e2fc43bc63
Version 0.8.2dev0
2 years ago
9a51e4ea2e
Add FlexiViT models and weights, refactoring, push more weights
...
* push all vision_transformer*.py weights to HF hub
* finalize more pretrained tags for pushed weights
* refactor pos_embed files and module locations, move some pos embed modules to layers
* tweak hf hub helpers to aid bulk uploading and updating
2 years ago
656e1776de
Convert mobilenetv3 to multi-weight, tweak PretrainedCfg metadata
2 years ago
6a01101905
Update efficientnet.py and convnext.py to multi-weight, add ImageNet-12k pretrained EfficientNet-B5 and ConvNeXt-Nano.
2 years ago
e7da205345
Fix aa min_max level clamp
2 years ago
e3b2f5be0a
Add 3-Augment support to auto_augment.py, clean up weighted choice handling, and allow adjust per op prob via arg string
2 years ago
e98c93264c
Merge pull request #1581 from rwightman/refactor-imports
...
Major module / path restructure
2 years ago
d5e7d6b27e
Merge remote-tracking branch 'origin/main' into refactor-imports
2 years ago
cda39b35bd
Add a deprecation phase to module re-org
2 years ago
0fe90449e5
Update README.md
2 years ago
1733177c75
Update README.md
2 years ago
9e47d8ad59
Update README.md
2 years ago
f266f841a0
Merge pull request #1586 from lorenzbaraldi/eval_loss
...
Put validation loss under amp_autocast
2 years ago
3d6bc42aa1
Put validation loss under amp_autocast
...
Secured the loss evaluation under the amp, avoiding function to operate on float16
2 years ago
7c4ed4d5a4
Add EVA-large models
2 years ago
6a92587e0d
Update README.md
2 years ago
98047ef5e3
Add EVA FT results, hopefully fix BEiT test failures
2 years ago
3cc4d7a894
Fix missing register for 224 eva model
2 years ago
eba07b0de7
Add eva models to beit.py
2 years ago
927f031293
Major module / path restructure, timm.models.layers -> timm.layers, add _ prefix to all non model modules in timm.models
2 years ago
da6644b6ba
Update README.md
2 years ago
61531f091e
Update multi-weight release README
2 years ago
3785c234d7
Remove clip vit models that won't be ft and comment two that aren't uploaded yet
2 years ago
f82239b30e
multi-weight branch version -> 0.8.0dev
2 years ago
755570e2d6
Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses
2 years ago
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.
2 years ago
dbe7531aa3
Update scripts to support torch.compile(). Make --results_file arg more consistent across benchmark/validate/inference. Fix #1570
2 years ago
05637a4bb0
More inference script changes, arg naming, multiple output fmts at once
2 years ago
eceeb9409a
Significant ugprade to inference.py, support for different formats, formatting, etc.
2 years ago
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
2 years ago
3db4e346e0
Switch TFDS dataset to use INTEGER_ACCURATE jpeg decode by default
2 years ago
9da7e3a799
Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate
2 years ago
8fca002c06
Add ImageNet22k and 12k subset sysnet/index maps
2 years ago
b2b6285af7
Add two more FT clip weights
2 years ago
5895056dc4
Add openai b32 ft
2 years ago
9dea5143d5
Adding more clip ft variants
2 years ago
444dcba4ad
CLIP B16 12k weights added
2 years ago
dff4717cbf
Add clip b16 384x384 finetunes
2 years ago
883fa2eeaa
Add fine-tuned B/16 224x224 in1k clip models
2 years ago
9a3d2ac2d5
Add latest CLIP ViT fine-tune pretrained configs / model entrypt updates
2 years ago
42bbbddee9
Add missing model config
2 years ago
def68befa7
Updating vit model defs for mult-weight support trial (vit first). Prepping for CLIP (laion2b and openai) fine-tuned weights.
2 years ago
0dadb4a6e9
Initial multi-weight support, handled so old pretraing config handling co-exists with new tags.
2 years ago
e8ddc6865c
Update torch to 1.13 and python to 3.10 in test workflow ( #1562 )
...
* Update torch and python version in test workflow
* Python back to 3.9 for test workflow, see if that's the cause of macos failure..
* Try windows runner
* Try Python 3.10 + macOS-12 in quest for working second target
* Remove macOS from tests, not working anymore
2 years ago
98c5e78226
Merge pull request #1564 from HongxinXiang/main
...
Fix compatible BUG: QMNIST and ImageNet datasets do not exist in torc…
2 years ago
653bdc7105
Fix comment: https://github.com/rwightman/pytorch-image-models/pull/1564#issuecomment-1326743424
2 years ago
bdc9fad638
Fix compatible BUG: QMNIST and ImageNet datasets do not exist in torchvision 0.10.1.
2 years ago
25ffac6880
Merge pull request #1547 from Wauplin/1546-fix-hf-hub-integration
...
Create repo before cloning with Repository.clone_from
2 years ago
9b114754db
refactor push_to_hub helper
2 years ago
ae0a0db7de
Create repo before cloning with Repository.clone_from
2 years ago
Ross Wightman