2bb65bd875
Wrong default_cfg pool_size for L1
2021-04-01 20:00:41 -07:00
bf2ca6bdf4
Merge jax and original weight init
2021-04-01 18:11:51 -07:00
acbd698c83
Update README.md with updates. Small tweak to head_dist handling.
2021-04-01 17:49:05 -07:00
9071568f0e
Add weights for SE NFNet-L0 model, rename nfnet_l0b -> nfnet_l0. 82.75 top-1 @ 288. Add nfnet_l1 model def for training.
2021-04-01 17:22:27 -07:00
c468c47a9c
Add regnety_160 weights from DeiT teacher model, update that and my regnety_032 weights to use higher test size.
2021-04-01 16:41:04 -07:00
288682796f
Update benchmark script to add precision arg. Fix some downstream (DeiT) compat issues with latest changes. Bump version to 0.4.7
2021-04-01 16:40:12 -07:00
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
a5310a3451
Merge remote-tracking branch 'origin/benchmark-fixes-vit_hybrids' into pit_and_vit_update
2021-04-01 12:15:34 -07:00
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
a760a4c3f4
Some ViT cleanup, merge distilled model with main, fixup torchscript support for distilled models
2021-03-31 18:21:02 -07:00
0dfc5a66bb
Add PiT model from https://github.com/naver-ai/pit
2021-03-31 18:20:14 -07:00
51febd869b
Small tweak to tests for tnt model, reorder model imports.
2021-03-29 11:33:08 -07:00
de86314655
Update TNT
2021-03-29 08:23:34 +08:00
cfc15283a4
Update TNT url
2021-03-28 23:19:15 +08:00
4a09bc851e
Add TNT model
2021-03-28 19:53:42 +08:00
cf5fec5047
Cleanup experimental vit weight init a bit
2021-03-20 09:44:24 -07:00
cbcb76d72c
Should have included Conv2d layers in original weight init. Lets see what the impact is...
2021-03-18 23:15:48 -07:00
4de57ccf01
Add weight init scheme that's closer to JAX impl
2021-03-18 15:35:22 -07:00
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
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
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
45c048ba13
A few minor fixes and bit more cleanup on the huggingface hub integration.
2021-03-17 13:18:52 -07:00
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
ead80d33c5
Fix typo, naming consistency
2021-03-16 23:02:51 -07:00
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
1f799afcb3
Remove capital letters in model names
2021-03-15 10:20:34 -07:00
82c1fe958a
added hardcorenas model
...
refactoring to support feature extraction
2021-03-15 08:06:34 +02:00
f57db99101
Update README, fix iabn pip version print.
2021-03-07 16:17:06 -08:00
7ef7788ee9
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
2021-03-06 16:56:34 -08:00
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
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
0706d05d52
Benchmark models listed in txt file. Add more hybrid vit variants for testing
2021-02-28 16:00:33 -08:00
de97be9146
Spell out diff between my small and deit small vit models.
2021-02-23 16:22:55 -08:00
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
4bc103f504
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
2021-02-23 13:15:52 -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
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
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
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
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
94ca140b67
update collections.abc import
2021-02-10 23:54:35 +11:00
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
a39c3ee216
Merge branch 'master' into eca-weights
2021-02-08 11:52:31 -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
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
b9843f954b
Merge pull request #282 from tigert1998/patch-1
...
Add symbolic for SwishJitAutoFn to support onnx
2021-02-04 12:18:40 -08:00
7a4be5c035
add operator HardSwishJitAutoFn export to onnx
2021-02-03 09:06:53 +08:00
f0e65e37b7
Fix NF-ResNet101 model defs
2021-01-30 23:26:19 -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
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
bb50ac4708
Add DeiT distilled weights and distilled model def. Remove some redudant ViT model args.
2021-01-25 11:05:23 -08:00
c16e965037
Add some ViT comments and fix a few minor issues.
