Migrations
/
pytorch-image-models
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
1595 Commits
41 Branches
41 Tags
28 MiB
 
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '98c5e78226'
${ noResults }
Go to file
Ross Wightman 98c5e78226
Merge pull request #1564 from HongxinXiang/main 		2 years ago
.github Fix xdist dependency change 2 years ago
convert Move aggregation (convpool) for nest into NestLevel, cleanup and enable features_only use. Finalize weight url. 3 years ago
docs Add TPU TRC acknowledge 2 years ago
hfdocs/source 🎨 deploy docs from main not master 2 years ago
results Update benchmark with latest model adds 2 years ago
tests Add hf hub entries for laion2b clip models, add huggingface_hub dependency, update some setup/reqs, torch >= 1.7 2 years ago
timm Fix comment: https://github.com/rwightman/pytorch-image-models/pull/1564#issuecomment-1326743424 2 years ago
.gitattributes Add .gitattributes 5 years ago
.gitignore Update .gitignore, remove out of date notebooks 3 years ago
LICENSE Add Apache LICENSE file 6 years ago
MANIFEST.in Fix pruned txt files not being installed during pip install 5 years ago
README.md Update README.md 2 years ago
avg_checkpoints.py support bits checkpoints in avg/load 3 years ago
benchmark.py Refactor device handling in scripts, distributed init to be less 'cuda' centric. More device args passed through where needed. 2 years ago
bulk_runner.py Add bulk_runner script and updates to benchmark.py and validate.py for better error handling in bulk runs (used for benchmark and validation result runs). Improved batch size decay stepping on retry... 2 years ago
clean_checkpoint.py Transitioning default_cfg -> pretrained_cfg. Improving handling of pretrained_cfg source (HF-Hub, files, timm config, etc). Checkpoint handling tweaks. 3 years ago
distributed_train.sh Change the Python interpreter to Python 3.x in the scripts 4 years ago
hubconf.py Simpler approach to loading entrypoints in hubconf works properly 5 years ago
inference.py fix: the exeption when topk is 1 4 years ago
mkdocs.yml Tweak docs model summaries / pages names and layout 4 years ago
model-index.yml Move modelindex files into doc tree, add headings to model templates. Tweak a few details. 4 years ago
requirements-docs.txt Update docs requirements 4 years ago
requirements-modelindex.txt Bump jinja2 from 2.11.2 to 2.11.3 4 years ago
requirements.txt Add hf hub entries for laion2b clip models, add huggingface_hub dependency, update some setup/reqs, torch >= 1.7 2 years ago
setup.cfg Version 0.3.4. Tweak setup.cfg and update setup.py metadata 4 years ago
setup.py Add hf hub entries for laion2b clip models, add huggingface_hub dependency, update some setup/reqs, torch >= 1.7 2 years ago
train.py Merge pull request #1525 from TianyiFranklinWang/main 2 years ago
validate.py Update validate.py to use updated amp args for impl/dtype 2 years ago

README.md
Escape

PyTorch Image Models

Sponsors

Thanks to the following for hardware support:

And a big thanks to all GitHub sponsors who helped with some of my costs before I joined Hugging Face.

What's New

Oct 15, 2022

  • Train and validation script enhancements
  • Non-GPU (ie CPU) device support
  • SLURM compatibility for train script
  • HF datasets support (via ReaderHfds)
  • TFDS/WDS dataloading improvements (sample padding/wrap for distributed use fixed wrt sample count estimate)
  • in_chans !=3 support for scripts / loader
  • Adan optimizer
  • Can enable per-step LR scheduling via args
  • Dataset 'parsers' renamed to 'readers', more descriptive of purpose
  • AMP args changed, APEX via --amp-impl apex, bfloat16 supportedf via --amp-dtype bfloat16
  • main branch switched to 0.7.x version, 0.6x forked for stable release of weight only adds
  • master -> main branch rename

