7c846d9970
Better vmap compat across recent torch versions
2022-12-24 14:37:04 -08:00
130458988a
Update README.md
2022-12-23 15:20:43 -08:00
d96538f1d2
Update README
2022-12-23 15:19:54 -08:00
4e24f75289
Merge pull request #1593 from rwightman/multi-weight_effnet_convnext
...
Update efficientnet.py and convnext.py to multi-weight, add new 12k pretrained weights
2022-12-23 10:09:08 -08:00
8ece53e194
Switch BEiT to HF hub weights
2022-12-22 21:43:04 -08:00
d1bfa9a000
Support HF datasets and TFSD w/ a sub-path by fixing split, fix #1598 ... add class mapping support to HF datasets in case class label isn't in info.
2022-12-22 21:34:13 -08:00
35fb00c779
Add flexivit to non-std tests list
2022-12-22 21:32:31 -08:00
e2fc43bc63
Version 0.8.2dev0
2022-12-22 17:34:09 -08:00
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
2022-12-22 17:23:09 -08:00
656e1776de
Convert mobilenetv3 to multi-weight, tweak PretrainedCfg metadata
2022-12-16 09:29:13 -08:00
18ec173f95
Merge pull request #1592 from twmht/add_adan_to_init
...
Add Adan to __init__.py
2022-12-14 20:43:12 -08:00
6a01101905
Update efficientnet.py and convnext.py to multi-weight, add ImageNet-12k pretrained EfficientNet-B5 and ConvNeXt-Nano.
2022-12-14 20:33:23 -08:00
74d6afb4cd
Add Adan to __init__.py
2022-12-15 11:37:29 +08:00
e7da205345
Fix aa min_max level clamp
2022-12-10 16:43:28 -08:00
e3b2f5be0a
Add 3-Augment support to auto_augment.py, clean up weighted choice handling, and allow adjust per op prob via arg string
2022-12-10 16:25:50 -08:00
e98c93264c
Merge pull request #1581 from rwightman/refactor-imports
...
Major module / path restructure
2022-12-10 14:35:48 -08:00
d5e7d6b27e
Merge remote-tracking branch 'origin/main' into refactor-imports
2022-12-09 14:49:44 -08:00
cda39b35bd
Add a deprecation phase to module re-org
2022-12-09 14:39:45 -08:00
0fe90449e5
Update README.md
2022-12-09 11:21:46 -08:00
1733177c75
Update README.md
2022-12-09 11:14:35 -08:00
9e47d8ad59
Update README.md
2022-12-09 11:13:37 -08:00
f266f841a0
Merge pull request #1586 from lorenzbaraldi/eval_loss
...
Put validation loss under amp_autocast
2022-12-09 04:29:37 -08:00
3d6bc42aa1
Put validation loss under amp_autocast
...
Secured the loss evaluation under the amp, avoiding function to operate on float16
2022-12-09 12:03:23 +01:00
7c4ed4d5a4
Add EVA-large models
2022-12-08 16:21:30 -08:00
6a92587e0d
Update README.md
2022-12-07 09:34:21 -08:00
98047ef5e3
Add EVA FT results, hopefully fix BEiT test failures
2022-12-07 08:54:06 -08:00
3cc4d7a894
Fix missing register for 224 eva model
2022-12-07 08:54:06 -08:00
eba07b0de7
Add eva models to beit.py
2022-12-07 08:54:06 -08:00
927f031293
Major module / path restructure, timm.models.layers -> timm.layers, add _ prefix to all non model modules in timm.models
2022-12-06 15:00:06 -08:00
da6644b6ba
Update README.md
2022-12-05 10:21:34 -08:00
61531f091e
Update multi-weight release README
2022-12-05 10:21:34 -08:00
3785c234d7
Remove clip vit models that won't be ft and comment two that aren't uploaded yet
2022-12-05 10:21:34 -08:00
f82239b30e
multi-weight branch version -> 0.8.0dev
2022-12-05 10:21:34 -08:00
755570e2d6
Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses
2022-12-05 10:21:34 -08:00
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.
2022-12-05 10:21:34 -08:00
dbe7531aa3
Update scripts to support torch.compile(). Make --results_file arg more consistent across benchmark/validate/inference. Fix #1570
2022-12-05 10:21:34 -08:00
05637a4bb0
More inference script changes, arg naming, multiple output fmts at once
2022-12-05 10:21:34 -08:00
eceeb9409a
Significant ugprade to inference.py, support for different formats, formatting, etc.
2022-12-05 10:21:34 -08:00
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
2022-12-05 10:21:34 -08:00
3db4e346e0
Switch TFDS dataset to use INTEGER_ACCURATE jpeg decode by default
2022-12-05 10:21:34 -08:00
9da7e3a799
Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate
2022-12-05 10:21:34 -08:00
8fca002c06
Add ImageNet22k and 12k subset sysnet/index maps
2022-12-05 10:21:34 -08:00
b2b6285af7
Add two more FT clip weights
2022-12-05 10:21:34 -08:00
5895056dc4
Add openai b32 ft
2022-12-05 10:21:34 -08:00
9dea5143d5
Adding more clip ft variants
2022-12-05 10:21:34 -08:00
444dcba4ad
CLIP B16 12k weights added
2022-12-05 10:21:34 -08:00
dff4717cbf
Add clip b16 384x384 finetunes
2022-12-05 10:21:34 -08:00
883fa2eeaa
Add fine-tuned B/16 224x224 in1k clip models
2022-12-05 10:21:34 -08:00
9a3d2ac2d5
Add latest CLIP ViT fine-tune pretrained configs / model entrypt updates
2022-12-05 10:21:34 -08:00
42bbbddee9
Add missing model config
2022-12-05 10:21:34 -08:00
Ross Wightman
Ross Wightman
alec.tu
Lorenzo Baraldi