Ross Wightman
ea9c9550b2
Fully move ViT hybrids to their own file, including embedding module. Remove some extra DeiT models that were for benchmarking only.
2021-04-01 14:17:38 -07:00
Ross Wightman
a5310a3451
Merge remote-tracking branch 'origin/benchmark-fixes-vit_hybrids' into pit_and_vit_update
2021-04-01 12:15:34 -07:00
Ross Wightman
7953e5d11a
Fix pos_embed scaling for ViT and num_classes != 1000 for pretrained distilled deit and pit models. Fix #426 and fix #433
2021-03-31 23:11:28 -07:00
Ross Wightman
a760a4c3f4
Some ViT cleanup, merge distilled model with main, fixup torchscript support for distilled models
2021-03-31 18:21:02 -07:00
Ross Wightman
0dfc5a66bb
Add PiT model from https://github.com/naver-ai/pit
2021-03-31 18:20:14 -07:00
Ross Wightman
51febd869b
Small tweak to tests for tnt model, reorder model imports.
2021-03-29 11:33:08 -07:00
contrastive
de86314655
Update TNT
2021-03-29 08:23:34 +08:00
contrastive
cfc15283a4
Update TNT url
2021-03-28 23:19:15 +08:00
contrastive
4a09bc851e
Add TNT model
2021-03-28 19:53:42 +08:00
Ross Wightman
cf5fec5047
Cleanup experimental vit weight init a bit
2021-03-20 09:44:24 -07:00
Ross Wightman
cbcb76d72c
Should have included Conv2d layers in original weight init. Lets see what the impact is...
2021-03-18 23:15:48 -07:00
Ross Wightman
4de57ccf01
Add weight init scheme that's closer to JAX impl
2021-03-18 15:35:22 -07:00
Ross Wightman
14ac4abf74
Change huggingface hub revision delimiter to '@', add hf_hub reference for eca_nfnet_l0 model as an example.
2021-03-18 11:38:06 -07:00
Ross Wightman
740f32c96a
Add ECA-NFNet-L0 weights and update model name. Update README and bump version to 0.4.6
2021-03-17 13:55:32 -07:00
Ross Wightman
5e2e4e7fb6
Merge pull request #502 from khatami-mehrdad/efficientnet_dg
...
adding efficientnet_el, efficientnet_es_pruned and efficientnet_el_pruned pre-trained models
2021-03-17 13:35:22 -07:00
Ross Wightman
45c048ba13
A few minor fixes and bit more cleanup on the huggingface hub integration.
2021-03-17 13:18:52 -07:00
Mehrdad
97f49d163c
adding efficientnet_el, efficientnet_es_prunedefficientnet_es_pruned and efficientnet_el_pruned pretrained models to timm/models
2021-03-17 10:51:51 -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
17cdee7354
Fix C&P patch_size error, and order of op patch_size arg resolution bug. Remove a test vit model.
2021-03-01 16:53:32 -08:00
Ross Wightman
0706d05d52
Benchmark models listed in txt file. Add more hybrid vit variants for testing
2021-02-28 16:00:33 -08:00
Ross Wightman
de97be9146
Spell out diff between my small and deit small vit models.
2021-02-23 16:22:55 -08:00
Ross Wightman
f0ffdf89b3
Add numerous experimental ViT Hybrid models w/ ResNetV2 base. Update the ViT naming for hybrids. Fix #426 for pretrained vit resizing.
2021-02-23 15:54:55 -08:00
Ross Wightman
4bc103f504
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
2021-02-23 13:15:52 -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
