Ross Wightman
ec6921fcb0
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
Ross Wightman
d1e0a4607d
Switch TFDS dataset to use INTEGER_ACCURATE jpeg decode by default
2 years ago
Ross Wightman
0ed0cc7eba
Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate
2 years ago
Ross Wightman
70442fd5a8
Add ImageNet22k and 12k subset sysnet/index maps
2 years ago
Ross Wightman
f6e0a848d0
Add two more FT clip weights
2 years ago
Ross Wightman
884a0f1a12
Add openai b32 ft
2 years ago
Ross Wightman
2c80da3b9a
Adding more clip ft variants
2 years ago
Ross Wightman
da2de0de95
CLIP B16 12k weights added
2 years ago
Ross Wightman
b2897f5ea6
Add clip b16 384x384 finetunes
2 years ago
Ross Wightman
092287436e
Add fine-tuned B/16 224x224 in1k clip models
2 years ago
Ross Wightman
d3415e3134
Add latest CLIP ViT fine-tune pretrained configs / model entrypt updates
2 years ago
Ross Wightman
2eb825c014
Add missing model config
2 years ago
Ross Wightman
0761ce7a1b
Updating vit model defs for mult-weight support trial (vit first). Prepping for CLIP (laion2b and openai) fine-tuned weights.
2 years ago
Ross Wightman
041709b470
Fix xdist dependency change
2 years ago
Ross Wightman
ebb99a1f8d
Initial multi-weight support, handled so old pretraing config handling co-exists with new tags.
2 years ago
Ross Wightman
475ecdfa3d
cast env var args for dataset readers to int
2 years ago
Ross Wightman
44cea489fb
Merge pull request #1502 from infomon/main
...
Fix typo of "sched-on-updates" argument
2 years ago
Simon Schrodi
aceb79e002
Fix typo
2 years ago
Ross Wightman
8a1ba67a50
Merge pull request #1500 from nguyenhoan1988/main
...
Remove inplace operators when calculating the loss
2 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
```
2 years ago
Ross Wightman
91fc4c7ed1
Update tests.yml
2 years ago
Ross Wightman
26c400bf1e
Merge pull request #1498 from nateraw/docs-deploy-from-main
...
Deploy docs from main not master
2 years ago
nateraw
cf549c28b1
🎨 deploy docs from main not master
2 years ago
Ross Wightman
3e57377f7a
Update README.md
2 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
2 years ago
Ross Wightman
0e6023f032
Merge pull request #1381 from ChristophReich1996/master
...
Fix typo in PositionalEncodingFourier
2 years ago
Ross Wightman
66f4af7090
Merge remote-tracking branch 'origin/master' into script_cleanup
2 years ago
Ross Wightman
eb333d6641
Update validate.py to use updated amp args for impl/dtype
2 years ago
Ross Wightman
d3961536c9
comment some debug logs for WDS dataset
2 years ago
Ross Wightman
e9dccc918c
Rename dataset/parsers -> dataset/readers, create_parser to create_reader, etc
2 years ago
Ross Wightman
8c28363dc9
Version 0.7.dev0 for master
2 years ago
Ross Wightman
1ae6ba62cd
Merge pull request #1494 from nateraw/add-dev-suffix-to-tag
...
Add dev suffix to version tag
2 years ago
nateraw
30bafd7347
🔖 add dev suffix to version tag
2 years ago
Ross Wightman
94aed25224
Merge pull request #1493 from nateraw/fix-hf-docs-build
...
💚 Rename _conf.yml to _config.py
2 years ago
nateraw
edceac4aaf
💚 fix ci build
2 years ago
Ross Wightman
2f041b84da
Merge pull request #1473 from nateraw/hfdocs
...
Add Hugging Face Docs
2 years ago
Ross Wightman
f67a7ee8bd
Set num_workers in Iterable WDS/TFDS datasets early so sample estimate is correct
2 years ago
Ross Wightman
bb49d02aae
Update README.md
2 years ago
Ross Wightman
b944546200
Update README.md
2 years ago
Ross Wightman
cea8df3d0c
Version 0.6.12
2 years ago
Ross Wightman
9914f744dc
Add more maxxvit weights includ ConvNeXt conv block based experiments.
2 years ago
Ross Wightman
285771972e
Change --amp flags, no more --apex-amp and --native-amp, add --amp-impl to select apex, and --amp-dtype to allow bfloat16 AMP dtype
2 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
2 years ago
Ross Wightman
4f18d6dc5f
Fix logs in WDS parser
2 years ago
nateraw
af0c644c5d
👷 remove --not_python_module flag
2 years ago
nateraw
df29d46872
♻️ old doc links -> new doc links
2 years ago
nateraw
8ef9c48cc5
👷 use main branch of doc-builder thats fixed now
2 years ago
nateraw
9343f6e431
👷 update ci
2 years ago
nateraw
5f9eef712c
👷 bump ci
2 years ago
nateraw
09a77700f6
👷 bump back. it was actions outage not me
2 years ago