2021-01-24 23:18:35 -08:00
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
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
d55bcc0fee
Finishing adding stochastic depth support to BiT ResNetV2 models
2021-01-16 16:32:03 -08:00
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
20516abc18
Fix some broken tests for ResNetV2 BiT models
2021-01-04 23:21:39 -08:00
59ec7e6a53
Merge branch 'master' into imagenet21k_datasets_more
2021-01-04 12:11:05 -08:00
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
0167f749d3
Remove some old __future__ imports
2021-01-03 11:24:16 -08:00
ce69de70d3
Add 21k weight urls to vision_transformer. Cleanup feature_info for preact ResNetV2 (BiT) models
2020-12-28 16:59:15 -08:00
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
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
b1f1228a41
Add ResNet101D, 152D, and 200D weights, remove meh 66d model
2020-12-18 17:13:37 -08:00
cd72e66eff
Bug in last mod for features_only default_cfg
2020-12-03 12:33:01 -08:00
867a0e5a04
Add default_cfg back to models wrapped in feature extraction module as per discussion in #294 .
2020-12-03 10:24:35 -08:00
2ed8f24715
A few more changes for 0.3.2 maint release. Linear layer change for mobilenetv3 and inception_v3, support no bias for linear wrapper.
2020-11-30 16:19:52 -08:00
460eba7f24
Work around casting issue with combination of native torch AMP and torchscript for Linear layers
2020-11-30 13:30:51 -08:00
5f4b6076d8
Fix inplace arg compat for GELU and PreLU via activation factory
2020-11-30 13:27:40 -08:00
fd962c4b4a
Native SiLU (Swish) op doesn't export to ONNX
2020-11-29 21:56:55 -08:00
43f2500c26
Add symbolic for SwishJitAutoFn to support onnx
2020-11-18 14:36:12 +08:00
b401952caf
Add newly added vision transformer large/base 224x224 weights ported from JAX official repo
2020-10-29 17:31:01 -07:00
61200db0ab
in_chans=1 working w/ pretrained weights for vision_transformer
2020-10-29 15:49:36 -07:00
e90edce438
Support native silu activation (aka swish). An optimized ver is available in PyTorch 1.7.
2020-10-29 15:45:17 -07:00
da6cd2cc1f
Fix regression for pretrained classifier loading when using entrypt functions directly
2020-10-29 15:43:39 -07:00
f591e90b0d
Make sure num_features attr is present in vit models as with others
2020-10-29 15:33:47 -07:00
f944242cb0
Fix #262 , num_classes arg mixup. Make vision_transformers a bit closer to other models wrt get/reset classfier/forward_features. Fix torchscript for ViT.
2020-10-29 13:58:28 -07:00
736f209e7d
Update vision transformers to be compatible with official code. Port official ViT weights from jax impl.
2020-10-26 18:42:11 -07:00
27a93e9de7
Improve test crop for ViT models. Small now 77.85, added base weights at 79.35 top-1.
2020-10-21 23:35:25 -07:00
d4db9e7977
Add small vision transformer weights. 77.42 top-1.
2020-10-21 12:14:12 -07:00
f31933cb37
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
2020-10-13 13:33:44 -07:00
fcb6258877
Add missing leaky_relu layer factory defn, update Apex/Native loss scaler interfaces to support unscaled grad clipping. Bump ver to 0.2.2 for pending release.
2020-10-02 16:19:39 -07:00
e8e2d9cabf
Add DropPath (stochastic depth) to ReXNet and VoVNet. RegNet DropPath impl tweak and dedupe se args.
2020-09-24 18:20:36 -07:00
e8ca45854c
More models in sotabench, more control over sotabench run, dataset filename extraction consistency
2020-09-24 15:56:57 -07:00
9c406532bd
Add EfficientNet-EdgeTPU-M (efficientnet_em) model trained natively in PyTorch. More sotabench fiddling.
2020-09-23 17:12:07 -07:00
c40384f5bd
Add ResNet weights. 80.5 (top-1) ResNet-50-D, 77.1 ResNet-34-D, 72.7 ResNet-18-D.
2020-09-18 12:05:37 -07:00
33f8a1bf36
Updated README, add wide_resnet50_2 and seresnext50_32x4d weights
2020-09-03 10:45:17 -07:00
751b0bba98
Add global_pool (--gp) arg changes to allow passing 'fast' easily for train/validate to avoid channels_last issue with AdaptiveAvgPool
2020-09-02 16:13:47 -07:00
Ross Wightman
contrastive
Ross Wightman
Mehrdad
AFLALO, Jonathan Isaac
Reuben
hwangdeyu
tigertang