bdc9fad638
Fix compatible BUG: QMNIST and ImageNet datasets do not exist in torchvision 0.10.1.
2 years ago
9b114754db
refactor push_to_hub helper
2 years ago
ae0a0db7de
Create repo before cloning with Repository.clone_from
2 years ago
803254bb40
Fix spacing misalignment for fast norm path in LayerNorm modules
2 years ago
475ecdfa3d
cast env var args for dataset readers to int
2 years ago
39190f5f44
Remove inplace operators when calculating the loss
...
Remove inplace operators to overcome the following error when using `asymmetric_loss`
```
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation
```
2 years ago
6635bc3f7d
Merge pull request #1479 from rwightman/script_cleanup
...
Train / val script enhancements, non-GPU (ie CPU) device support, HF datasets support, TFDS/WDS dataloading improvements
2 years ago
0e6023f032
Merge pull request #1381 from ChristophReich1996/master
...
Fix typo in PositionalEncodingFourier
2 years ago
66f4af7090
Merge remote-tracking branch 'origin/master' into script_cleanup
2 years ago
d3961536c9
comment some debug logs for WDS dataset
2 years ago
e9dccc918c
Rename dataset/parsers -> dataset/readers, create_parser to create_reader, etc
2 years ago
8c28363dc9
Version 0.7.dev0 for master
2 years ago
30bafd7347
🔖 add dev suffix to version tag
2 years ago
f67a7ee8bd
Set num_workers in Iterable WDS/TFDS datasets early so sample estimate is correct
2 years ago
cea8df3d0c
Version 0.6.12
2 years ago
9914f744dc
Add more maxxvit weights includ ConvNeXt conv block based experiments.
2 years ago
b1b024dfed
Scheduler update, add v2 factory method, support scheduling on updates instead of just epochs. Add LR to summary csv. Add lr_base scaling calculations to train script. Fix #1168
2 years ago
4f18d6dc5f
Fix logs in WDS parser
2 years ago
8fda68aff6
Fix repo id bug
...
This to fix this issue #1482
2 years ago
b8c8550841
Data improvements. Improve train support for in_chans != 3. Add wds dataset support from bits_and_tpu branch w/ fixes and tweaks. TFDS tweaks.
2 years ago
7327792f39
update to support pickle based dictionaries
2 years ago
1199c5a1a4
clip_laion2b models need 1e-5 eps for LayerNorm
2 years ago
87939e6fab
Refactor device handling in scripts, distributed init to be less 'cuda' centric. More device args passed through where needed.
2 years ago
c88947ad3d
Add initial Hugging Face Datasets parser impl.
2 years ago
e858912e0c
Add brute-force checkpoint remapping option
2 years ago
b293dfa595
Add CL SE module
2 years ago
2a296412be
Add Adan optimizer
2 years ago
5dc4343308
version 0.6.11
2 years ago
a383ef99f5
Make huggingface_hub necessary if it's the only source for a pretrained weight
2 years ago
33e30f8c8b
Remove layer-decay print
2 years ago
e069249a2d
Add hf hub entries for laion2b clip models, add huggingface_hub dependency, update some setup/reqs, torch >= 1.7
2 years ago
9d65557be3
Fix errant import
2 years ago
9709dbaaa9
Adding support for fine-tune CLIP LAION-2B image tower weights for B/32, L/14, H/14 and g/14. Still WIP
2 years ago
a520da9b49
Update tresnet features_info for v2
2 years ago
c8ab747bf4
BEiT-V2 checkpoints didn't remove 'module' from weights, adapt checkpoint filter
2 years ago
73049dc2aa
Fix type in dla weight update
2 years ago
3599c7e6a4
version 0.6.10
2 years ago
e11efa872d
Update a bunch of weights with external links to timm release assets. Fixes issue with *aliyuncs.com returning forbidden. Did pickle scan / verify and re-hash. Add TresNet-V2-L weights.
2 years ago
fa8c84eede
Update maxvit_tiny_256 weight to better iter, add coatnet / maxvit / maxxvit model defs for future runs
2 years ago
c1b3cea19d
Add maxvit_rmlp_tiny_rw_256 model def and weights w/ 84.2 top-1 @ 256, 84.8 @ 320
2 years ago
914544fc81
Add beitv2 224x224 checkpoints from https://github.com/microsoft/unilm/tree/master/beit2
2 years ago
dc90816f26
Add `maxvit_tiny_rw_224` weights 83.5 @ 224 and `maxvit_rmlp_pico_rw_256` relpos weights, 80.5 @ 256, 81.3 @ 320
2 years ago
f489f02ad1
Make gcvit window size ratio based to improve resolution changing support #1449 . Change default init to original.