Oct 10, 2022

  • More weights in maxxvit series, incl first ConvNeXt block based coatnext and maxxvit experiments:
    • coatnext_nano_rw_224 - 82.0 @ 224 (G) -- (uses ConvNeXt conv block, no BatchNorm)
    • maxxvit_rmlp_nano_rw_256 - 83.0 @ 256, 83.7 @ 320 (G) (uses ConvNeXt conv block, no BN)
    • maxvit_rmlp_small_rw_224 - 84.5 @ 224, 85.1 @ 320 (G)
    • maxxvit_rmlp_small_rw_256 - 84.6 @ 256, 84.9 @ 288 (G) -- could be trained better, hparams need tuning (uses ConvNeXt block, no BN)
    • coatnet_rmlp_2_rw_224 - 84.6 @ 224, 85 @ 320 (T)
    • NOTE: official MaxVit weights (in1k) have been released at https://github.com/google-research/maxvit -- some extra work is needed to port and adapt since my impl was created independently of theirs and has a few small differences + the whole TF same padding fun.

Sept 23, 2022

  • LAION-2B CLIP image towers supported as pretrained backbones for fine-tune or features (no classifier)
    • vit_base_patch32_224_clip_laion2b
    • vit_large_patch14_224_clip_laion2b
    • vit_huge_patch14_224_clip_laion2b
    • vit_giant_patch14_224_clip_laion2b

Sept 7, 2022

  • Hugging Face timm docs home now exists, look for more here in the future
  • Add BEiT-v2 weights for base and large 224x224 models from https://github.com/microsoft/unilm/tree/master/beit2
  • Add more weights in maxxvit series incl a pico (7.5M params, 1.9 GMACs), two tiny variants:
    • maxvit_rmlp_pico_rw_256 - 80.5 @ 256, 81.3 @ 320 (T)
    • maxvit_tiny_rw_224 - 83.5 @ 224 (G)
    • maxvit_rmlp_tiny_rw_256 - 84.2 @ 256, 84.8 @ 320 (T)

Aug 29, 2022

  • MaxVit window size scales with img_size by default. Add new RelPosMlp MaxViT weight that leverages this:
    • maxvit_rmlp_nano_rw_256 - 83.0 @ 256, 83.6 @ 320 (T)

Aug 26, 2022

Aug 15, 2022

  • ConvNeXt atto weights added
    • convnext_atto - 75.7 @ 224, 77.0 @ 288
    • convnext_atto_ols - 75.9 @ 224, 77.2 @ 288

Aug 5, 2022

  • More custom ConvNeXt smaller model defs with weights
    • convnext_femto - 77.5 @ 224, 78.7 @ 288
    • convnext_femto_ols - 77.9 @ 224, 78.9 @ 288
    • convnext_pico - 79.5 @ 224, 80.4 @ 288
    • convnext_pico_ols - 79.5 @ 224, 80.5 @ 288
    • convnext_nano_ols - 80.9 @ 224, 81.6 @ 288
  • Updated EdgeNeXt to improve ONNX export, add new base variant and weights from original (https://github.com/mmaaz60/EdgeNeXt)

July 28, 2022

  • Add freshly minted DeiT-III Medium (width=512, depth=12, num_heads=8) model weights. Thanks Hugo Touvron!

July 27, 2022

  • All runtime benchmark and validation result csv files are finally up-to-date!
  • A few more weights & model defs added:
    • darknetaa53 - 79.8 @ 256, 80.5 @ 288
    • convnext_nano - 80.8 @ 224, 81.5 @ 288
    • cs3sedarknet_l - 81.2 @ 256, 81.8 @ 288
    • cs3darknet_x - 81.8 @ 256, 82.2 @ 288
    • cs3sedarknet_x - 82.2 @ 256, 82.7 @ 288
    • cs3edgenet_x - 82.2 @ 256, 82.7 @ 288
    • cs3se_edgenet_x - 82.8 @ 256, 83.5 @ 320
  • cs3* weights above all trained on TPU w/ bits_and_tpu branch. Thanks to TRC program!
  • Add output_stride=8 and 16 support to ConvNeXt (dilation)
  • deit3 models not being able to resize pos_emb fixed
  • Version 0.6.7 PyPi release (/w above bug fixes and new weighs since 0.6.5)

