4bc103f504
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
2021-02-23 13:15:52 -08:00
da4839530c
Fix test model filter to include dm_ variants that break GitHub CI limits
2021-02-18 13:43:04 -08:00
8563609b28
Update notes in ScaledStdConv impl
2021-02-18 12:44:08 -08:00
678ba4e0a2
Add NFNet-F model weights ported from DeepMind Haiku impl and new set of models w/ compatible config.
2021-02-18 12:28:46 -08:00
4ea5931964
Merge pull request #437 from rwightman/agc
...
Adaptive Gradient Clipping (AGC) Impl
2021-02-16 10:27:58 -08:00
361fd0fc40
Update README.md
2021-02-16 10:27:41 -08:00
9de2ec5e44
Update README for AGC and bump version to 0.4.4
2021-02-16 09:13:03 -08:00
01653db104
Missed clip-mode arg for repo train script
2021-02-15 23:27:16 -08:00
4f49b94311
Initial AGC impl. Still testing.
2021-02-15 23:22:44 -08:00
5f9aff395c
Fix stem width in NFNet-F models, add some more comments, add some 'light' NFNet models for testing.
2021-02-13 16:58:51 -08:00
4df513c68f
Merge pull request #427 from rwightman/nfnet
...
Add NFNet-F models and tweak existing NF models.
2021-02-12 22:08:03 -08:00
d86dbe45c2
Update README.md and few more comments
2021-02-12 22:07:18 -08:00
0d253e2c5e
Fix issue with nfnet tests, bit more cleanup.
2021-02-12 21:05:41 -08:00
cb06c7a910
Add NFNet-F models and tweak existing NF models.
2021-02-12 18:28:56 -08:00
607f9149b1
Update README.md
2021-02-11 22:06:06 -08:00
e4de077021
Add first 'Normalizer Free' models. nf_regnet_b1 79.3 @ 288x288 test, and nf_resnet50 80.3 @ 256x256 test (80.68 @ 288x288).
2021-02-11 13:20:11 -08:00
d8e69206be
Merge pull request #419 from rwightman/byob_vgg_models
...
More models, GPU-Efficient Nets, RepVGG, classic VGG, and flexible Byob backbone.
2021-02-10 15:44:09 -08:00
ca9b078ac7
Update README.md and docs. Version bumped to 0.4.3
2021-02-10 14:46:07 -08:00
6853b07bbd
Improve RegVGG block identity/vs non for clariy and fix attn usage. Add comments.
2021-02-10 14:40:29 -08:00
0356e773f5
Default to native PyTorch AMP instead of APEX amp. Too many APEX issues cropping up lately.
2021-02-10 14:31:18 -08:00
b9bd960a03
Merge pull request #421 from aboutmedicine/master
...
Update collections.abc import to avoid pytorch 1.8 issue. Fix #420
2021-02-10 08:11:49 -08:00
94ca140b67
update collections.abc import
2021-02-10 23:54:35 +11:00
db6128db0f
Merge pull request #418 from kecsap/master
...
Change the Python interpreter to Python 3.x in the scripts
2021-02-09 20:55:55 -08:00
b4e216e377
Fix a few small things.
2021-02-09 17:33:43 -08:00
dc85e5a237
Add ByobNet w/ GPU-EfficientNets and RepVGG. Also add classic vgg models.
2021-02-09 16:22:52 -08:00
1bcc69e0ad
Use in_channels for depthwise groups, allows using `out_channels=N * in_channels` (does not impact existing models). Fix #354 .
2021-02-09 16:22:52 -08:00
9811e229f7
Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.
2021-02-09 16:22:52 -08:00
5114c214fc
Change the Python interpreter to Python 3.x in the scripts
2021-02-09 21:20:28 +02:00
aaa715b1e9
Update README.md
2021-02-08 12:04:48 -08:00
a7f95818e4
Merge pull request #413 from rwightman/eca-weights
...
Add new weights for ecaresnet26t/50t/269d models.
2021-02-08 12:03:19 -08:00
a39c3ee216
Merge branch 'master' into eca-weights
2021-02-08 11:52:31 -08:00
e9d6fe293c
Update README for new weights. Version 0.4.2
2021-02-08 11:51:16 -08:00
666de85cf1
Move stride in EdgeResidual block to 3x3 expansion conv. Fix #414
2021-02-07 22:10:18 -08:00
3b57490a63
Fix some half removed resnet model defs, pooling for ecaresnet269d
2021-02-07 22:09:25 -08:00
2a8c4dc63b
Add validation script update for using test_input_size in model default_cfgs
2021-02-07 21:35:50 -08:00
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.
2021-02-06 16:30:02 -08:00
3a7aa95f7e
Update README.md
2021-02-05 07:39:21 -08:00
b9843f954b
Merge pull request #282 from tigert1998/patch-1
...
Add symbolic for SwishJitAutoFn to support onnx
2021-02-04 12:18:40 -08:00
ea36a78cff
Merge pull request #401 from hwangdeyu/deyu/add_HardSwishJitAutoFn_operator
...
add HardSwishJitAutoFn operator export to onnx
2021-02-04 12:18:19 -08:00
7a4be5c035
add operator HardSwishJitAutoFn export to onnx
2021-02-03 09:06:53 +08:00
4203efa36d
Fix #387 so that checkpoint saver works with max history of 1. Add checkpoint-hist arg to train.py.
2021-01-31 20:14:51 -08:00
99b82ae5ab
Merge pull request #389 from rwightman/norm_free_models
...
Normalizer-Free RegNet and ResNet impl
2021-01-31 12:47:47 -08:00
f0e65e37b7
Fix NF-ResNet101 model defs
2021-01-30 23:26:19 -08:00
2c988c3b6e
Update README.md for NF-nets, bump version to 0.4.1 for merge
2021-01-30 23:19:45 -08:00
2de54d174a
Fix pool size defs for NFNet models, add a comment.
2021-01-30 18:02:33 -08:00
90980de4a9
Fix up a few details in NFResNet models, managed stable training. Add support for gamma gain to be applied in activation or ScaleStdConv. Some tweaks to ScaledStdConv.
2021-01-30 16:32:07 -08:00
5a8e1e643e
Initial Normalizer-Free Reg/ResNet impl. A bit of related layer refactoring.
2021-01-27 22:06:57 -08:00
9a38416fbd
Merge pull request #323 from rwightman/imagenet21k_datasets_more
...
BiT (Big Transfer) ResNetV2 models, Official ViT Hybrid R50 weights, VIT IN21K weights updated w/ repr layer, ImageNet21k and dataset / parser refactor
2021-01-25 13:31:15 -08:00
745bc5f723
Mention 21k ViT weights in README.md
2021-01-25 12:26:55 -08:00
6306aa79e9
Merge branch 'master' into imagenet21k_datasets_more
2021-01-25 12:26:05 -08:00
Ross Wightman
Ross Wightman
Reuben
Csaba Kertesz
hwangdeyu