Commit Graph

308 Commits (3eac7dc5a3a04cb616db1b54c3e5dc67af798083)

Author SHA1 Message Date
Ross Wightman 45c048ba13 A few minor fixes and bit more cleanup on the huggingface hub integration. 2021-03-17 13:18:52 -07:00
Ross Wightman ead80d33c5 Fix typo, naming consistency 2021-03-16 23:02:51 -07:00
Ross Wightman d584e7f617 Support for huggingface hub via create_model and default_cfgs.
* improve consistency of model creation helper fns
* add comments to some of the model helpers
* support passing external default_cfgs so they can be sourced from hub
2021-03-16 22:48:26 -07:00
Ross Wightman 1f799afcb3 Remove capital letters in model names 2021-03-15 10:20:34 -07:00
AFLALO, Jonathan Isaac 82c1fe958a added hardcorenas model
refactoring to support feature extraction
2021-03-15 08:06:34 +02:00
Ross Wightman f57db99101 Update README, fix iabn pip version print. 2021-03-07 16:17:06 -08:00
Ross Wightman 7ef7788ee9 Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk() 2021-03-06 16:56:34 -08:00
Ross Wightman 317ea3e599 Tweak NFNet, ResNetV2, RexNet feature extraction, use pre-act features for simplicty. Update tests for pytorch 1.8. 0.4.5 version bump. 2021-03-06 12:48:06 -08:00
Ross Wightman 8563609b28 Update notes in ScaledStdConv impl 2021-02-18 12:44:08 -08:00
Ross Wightman 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
Ross Wightman 4f49b94311 Initial AGC impl. Still testing. 2021-02-15 23:22:44 -08:00
Ross Wightman 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
Ross Wightman d86dbe45c2 Update README.md and few more comments 2021-02-12 22:07:18 -08:00
Ross Wightman 0d253e2c5e Fix issue with nfnet tests, bit more cleanup. 2021-02-12 21:05:41 -08:00
Ross Wightman cb06c7a910 Add NFNet-F models and tweak existing NF models. 2021-02-12 18:28:56 -08:00
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). 2021-02-11 13:20:11 -08:00
Ross Wightman 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
Ross Wightman 6853b07bbd Improve RegVGG block identity/vs non for clariy and fix attn usage. Add comments. 2021-02-10 14:40:29 -08:00
Ross Wightman 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
Reuben 94ca140b67 update collections.abc import 2021-02-10 23:54:35 +11:00
Ross Wightman b4e216e377 Fix a few small things. 2021-02-09 17:33:43 -08:00
Ross Wightman dc85e5a237 Add ByobNet w/ GPU-EfficientNets and RepVGG. Also add classic vgg models. 2021-02-09 16:22:52 -08:00
Ross Wightman 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
Ross Wightman 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
Ross Wightman a39c3ee216
Merge branch 'master' into eca-weights 2021-02-08 11:52:31 -08:00
Ross Wightman 666de85cf1 Move stride in EdgeResidual block to 3x3 expansion conv. Fix #414 2021-02-07 22:10:18 -08:00
Ross Wightman 3b57490a63 Fix some half removed resnet model defs, pooling for ecaresnet269d 2021-02-07 22:09:25 -08:00
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. 2021-02-06 16:30:02 -08:00
Ross Wightman b9843f954b
Merge pull request #282 from tigert1998/patch-1
Add symbolic for SwishJitAutoFn to support onnx
2021-02-04 12:18:40 -08:00
hwangdeyu 7a4be5c035 add operator HardSwishJitAutoFn export to onnx 2021-02-03 09:06:53 +08:00
Ross Wightman f0e65e37b7 Fix NF-ResNet101 model defs 2021-01-30 23:26:19 -08:00
Ross Wightman 2de54d174a Fix pool size defs for NFNet models, add a comment. 2021-01-30 18:02:33 -08:00
Ross Wightman 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
Ross Wightman 5a8e1e643e Initial Normalizer-Free Reg/ResNet impl. A bit of related layer refactoring. 2021-01-27 22:06:57 -08:00
Ross Wightman 38d8f67570 Fix potential issue with change to num_classes arg in train/validate.py defaulting to None (rely on model def / default_cfg) 2021-01-25 11:53:34 -08:00
Ross Wightman bb50ac4708 Add DeiT distilled weights and distilled model def. Remove some redudant ViT model args. 2021-01-25 11:05:23 -08:00
Ross Wightman c16e965037 Add some ViT comments and fix a few minor issues. 2021-01-24 23:18:35 -08:00
Ross Wightman 22748f1a2d Convert samples/targets in ParserImageInTar to numpy arrays, slightly less mem usage for massive datasets. Add a few more se/eca model defs to resnet.py 2021-01-22 16:54:33 -08:00
Ross Wightman 55f7dfa9ea Refactor vision_transformer entrpy fns, add pos embedding resize support for fine tuning, add some deit models for testing 2021-01-18 16:11:02 -08:00
Ross Wightman d55bcc0fee Finishing adding stochastic depth support to BiT ResNetV2 models 2021-01-16 16:32:03 -08:00
Ross Wightman 855d6cc217 More dataset work including factories and a tensorflow datasets (TFDS) wrapper
* Add parser/dataset factory methods for more flexible dataset & parser creation
* Add dataset parser that wraps TFDS image classification datasets
* Tweak num_classes handling bug for 21k models
* Add initial deit models so they can be benchmarked in next csv results runs
2021-01-15 17:26:20 -08:00
Ross Wightman 20516abc18 Fix some broken tests for ResNetV2 BiT models 2021-01-04 23:21:39 -08:00
Ross Wightman 59ec7e6a53 Merge branch 'master' into imagenet21k_datasets_more 2021-01-04 12:11:05 -08:00
Ross Wightman 4e2533db77 Add 320x320 model default cfgs for 101D and 152D ResNets. Add SEResNet-152D weights and 320x320 cfg. 2021-01-03 12:10:25 -08:00
Ross Wightman 0167f749d3 Remove some old __future__ imports 2021-01-03 11:24:16 -08:00
Ross Wightman ce69de70d3 Add 21k weight urls to vision_transformer. Cleanup feature_info for preact ResNetV2 (BiT) models 2020-12-28 16:59:15 -08:00
Ross Wightman 231d04e91a ResNetV2 pre-act and non-preact model, w/ BiT pretrained weights and support for ViT R50 model. Tweaks for in21k num_classes passing. More to do... tests failing. 2020-12-28 16:59:15 -08:00
Ross Wightman 392595c7eb Add pool_size to default cfgs for new models to prevent tests from failing. Add explicit 200D_320 model entrypoint for next benchmark run. 2020-12-18 21:28:47 -08:00
Ross Wightman b1f1228a41 Add ResNet101D, 152D, and 200D weights, remove meh 66d model 2020-12-18 17:13:37 -08:00
Ross Wightman cd72e66eff Bug in last mod for features_only default_cfg 2020-12-03 12:33:01 -08:00