2 years ago
7f1b223c02
Add maxvit_rmlp_nano_rw_256 model def & weights, make window/grid size dynamic wrt img_size by default
2 years ago
e6a4361306
pretrained_cfg entry for mvitv2_small_cls
2 years ago
f66e5f0e35
Fix class token support in MViT-V2, add small_class variant to ensure it's tested. Fix #1443
2 years ago
f1d2160d85
Update a few maxxvit comments, rename PartitionAttention -> PartitionAttenionCl for consistency with other blocks
2 years ago
eca6f0a25c
Fix syntax error (extra dataclass comma) in maxxvit.py
2 years ago
ff6a919cf5
Add --fast-norm arg to benchmark.py, train.py, validate.py
2 years ago
769ab4b98a
Clean up no_grad for trunc normal weight inits
2 years ago
48e1df8b37
Add norm/norm_act header comments
2 years ago
7c2660576d
Tweak init for convnext block using maxxvit/coatnext.
2 years ago
1d8d6f6072
Fix two default args in DenseNet blocks... fix #1427
2 years ago
527f9a4cb2
Updated to correct maxvit_nano weights...
2 years ago
b2e8426fca
Make k=stride=2 ('avg2') pooling default for coatnet/maxvit. Add weight links. Rename 'combined' partition to 'parallel'.
2 years ago
837c68263b
For ConvNeXt, use timm internal LayerNorm for fast_norm in non conv_mlp mode
2 years ago
cac0a4570a
More test fixes, pool size for 256x256 maxvit models
2 years ago
e939ed19b9
Rename internal creation fn for maxvit, has not been just coatnet for a while...
2 years ago
ffaf97f813
MaxxVit! A very configurable MaxVit and CoAtNet impl with lots of goodies..
2 years ago
8c9696c9df
More model and test fixes
2 years ago
ca52108c2b
Fix some model support functions
2 years ago
f332fc2db7
Fix some test failures, torchscript issues
2 years ago
6e559e9b5f
Add MViT (Multi-Scale) V2
2 years ago
43aa84e861
Add 'fast' layer norm that doesn't cast to float32, support APEX LN impl for slight speed gain, update norm and act factories, tweak SE for ability to disable bias (needed by GCVit)
2 years ago
c486aa71f8
Add GCViT
2 years ago
fba6ecd39b
Add EfficientFormer
2 years ago
ff4a38e2c3
Add PyramidVisionTransformerV2
2 years ago
1d8ada359a
Add timm ConvNeXt 'atto' weights, change test resolution for FB ConvNeXt 224x224 weights, add support for different dw kernel_size
2 years ago
2544d3b80f
ConvNeXt pico, femto, and nano, pico, femto ols (overlapping stem) weights and model defs
2 years ago
13565aad50
Add edgenext_base model def & weight link, update to improve ONNX export #1385
2 years ago
8ad4bdfa06
Allow ntuple to be used with string values
2 years ago
faae93e62d
Fix typo in PositionalEncodingFourier
2 years ago
7430a85d07
Update README, bump version to 0.6.8
2 years ago
ec6a28830f
Add DeiT-III 'medium' model defs and weights
2 years ago
d875a1d3f6
version 0.6.7
2 years ago
6f103a442b
Add convnext_nano weights, 80.8 @ 224, 81.5 @ 288
2 years ago
4042a94f8f
Add weights for two 'Edge' block (3x3->1x1) variants of CS3 networks.
2 years ago
c8f69e04a9
Merge pull request #1365 from veritable-tech/fix-resize-pos-embed
...
Take `no_emb_class` into account when calling `resize_pos_embed`
2 years ago
0b64117592
Take `no_emb_class` into account when calling `resize_pos_embed`
2 years ago
56c3a84db3
Update type hint for `register_notrace_module`
...
register_notrace_module is used to decorate types (i.e. subclasses of nn.Module).
It is not called on module instances.