July 8, 2022

More models, more fixes

  • Official research models (w/ weights) added:
  • My own models:
    • Small ResNet defs added by request with 1 block repeats for both basic and bottleneck (resnet10 and resnet14)
    • CspNet refactored with dataclass config, simplified CrossStage3 (cs3) option. These are closer to YOLO-v5+ backbone defs.
    • More relative position vit fiddling. Two srelpos (shared relative position) models trained, and a medium w/ class token.
    • Add an alternate downsample mode to EdgeNeXt and train a small model. Better than original small, but not their new USI trained weights.
  • My own model weight results (all ImageNet-1k training)
    • resnet10t - 66.5 @ 176, 68.3 @ 224
    • resnet14t - 71.3 @ 176, 72.3 @ 224
    • resnetaa50 - 80.6 @ 224 , 81.6 @ 288
    • darknet53 - 80.0 @ 256, 80.5 @ 288
    • cs3darknet_m - 77.0 @ 256, 77.6 @ 288
    • cs3darknet_focus_m - 76.7 @ 256, 77.3 @ 288
    • cs3darknet_l - 80.4 @ 256, 80.9 @ 288
    • cs3darknet_focus_l - 80.3 @ 256, 80.9 @ 288
    • vit_srelpos_small_patch16_224 - 81.1 @ 224, 82.1 @ 320
    • vit_srelpos_medium_patch16_224 - 82.3 @ 224, 83.1 @ 320
    • vit_relpos_small_patch16_cls_224 - 82.6 @ 224, 83.6 @ 320
    • edgnext_small_rw - 79.6 @ 224, 80.4 @ 320
  • cs3, darknet, and vit_*relpos weights above all trained on TPU thanks to TRC program! Rest trained on overheating GPUs.
  • Hugging Face Hub support fixes verified, demo notebook TBA
  • Pretrained weights / configs can be loaded externally (ie from local disk) w/ support for head adaptation.
  • Add support to change image extensions scanned by timm datasets/readers. See (https://github.com/rwightman/pytorch-image-models/pull/1274#issuecomment-1178303103)
  • Default ConvNeXt LayerNorm impl to use F.layer_norm(x.permute(0, 2, 3, 1), ...).permute(0, 3, 1, 2) via LayerNorm2d in all cases.
    • a bit slower than previous custom impl on some hardware (ie Ampere w/ CL), but overall fewer regressions across wider HW / PyTorch version ranges.
    • previous impl exists as LayerNormExp2d in models/layers/norm.py
  • Numerous bug fixes
  • Currently testing for imminent PyPi 0.6.x release
  • LeViT pretraining of larger models still a WIP, they don't train well / easily without distillation. Time to add distill support (finally)?
  • ImageNet-22k weight training + finetune ongoing, work on multi-weight support (slowly) chugging along (there are a LOT of weights, sigh) ...

May 13, 2022

  • Official Swin-V2 models and weights added from (https://github.com/microsoft/Swin-Transformer). Cleaned up to support torchscript.
  • Some refactoring for existing timm Swin-V2-CR impl, will likely do a bit more to bring parts closer to official and decide whether to merge some aspects.
  • More Vision Transformer relative position / residual post-norm experiments (all trained on TPU thanks to TRC program)
    • vit_relpos_small_patch16_224 - 81.5 @ 224, 82.5 @ 320 -- rel pos, layer scale, no class token, avg pool
    • vit_relpos_medium_patch16_rpn_224 - 82.3 @ 224, 83.1 @ 320 -- rel pos + res-post-norm, no class token, avg pool
    • vit_relpos_medium_patch16_224 - 82.5 @ 224, 83.3 @ 320 -- rel pos, layer scale, no class token, avg pool
    • vit_relpos_base_patch16_gapcls_224 - 82.8 @ 224, 83.9 @ 320 -- rel pos, layer scale, class token, avg pool (by mistake)
  • Bring 512 dim, 8-head 'medium' ViT model variant back to life (after using in a pre DeiT 'small' model for first ViT impl back in 2020)
  • Add ViT relative position support for switching btw existing impl and some additions in official Swin-V2 impl for future trials
  • Sequencer2D impl (https://arxiv.org/abs/2205.01972), added via PR from author (https://github.com/okojoalg)

