Fredo Guan
c959f1d14c
Update davit.py
3 years ago
Fredo Guan
29eb0a675c
Update davit.py
3 years ago
Fredo Guan
4bee8f5394
Update davit.py
3 years ago
Fredo Guan
9fb41cc67e
Update davit.py
3 years ago
Fredo Guan
feb3f51765
Update davit.py
3 years ago
Fredo Guan
b2dfa60557
Update davit.py
3 years ago
Fredo Guan
69528d2dc2
Update davit.py
3 years ago
Fredo Guan
962b12e166
Update davit.py
3 years ago
Fredo Guan
bca73b7ec2
Update davit.py
3 years ago
Fredo Guan
00c7a7e32f
Update davit.py
3 years ago
Fredo Guan
6812acbb72
Update davit.py
3 years ago
Fredo Guan
1d7c04e28a
Update davit.py
3 years ago
Fredo Guan
5a9f582271
Update davit.py
3 years ago
Fredo Guan
8ac5ec2d88
Update davit.py
3 years ago
Fredo Guan
4a936b92a9
Update davit.py
3 years ago
Fredo Guan
9ad97c9fb1
Update davit.py
3 years ago
Fredo Guan
2faeaebfee
Update davit.py
3 years ago
Fredo Guan
e7c5ab9d1e
Update davit.py
3 years ago
Fredo Guan
e643c36488
Update davit.py
3 years ago
Fredo Guan
0de8313183
Update davit.py
3 years ago
Fredo Guan
dbf38cd45b
Update davit.py
3 years ago
Fredo Guan
15b168e305
Update davit.py
3 years ago
Fredo Guan
cd82d53149
Update davit.py
3 years ago
Fredo Guan
f6993dbf20
Update davit.py
3 years ago
Fredo Guan
7997ddc30d
Update davit.py
3 years ago
Fredo Guan
d35e98b7fa
Update davit.py
3 years ago
Fredo Guan
c42e26f866
Update davit.py
3 years ago
Fredo Guan
d1e68fa33f
Update davit.py
3 years ago
Fredo Guan
4ba893ceae
Update davit.py
3 years ago
Fredo Guan
6d135d22c7
Update davit.py
3 years ago
Fredo Guan
889c2ca728
Update davit.py
3 years ago
Fredo Guan
eef8673a93
Update davit.py
3 years ago
Fredo Guan
007be8319b
Update davit.py
3 years ago
Fredo Guan
8f32133dbb
Update davit.py
3 years ago
Fredo Guan
3b993a9301
Update davit.py
3 years ago
Fredo Guan
f7a8fb9f97
Update davit.py
3 years ago
Ross Wightman
98047ef5e3
Add EVA FT results, hopefully fix BEiT test failures
3 years ago
Ross Wightman
3cc4d7a894
Fix missing register for 224 eva model
3 years ago
Ross Wightman
eba07b0de7
Add eva models to beit.py
3 years ago
Fredo Guan
11f27df29f
Merge branch 'main' into davit
3 years ago
Fredo Guan
36527b5a33
Update davit.py
3 years ago
Fredo Guan
f8c5150fcd
Update davit.py
3 years ago
Fredo Guan
625bb86a64
Update davit.py
3 years ago
Fredo Guan
e9a16ee19d
Update davit.py
3 years ago
Fredo Guan
c82f9204e7
Update davit.py
3 years ago
Fredo Guan
a813bbd1df
Update davit.py
3 years ago
Fredo Guan
62b9d696b0
Update davit.py
3 years ago
Fredo Guan
375be19be6
Update davit.py
3 years ago
Fredo Guan
8e421bccfb
Update davit.py
3 years ago
Fredo Guan
5c7c8f2e36
Update davit.py
3 years ago
Fredo Guan
c1a5882c5a
Update davit.py
3 years ago
Fredo Guan
96e0b06ee1
Update davit.py
3 years ago
Fredo Guan
234748cf30
Update davit.py
3 years ago
Fredo Guan
b3526cc9a4
Update davit.py
3 years ago
Fredo Guan
deb3e09b3d
Update davit.py
3 years ago
Fredo Guan
e222f474f4
Update davit.py
3 years ago
Fredo Guan
90a71c35b3
Update davit.py
3 years ago
Fredo Guan
f1fff20524
Update davit.py
3 years ago
Fredo Guan
02f9f76ac8
Update davit.py
3 years ago
Fredo Guan
222dca8f7b
Update davit.py
3 years ago
Fredo Guan
6b3a266988
Update davit.py
3 years ago
Fredo Guan
792564543c
Update davit.py
3 years ago
Fredo Guan
128d9729c3
Update davit.py
3 years ago
Fredo Guan
143a239e93
Update davit.py
3 years ago
Fredo Guan
5f0a9e9a9f
Update davit.py
3 years ago
Fredo Guan
6abb3ba634
Update davit.py
3 years ago
Fredo Guan
e8fd52e39f
Update davit.py
3 years ago
Fredo Guan
c902731699
Update davit.py
3 years ago
Fredo Guan
2a55d9516e
Update davit.py
3 years ago
Fredo Guan
3a422f735a
Update davit.py
3 years ago
Fredo Guan
e5847a93c4
Update davit.py
3 years ago
Fredo Guan
cf1cc8b1d1
Update davit.py
3 years ago
Fredo Guan
0ed0e9ac35
Update davit.py
3 years ago
Fredo Guan
6692983832
Update davit.py
3 years ago
Fredo Guan
62eb0c4346
Update davit.py
3 years ago
Fredo Guan
c8559878fb
Update davit.py
3 years ago
Fredo Guan
3bd96609c8
Davit ( #1 )
...
