refactor cspnet configuration using dataclasses, update feature extraction for new cs3 variants.
2 years ago
eca09b8642
Add MobileVitV2 support. Fix #1332 . Move GroupNorm1 to common layers (used in poolformer + mobilevitv2). Keep ol custom ConvNeXt LayerNorm2d impl as LayerNormExp2d for reference.
2 years ago
06307b8b41
Remove experimental downsample in block support in ConvNeXt. Experiment further before keeping it in.
2 years ago
bfc0dccb0e
Improve image extension handling, add methods to modify / get defaults. Fix #1335 fix #1274 .
2 years ago
7d4b3807d5
Support DeiT-3 (Revenge of the ViT) checkpoints. Add non-overlapping (w/ class token) pos-embed support to vit.
2 years ago
d0c5bd5722
Rename cs2->cs3 for darknets. Fix features_only for cs3 darknets.
2 years ago
d765305821
Remove first_conv for resnetaa50 def
2 years ago
dd9b8f57c4
Add feature_info to edgenext for features_only support, hopefully fix some fx / test errors
2 years ago
377e9bfa21
Add TPU trained darknet53 weights. Add mising pretrain_cfg for some csp/darknet models.
2 years ago
c170ba3173
Add weights for resnet10t, resnet14t, and resnetaa50 models. Fix #1314
2 years ago
188c194b0f
Left some experiment stem code in convnext by mistake
2 years ago
70d6d2c484
support test_crop_size in data config resolve
2 years ago
6064d16a2d
Add initial EdgeNeXt import. Significant cleanup / reorg (like ConvNeXt). Fix #1320
...
* edgenext refactored for torchscript compat, stage base organization
* slight refactor of ConvNeXt to match some EdgeNeXt additions
* remove use of funky LayerNorm layer in ConvNeXt and just use nn.LayerNorm and LayerNorm2d (permute)
2 years ago
7a9c6811c9
Add eps arg to LayerNorm2d, add 'tf' (tensorflow) variant of trunc_normal_ that applies scale/shift after sampling (instead of needing to move a/b)
2 years ago
82c311d082
Add more experimental darknet and 'cs2' darknet variants (different cross stage setup, closer to newer YOLO backbones) for train trials.
2 years ago
a050fde5cd
Add resnet10t (basic block) and resnet14t (bottleneck) with 1,1,1,1 repeats
2 years ago
e6d7df40ec
no longer a point using kwargs for pretrain_cfg resolve, just pass explicit arg
2 years ago
07d0c4ae96
Improve repr for DropPath module
2 years ago
e27c16b8a0
Remove unecessary code for synbn guard
2 years ago
0da3c9ebbf
Remove SiLU layer in default args that breaks import on old old PyTorch
2 years ago
7d657d2ef4
Improve resolve_pretrained_cfg behaviour when no cfg exists, warn instead of crash. Improve usability ex #1311
2 years ago
879df47c0a
Support BatchNormAct2d for sync-bn use. Fix #1254
2 years ago
7cedc8d474
Follow up to #1256 , fix interpolation warning in auto_autoaugment as well
2 years ago
db64393c0d
use `Image.Resampling` namespace for PIL mapping ( #1256 )
...
* use `Image.Resampling` namespace for PIL mapping
PIL shows a deprecation warning when accessing resampling constants via the `Image` namespace. The suggested namespace is `Image.Resampling`. This commit updates `_pil_interpolation_to_str` to use the `Image.Resampling` namespace.
```
/tmp/ipykernel_11959/698124036.py:2: DeprecationWarning: NEAREST is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.NEAREST or Dither.NONE instead.
Image.NEAREST: 'nearest',
/tmp/ipykernel_11959/698124036.py:3: DeprecationWarning: BILINEAR is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BILINEAR instead.
Image.BILINEAR: 'bilinear',
/tmp/ipykernel_11959/698124036.py:4: DeprecationWarning: BICUBIC is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BICUBIC instead.
Image.BICUBIC: 'bicubic',
/tmp/ipykernel_11959/698124036.py:5: DeprecationWarning: BOX is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BOX instead.
Image.BOX: 'box',
/tmp/ipykernel_11959/698124036.py:6: DeprecationWarning: HAMMING is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.HAMMING instead.
Image.HAMMING: 'hamming',
/tmp/ipykernel_11959/698124036.py:7: DeprecationWarning: LANCZOS is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.LANCZOS instead.