2 years ago
1b278136c3
Change models with mean 0,0,0 std 1,1,1 from int to float for consistency as mentioned in #1355
2 years ago
909705e7ff
Remove some redundant requires_grad=True from nn.Parameter in third party code
2 years ago
c5e0d1c700
Add dilation support to convnext, allows output_stride=8 and 16 use. Fix #1341
2 years ago
dc376e3676
Ensure all model entrypoint fn default to `pretrained=False` (a few didn't)
2 years ago
23b102064a
Add cs3sedarknet_x weights w/ 82.65 @ 288 top1. Add 2 cs3 edgenet models (w/ 3x3-1x1 block), remove aa from cspnet blocks (not needed)
2 years ago
0dbd9352ce
Add bulk_runner script and updates to benchmark.py and validate.py for better error handling in bulk runs (used for benchmark and validation result runs). Improved batch size decay stepping on retry...
2 years ago
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.
3 years ago
d0c5bd5722
Rename cs2->cs3 for darknets. Fix features_only for cs3 darknets.
3 years ago
d765305821
Remove first_conv for resnetaa50 def
3 years ago
dd9b8f57c4
Add feature_info to edgenext for features_only support, hopefully fix some fx / test errors
3 years ago
377e9bfa21
Add TPU trained darknet53 weights. Add mising pretrain_cfg for some csp/darknet models.
3 years ago
c170ba3173
Add weights for resnet10t, resnet14t, and resnetaa50 models. Fix #1314
3 years ago
188c194b0f
Left some experiment stem code in convnext by mistake
3 years ago
70d6d2c484
support test_crop_size in data config resolve
3 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)
3 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)
3 years ago
82c311d082
Add more experimental darknet and 'cs2' darknet variants (different cross stage setup, closer to newer YOLO backbones) for train trials.
3 years ago
a050fde5cd
Add resnet10t (basic block) and resnet14t (bottleneck) with 1,1,1,1 repeats
3 years ago
e6d7df40ec
no longer a point using kwargs for pretrain_cfg resolve, just pass explicit arg
3 years ago
07d0c4ae96
Improve repr for DropPath module
3 years ago
e27c16b8a0
Remove unecessary code for synbn guard
3 years ago
0da3c9ebbf
Remove SiLU layer in default args that breaks import on old old PyTorch
3 years ago
7d657d2ef4
Improve resolve_pretrained_cfg behaviour when no cfg exists, warn instead of crash. Improve usability ex #1311
3 years ago
879df47c0a
Support BatchNormAct2d for sync-bn use. Fix #1254
3 years ago
7cedc8d474
Follow up to #1256 , fix interpolation warning in auto_autoaugment as well
3 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
3 years ago
20a1fa63f8
Make dev version 0.6.2.dev0 for pypi pre
3 years ago
347308faad
Update README.md, version to 0.6.2
3 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
3 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
3 years ago
27c42f0830
Fix torchscript use for offician Swin-V2, add support for non-square window/shift to WindowAttn/Block
3 years ago
2f2b22d8c7
Disable nvfuser fma / opt level overrides per #1244
3 years ago
c0211b0bf7
Swin-V2 test fixes, typo
3 years ago
9a86b900fa
Official SwinV2 models
3 years ago
d07d015173
Merge pull request #1249 from okojoalg/sequencer
...
Add Sequencer
3 years ago
d30685c283
Merge pull request #1251 from hankyul2/fix-multistep-scheduler
...
fix: multistep lr decay epoch bugs
3 years ago
a16171335b
fix: change milestones to decay-milestones
...
- change argparser option `milestone` to `decay-milestone`
3 years ago
39b725e1c9
Fix tests for rank-4 output where feature channels dim is -1 (3) and not 1
3 years ago
78a32655fa
Fix poolformer group_matcher to merge proj downsample with previous block, support coarse
3 years ago
d79f3d9d1e
Fix torchscript use for sequencer, add group_matcher, forward_head support, minor formatting
3 years ago
37b6920df3
Fix group_matcher regex for regnet.py
3 years ago
93a79a3dd9
Fix num_features in Sequencer
3 years ago
57a988df30
fix: multistep lr decay epoch bugs
...
- add milestones arguments
- change decay_epochs to milestones variable
3 years ago
578d52e752
Add Sequencer
3 years ago
f5ca4141f7
Adjust arg order for recent vit model args, add a few comments
3 years ago
41dc49a337
Vision Transformer refactoring and Rel Pos impl
3 years ago
b7cb8d0337
Add Swin-V2 Small-NS weights (83.5 @ 224). Add layer scale like 'init_values' via post-norm LN weight scaling
3 years ago
f88c606fcf
fixing channels_last on cond_conv2d; update nvfuser debug env variable
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
8f0bc0591e
fix convnext args
3 years ago
c5a8e929fb
Add initial swinv2 tiny / small weights
3 years ago
hongxin xiang