Implement the davit model from https://arxiv.org/abs/2204.03645 and https://github.com/dingmyu/davit
3 years ago
Fredo Guan
6e5be758dc
Update davit.py
3 years ago
Fredo Guan
385a3bdb5e
Update davit.py
3 years ago
Fredo Guan
6521662d58
Update davit.py
3 years ago
Fredo Guan
284de330cd
Update davit.py
3 years ago
Fredo Guan
d7930c70bd
update
3 years ago
Fredo Guan
92f43964de
Create davit.py
3 years ago
Ross Wightman
3785c234d7
Remove clip vit models that won't be ft and comment two that aren't uploaded yet
3 years ago
Ross Wightman
f82239b30e
multi-weight branch version -> 0.8.0dev
3 years ago
Ross Wightman
755570e2d6
Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses
3 years ago
Ross Wightman
72cfa57761
Add ported Tensorflow MaxVit weights. Add a few more CLIP ViT fine-tunes. Tweak some model tag names. Improve model tag name sorting. Update HF hub push config layout.
3 years ago
Ross Wightman
4d5c395160
MaxVit, ViT, ConvNeXt, and EfficientNet-v2 updates
...
* Add support for TF weights and modelling specifics to MaxVit (testing ported weights)
* More fine-tuned CLIP ViT configs
* ConvNeXt and MaxVit updated to new pretrained cfgs use
* EfficientNetV2, MaxVit and ConvNeXt high res models use squash crop/resize
3 years ago
Ross Wightman
3db4e346e0
Switch TFDS dataset to use INTEGER_ACCURATE jpeg decode by default
3 years ago
Ross Wightman
9da7e3a799
Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate
3 years ago
Ross Wightman
b2b6285af7
Add two more FT clip weights
3 years ago
Ross Wightman
5895056dc4
Add openai b32 ft
3 years ago
Ross Wightman
9dea5143d5
Adding more clip ft variants
3 years ago
Ross Wightman
444dcba4ad
CLIP B16 12k weights added
3 years ago
Ross Wightman
dff4717cbf
Add clip b16 384x384 finetunes
3 years ago
Ross Wightman
883fa2eeaa
Add fine-tuned B/16 224x224 in1k clip models
3 years ago
Ross Wightman
9a3d2ac2d5
Add latest CLIP ViT fine-tune pretrained configs / model entrypt updates
3 years ago
Ross Wightman
42bbbddee9
Add missing model config
3 years ago
Ross Wightman
def68befa7
Updating vit model defs for mult-weight support trial (vit first). Prepping for CLIP (laion2b and openai) fine-tuned weights.
3 years ago
Ross Wightman
0dadb4a6e9
Initial multi-weight support, handled so old pretraing config handling co-exists with new tags.
3 years ago
hongxin xiang
653bdc7105
Fix comment: https://github.com/rwightman/pytorch-image-models/pull/1564#issuecomment-1326743424
3 years ago
hongxin xiang
bdc9fad638
Fix compatible BUG: QMNIST and ImageNet datasets do not exist in torchvision 0.10.1.
3 years ago
Wauplin
9b114754db
refactor push_to_hub helper
3 years ago
Wauplin
ae0a0db7de
Create repo before cloning with Repository.clone_from
3 years ago
Ross Wightman
803254bb40
Fix spacing misalignment for fast norm path in LayerNorm modules
3 years ago
Ross Wightman
475ecdfa3d
cast env var args for dataset readers to int
3 years ago
Hoan Nguyen
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
```
3 years ago
Ross Wightman
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
3 years ago
Ross Wightman
0e6023f032
Merge pull request #1381 from ChristophReich1996/master
...