Image.LANCZOS: 'lanczos',
```
* use new pillow resampling enum only if it exists
2 years ago
20a1fa63f8
Make dev version 0.6.2.dev0 for pypi pre
2 years ago
347308faad
Update README.md, version to 0.6.2
2 years ago
4b30bae67b
Add updated vit_relpos weights, and impl w/ support for official swin-v2 differences for relpos. Add bias control support for MLP layers
2 years ago
d4c0588012
Remove persistent buffers from Swin-V2. Change SwinV2Cr cos attn + tau/logit_scale to match official, add ckpt convert, init_value zeros resid LN weight by default
2 years ago
27c42f0830
Fix torchscript use for offician Swin-V2, add support for non-square window/shift to WindowAttn/Block
2 years ago
2f2b22d8c7
Disable nvfuser fma / opt level overrides per #1244
2 years ago
c0211b0bf7
Swin-V2 test fixes, typo
2 years ago
9a86b900fa
Official SwinV2 models
2 years ago
d07d015173
Merge pull request #1249 from okojoalg/sequencer
...
Add Sequencer
2 years ago
d30685c283
Merge pull request #1251 from hankyul2/fix-multistep-scheduler
...
fix: multistep lr decay epoch bugs
2 years ago
a16171335b
fix: change milestones to decay-milestones
...
- change argparser option `milestone` to `decay-milestone`
2 years ago
39b725e1c9
Fix tests for rank-4 output where feature channels dim is -1 (3) and not 1
2 years ago
78a32655fa
Fix poolformer group_matcher to merge proj downsample with previous block, support coarse
2 years ago
d79f3d9d1e
Fix torchscript use for sequencer, add group_matcher, forward_head support, minor formatting
2 years ago
37b6920df3
Fix group_matcher regex for regnet.py
2 years ago
93a79a3dd9
Fix num_features in Sequencer
2 years ago
57a988df30
fix: multistep lr decay epoch bugs
...
- add milestones arguments
- change decay_epochs to milestones variable
2 years ago
578d52e752
Add Sequencer
2 years ago
f5ca4141f7
Adjust arg order for recent vit model args, add a few comments
2 years ago
41dc49a337
Vision Transformer refactoring and Rel Pos impl
2 years ago
b7cb8d0337
Add Swin-V2 Small-NS weights (83.5 @ 224). Add layer scale like 'init_values' via post-norm LN weight scaling
2 years ago
f88c606fcf
fixing channels_last on cond_conv2d; update nvfuser debug env variable
2 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.
2 years ago
52ac881402
Missed first_conv in latest seresnext 'D' default_cfgs
2 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.
2 years ago
8f0bc0591e
fix convnext args
2 years ago
c5a8e929fb
Add initial swinv2 tiny / small weights
2 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]
2 years ago
ec4e9aa5a0
Add ConvNeXt tiny and small pretrain in22k
...
Add ConvNeXt tiny and small pretrain in22k from ConvNeXt repo:
06f7b05f92
2 years ago
575924ed60
Update test crop for new RegNet-V weights to match Y
2 years ago
1618527098
Add layer scale and parallel blocks to vision_transformer
2 years ago
c42be74621
Add attrib / comments about Swin-S3 (AutoFormerV2) weights
2 years ago
474ac906a2
Add 'head norm first' convnext_tiny_hnf weights
2 years ago
dc51334cdc
Fix pruned adapt for EfficientNet models that are now using BatchNormAct layers
2 years ago
024fc4d9ab
version 0.6.1 for master
2 years ago
e1e037ba52
Fix bad tuple typing fix that was on XLA branch bust missed on master merge
2 years ago
341b464a5a
Remove redundant noise attr from Plateau scheduler (use parent)
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
b20665d379
Merge pull request #1007 from qwertyforce/patch-1
...
update arxiv link
2 years ago
7a0994f581
Merge pull request #1150 from ChristophReich1996/master
...
Swin Transformer V2
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
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
447677616f
version 0.5.5
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
cdcd0a92ca
fix lars
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
738a9cd635
unbiased=False for torch.var_mean path of ConvNeXt LN. Fix #1090
2 years ago
e0c4eec4b6
Default conv_mlp to False across the board for ConvNeXt, causing issues on more setups than it's improving right now...
2 years ago
b669f4a588
Add ConvNeXt 22k->1k fine-tuned and 384 22k-1k fine-tuned weights after testing
2 years ago
e967c72875
Update REAMDE.md. Sneak in g/G (giant / gigantic?) ViT defs from scaling paper
2 years ago
9ca3437178
Add some more small model weights lcnet, mnas, mnv2
2 years ago
fa6463c936
Version 0.5.4
2 years ago
fa81164378
Fix stem width for really small mobilenetv3 arch defs
2 years ago
edd3d73695
Add missing dropout for head reset in ConvNeXt default head
2 years ago
b093dcb46d
Some convnext cleanup, remove in place mul_ for gamma, breaking symbolic trace, cleanup head a bit...
