Ross Wightman
|
4de57ccf01
|
Add weight init scheme that's closer to JAX impl
|
3 years ago |
|
Ross Wightman
|
4445eaa470
|
Add img_size to benchmark output
|
3 years ago |
|
Ross Wightman
|
17cdee7354
|
Fix C&P patch_size error, and order of op patch_size arg resolution bug. Remove a test vit model.
|
3 years ago |
|
Ross Wightman
|
0706d05d52
|
Benchmark models listed in txt file. Add more hybrid vit variants for testing
|
3 years ago |
|
Ross Wightman
|
2db2d87ff7
|
Add epoch-repeats arg to multiply the number of dataset passes per epoch. Currently for iterable datasets (read TFDS wrapper) only.
|
3 years ago |
|
Ross Wightman
|
de97be9146
|
Spell out diff between my small and deit small vit models.
|
3 years ago |
|
Ross Wightman
|
f0ffdf89b3
|
Add numerous experimental ViT Hybrid models w/ ResNetV2 base. Update the ViT naming for hybrids. Fix #426 for pretrained vit resizing.
|
3 years ago |
|
Ross Wightman
|
0e16d4e9fb
|
Add benchmark.py script, and update optimizer factory to be more friendly to use outside of argparse interface.
|
3 years ago |
|
Ross Wightman
|
4bc103f504
|
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
|
3 years ago |
|
Ross Wightman
|
da4839530c
|
Fix test model filter to include dm_ variants that break GitHub CI limits
|
3 years ago |
|
Ross Wightman
|
8563609b28
|
Update notes in ScaledStdConv impl
|
3 years ago |
|
Ross Wightman
|
678ba4e0a2
|
Add NFNet-F model weights ported from DeepMind Haiku impl and new set of models w/ compatible config.
|
3 years ago |
Ross Wightman
|
4ea5931964
|
Merge pull request #437 from rwightman/agc
Adaptive Gradient Clipping (AGC) Impl
|
3 years ago |
|
Ross Wightman
|
361fd0fc40
|
Update README.md
|
3 years ago |
|
Ross Wightman
|
9de2ec5e44
|
Update README for AGC and bump version to 0.4.4
|
3 years ago |
|
Ross Wightman
|
01653db104
|
Missed clip-mode arg for repo train script
|
3 years ago |
|
Ross Wightman
|
4f49b94311
|
Initial AGC impl. Still testing.
|
3 years ago |
|
Ross Wightman
|
5f9aff395c
|
Fix stem width in NFNet-F models, add some more comments, add some 'light' NFNet models for testing.
|
3 years ago |
|
Ross Wightman
|
4df513c68f
|
Merge pull request #427 from rwightman/nfnet
Add NFNet-F models and tweak existing NF models.
|
3 years ago |
|
Ross Wightman
|
d86dbe45c2
|
Update README.md and few more comments
|
3 years ago |
|
Ross Wightman
|
0d253e2c5e
|
Fix issue with nfnet tests, bit more cleanup.
|
3 years ago |
|
Ross Wightman
|
cb06c7a910
|
Add NFNet-F models and tweak existing NF models.
|
3 years ago |
|
Ross Wightman
|
607f9149b1
|
Update README.md
|
3 years ago |
|
Ross Wightman
|
e4de077021
|
Add first 'Normalizer Free' models. nf_regnet_b1 79.3 @ 288x288 test, and nf_resnet50 80.3 @ 256x256 test (80.68 @ 288x288).
|
3 years ago |
|
Ross Wightman
|
d8e69206be
|
Merge pull request #419 from rwightman/byob_vgg_models
More models, GPU-Efficient Nets, RepVGG, classic VGG, and flexible Byob backbone.
|
3 years ago |
|
Ross Wightman
|
ca9b078ac7
|
Update README.md and docs. Version bumped to 0.4.3
|
3 years ago |
|
Ross Wightman
|
6853b07bbd
|
Improve RegVGG block identity/vs non for clariy and fix attn usage. Add comments.
|
3 years ago |
|
Ross Wightman
|
0356e773f5
|
Default to native PyTorch AMP instead of APEX amp. Too many APEX issues cropping up lately.
|
3 years ago |
|
Ross Wightman
|
b9bd960a03
|
Merge pull request #421 from aboutmedicine/master
Update collections.abc import to avoid pytorch 1.8 issue. Fix #420
|
3 years ago |
Reuben
|
94ca140b67
|
update collections.abc import
|
3 years ago |
|
Ross Wightman
|
db6128db0f
|
Merge pull request #418 from kecsap/master
Change the Python interpreter to Python 3.x in the scripts
|
3 years ago |
|
Ross Wightman
|
b4e216e377
|
Fix a few small things.
|
3 years ago |
|
Ross Wightman
|
dc85e5a237
|
Add ByobNet w/ GPU-EfficientNets and RepVGG. Also add classic vgg models.
|
3 years ago |
|
Ross Wightman
|
1bcc69e0ad
|
Use in_channels for depthwise groups, allows using `out_channels=N * in_channels` (does not impact existing models). Fix #354.
|
3 years ago |
|
Ross Wightman
|
9811e229f7
|
Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.
|
3 years ago |
Csaba Kertesz
|
5114c214fc
|
Change the Python interpreter to Python 3.x in the scripts
|
3 years ago |
|
Ross Wightman
|
aaa715b1e9
|
Update README.md
|
3 years ago |
|
Ross Wightman
|
a7f95818e4
|
Merge pull request #413 from rwightman/eca-weights
Add new weights for ecaresnet26t/50t/269d models.
|
3 years ago |
|
Ross Wightman
|
a39c3ee216
|
Merge branch 'master' into eca-weights
|
3 years ago |
|
Ross Wightman
|
e9d6fe293c
|
Update README for new weights. Version 0.4.2
|
3 years ago |
|
Ross Wightman
|
666de85cf1
|
Move stride in EdgeResidual block to 3x3 expansion conv. Fix #414
|
3 years ago |
|
Ross Wightman
|
3b57490a63
|
Fix some half removed resnet model defs, pooling for ecaresnet269d
|
3 years ago |
|
Ross Wightman
|
2a8c4dc63b
|
Add validation script update for using test_input_size in model default_cfgs
|
3 years ago |
|
Ross Wightman
|
68a4144882
|
Add new weights for ecaresnet26t/50t/269d models. Remove distinction between 't' and 'tn' (tiered models), tn is now t. Add test time img size spec to default cfg.
|
3 years ago |
|
Ross Wightman
|
3a7aa95f7e
|
Update README.md
|
3 years ago |
|
Ross Wightman
|
b9843f954b
|
Merge pull request #282 from tigert1998/patch-1
Add symbolic for SwishJitAutoFn to support onnx
|
3 years ago |
|
Ross Wightman
|
ea36a78cff
|
Merge pull request #401 from hwangdeyu/deyu/add_HardSwishJitAutoFn_operator
add HardSwishJitAutoFn operator export to onnx
|
3 years ago |
hwangdeyu
|
7a4be5c035
|
add operator HardSwishJitAutoFn export to onnx
|
3 years ago |
|
Ross Wightman
|
4203efa36d
|
Fix #387 so that checkpoint saver works with max history of 1. Add checkpoint-hist arg to train.py.
|
3 years ago |
|
Ross Wightman
|
99b82ae5ab
|
Merge pull request #389 from rwightman/norm_free_models
Normalizer-Free RegNet and ResNet impl
|
3 years ago |