Fix typo in PositionalEncodingFourier
3 years ago
Ross Wightman
66f4af7090
Merge remote-tracking branch 'origin/master' into script_cleanup
3 years ago
Ross Wightman
d3961536c9
comment some debug logs for WDS dataset
3 years ago
Ross Wightman
e9dccc918c
Rename dataset/parsers -> dataset/readers, create_parser to create_reader, etc
3 years ago
Ross Wightman
8c28363dc9
Version 0.7.dev0 for master
3 years ago
nateraw
30bafd7347
🔖 add dev suffix to version tag
3 years ago
Ross Wightman
f67a7ee8bd
Set num_workers in Iterable WDS/TFDS datasets early so sample estimate is correct
3 years ago
Ross Wightman
cea8df3d0c
Version 0.6.12
3 years ago
Ross Wightman
9914f744dc
Add more maxxvit weights includ ConvNeXt conv block based experiments.
3 years ago
Ross Wightman
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
3 years ago
Ross Wightman
4f18d6dc5f
Fix logs in WDS parser
3 years ago
Mohamed Rashad
8fda68aff6
Fix repo id bug
...
This to fix this issue #1482
3 years ago
Ross Wightman
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.
3 years ago
Alex Fafard
7327792f39
update to support pickle based dictionaries
3 years ago
Ross Wightman
1199c5a1a4
clip_laion2b models need 1e-5 eps for LayerNorm
3 years ago
Ross Wightman
87939e6fab
Refactor device handling in scripts, distributed init to be less 'cuda' centric. More device args passed through where needed.
3 years ago
Ross Wightman
c88947ad3d
Add initial Hugging Face Datasets parser impl.
3 years ago
Ross Wightman
e858912e0c
Add brute-force checkpoint remapping option
3 years ago
Ross Wightman
b293dfa595
Add CL SE module
3 years ago
Ross Wightman
2a296412be
Add Adan optimizer
3 years ago
Ross Wightman
5dc4343308
version 0.6.11
3 years ago
Ross Wightman
a383ef99f5
Make huggingface_hub necessary if it's the only source for a pretrained weight
3 years ago
Ross Wightman
33e30f8c8b
Remove layer-decay print
3 years ago
Ross Wightman
e069249a2d
Add hf hub entries for laion2b clip models, add huggingface_hub dependency, update some setup/reqs, torch >= 1.7
3 years ago
Ross Wightman
9d65557be3
Fix errant import
3 years ago
Ross Wightman
9709dbaaa9
Adding support for fine-tune CLIP LAION-2B image tower weights for B/32, L/14, H/14 and g/14. Still WIP
3 years ago
Ross Wightman
a520da9b49
Update tresnet features_info for v2
3 years ago
Ross Wightman
c8ab747bf4
BEiT-V2 checkpoints didn't remove 'module' from weights, adapt checkpoint filter
3 years ago
Ross Wightman
73049dc2aa
Fix type in dla weight update
3 years ago
Ross Wightman
3599c7e6a4
version 0.6.10
3 years ago
Ross Wightman
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.
3 years ago
Ross Wightman
fa8c84eede
Update maxvit_tiny_256 weight to better iter, add coatnet / maxvit / maxxvit model defs for future runs
3 years ago
Ross Wightman
c1b3cea19d
Add maxvit_rmlp_tiny_rw_256 model def and weights w/ 84.2 top-1 @ 256, 84.8 @ 320
3 years ago
Ross Wightman
914544fc81
Add beitv2 224x224 checkpoints from https://github.com/microsoft/unilm/tree/master/beit2
3 years ago
Ross Wightman
dc90816f26
Add `maxvit_tiny_rw_224` weights 83.5 @ 224 and `maxvit_rmlp_pico_rw_256` relpos weights, 80.5 @ 256, 81.3 @ 320
3 years ago
Ross Wightman
f489f02ad1
Make gcvit window size ratio based to improve resolution changing support #1449 . Change default init to original.
3 years ago
Ross Wightman
7f1b223c02
Add maxvit_rmlp_nano_rw_256 model def & weights, make window/grid size dynamic wrt img_size by default
3 years ago
Ross Wightman
e6a4361306
pretrained_cfg entry for mvitv2_small_cls
3 years ago
Ross Wightman
f66e5f0e35
Fix class token support in MViT-V2, add small_class variant to ensure it's tested. Fix #1443
3 years ago
Ross Wightman
f1d2160d85
Update a few maxxvit comments, rename PartitionAttention -> PartitionAttenionCl for consistency with other blocks
3 years ago
Ross Wightman
eca6f0a25c
Fix syntax error (extra dataclass comma) in maxxvit.py
3 years ago
Ross Wightman
ff6a919cf5
Add --fast-norm arg to benchmark.py, train.py, validate.py
3 years ago