2 years ago
18934debc5
Add initial ConvNeXt impl (mods of official code)
2 years ago
656757d26b
Fix MobileNetV2 head conv size for multiplier < 1.0. Add some missing modification copyrights, fix starting date of some old ones.
2 years ago
ccfeb06936
Fix out_indices handling breakage, should have left as per vgg approach.
3 years ago
a9f91483a6
Fix #1078 , DarkNet has 6 feature maps. Make vgg and darknet out_indices handling/comments equivalent
3 years ago
c21b21660d
visformer supports spatial feat map, update pool_size in pretrained cfg to match
3 years ago
9c11dfd9cb
Fix fbnetv3 pretrained cfg changes
3 years ago
1406cddc2e
FBNetV3 timm trained weights added for b/d/g variants. Update version to 0.5.2 for pypi release.
3 years ago
02ae11e526
Leaving repeat aug sampler indices as tensor thrashes worker shared process memory
3 years ago
4df51f3932
Add lcnet_100 and mnasnet_small weights
3 years ago
5ccf682a8f
Remove deprecated bn-tf train arg and create_model handler. Add evos/evob models back into fx test filter until norm_norm_norm branch merged.
3 years ago
b9a715c86a
Add more small model defs for MobileNetV3/V2/LCNet
3 years ago
b27c21b09a
Update drop_path and drop_block (fast impl) to be symbolically traceable, slightly faster
3 years ago
214c84a235
Disable use of timm nn.Linear wrapper since AMP autocast + torchscript use appears fixed
3 years ago
72b57163d1
Merge branch 'master' of https://github.com/mrT23/pytorch-image-models into mrT23-master
3 years ago
de5fa791c6
Merge branch 'master' into norm_norm_norm
3 years ago
26ff57f953
Add more small model defs for MobileNetV3/V2/LCNet
3 years ago
a0b2657497
Use `torch.repeat_interleave()` to generate repeated indices faster ( #1058 )
...
* update: use numpy to generate repeated indices faster
* update: use torch.repeat_interleave() instead of np.repeat()
* refactor: remove unused import, numpy
* refactor: torch.range to torch.arange
* update: tensor to list before appending the extra samples
* update: concatenate the paddings with torch.cat
3 years ago
450ac6a0f5
Post merge tinynet fixes for pool_size, feature extraction
3 years ago
a04164cd75
Merge branch 'tinynet' of https://github.com/rsomani95/pytorch-image-models into rsomani95-tinynet
3 years ago
8a93ce6ee3
Fix regnetv/w tests, refactor regnet generator code a bit
3 years ago
4dec8c8087
Fix skip path regression for updated EfficientNet and RegNet def. Add Pre-Act RegNet support (experimental). Remove BN-TF flag. Add efficientnet_b0_g8_gn model.
3 years ago
a52a614475
Remove layer experiment which should not have been added
3 years ago
ab49d275de
Significant norm update
...
* ConvBnAct layer renamed -> ConvNormAct and ConvNormActAa for anti-aliased
* Significant update to EfficientNet and MobileNetV3 arch to support NormAct layers and grouped conv (as alternative to depthwise)
* Update RegNet to add Z variant
* Add Pre variant of XceptionAligned that works with NormAct layers
* EvoNorm matches bits_and_tpu branch for merge
3 years ago
31bcd36e46
add tinynet models
3 years ago
b4b8d1ec18
fix hard-coded strides
3 years ago
d04f2f1377
Update drop_path and drop_block (fast impl) to be symbolically traceable, slightly faster
3 years ago
834a9ec721
Disable use of timm nn.Linear wrapper since AMP autocast + torchscript use appears fixed
3 years ago
78912b6375
Updated EvoNorm implementations with some experimentation. Add FilterResponseNorm. Updated RegnetZ and ResNetV2 model defs for trials.
3 years ago
55adfbeb8d
Add commented code to increase open file limit via Python (for TFDS dataset building)
3 years ago
Ross Wightman
nateraw
Jakub Kaczmarzyk
Ross Wightman
han
okojoalg
jjsjann123
Li Dong
SeeFun
Christoph Reich
ayasyrev
Mi-Peng
Hyeongchan Kim
Rahul Somani
KAI ZHAO