May 2, 2022

  • Vision Transformer experiments adding Relative Position (Swin-V2 log-coord) (vision_transformer_relpos.py) and Residual Post-Norm branches (from Swin-V2) (vision_transformer*.py)
    • vit_relpos_base_patch32_plus_rpn_256 - 79.5 @ 256, 80.6 @ 320 -- rel pos + extended width + res-post-norm, no class token, avg pool
    • vit_relpos_base_patch16_224 - 82.5 @ 224, 83.6 @ 320 -- rel pos, layer scale, no class token, avg pool
    • vit_base_patch16_rpn_224 - 82.3 @ 224 -- rel pos + res-post-norm, no class token, avg pool
  • Vision Transformer refactor to remove representation layer that was only used in initial vit and rarely used since with newer pretrain (ie How to Train Your ViT)
  • vit_* models support removal of class token, use of global average pool, use of fc_norm (ala beit, mae).

April 22, 2022

  • timm models are now officially supported in fast.ai! Just in time for the new Practical Deep Learning course. timmdocs documentation link updated to timm.fast.ai.
  • Two more model weights added in the TPU trained series. Some In22k pretrain still in progress.
    • seresnext101d_32x8d - 83.69 @ 224, 84.35 @ 288
    • seresnextaa101d_32x8d (anti-aliased w/ AvgPool2d) - 83.85 @ 224, 84.57 @ 288

March 23, 2022

  • Add ParallelBlock and LayerScale option to base vit models to support model configs in Three things everyone should know about ViT
  • convnext_tiny_hnf (head norm first) weights trained with (close to) A2 recipe, 82.2% top-1, could do better with more epochs.

March 21, 2022

  • Merge norm_norm_norm. IMPORTANT this update for a coming 0.6.x release will likely de-stabilize the master branch for a while. Branch 0.5.x or a previous 0.5.x release can be used if stability is required.
  • Significant weights update (all TPU trained) as described in this release
    • regnety_040 - 82.3 @ 224, 82.96 @ 288
    • regnety_064 - 83.0 @ 224, 83.65 @ 288
    • regnety_080 - 83.17 @ 224, 83.86 @ 288
    • regnetv_040 - 82.44 @ 224, 83.18 @ 288 (timm pre-act)
    • regnetv_064 - 83.1 @ 224, 83.71 @ 288 (timm pre-act)
    • regnetz_040 - 83.67 @ 256, 84.25 @ 320
    • regnetz_040h - 83.77 @ 256, 84.5 @ 320 (w/ extra fc in head)
    • resnetv2_50d_gn - 80.8 @ 224, 81.96 @ 288 (pre-act GroupNorm)
    • resnetv2_50d_evos 80.77 @ 224, 82.04 @ 288 (pre-act EvoNormS)
    • regnetz_c16_evos - 81.9 @ 256, 82.64 @ 320 (EvoNormS)
    • regnetz_d8_evos - 83.42 @ 256, 84.04 @ 320 (EvoNormS)
    • xception41p - 82 @ 299 (timm pre-act)
    • xception65 - 83.17 @ 299
    • xception65p - 83.14 @ 299 (timm pre-act)
    • resnext101_64x4d - 82.46 @ 224, 83.16 @ 288
    • seresnext101_32x8d - 83.57 @ 224, 84.270 @ 288
    • resnetrs200 - 83.85 @ 256, 84.44 @ 320
  • HuggingFace hub support fixed w/ initial groundwork for allowing alternative 'config sources' for pretrained model definitions and weights (generic local file / remote url support soon)
  • SwinTransformer-V2 implementation added. Submitted by Christoph Reich. Training experiments and model changes by myself are ongoing so expect compat breaks.
  • Swin-S3 (AutoFormerV2) models / weights added from https://github.com/microsoft/Cream/tree/main/AutoFormerV2
  • MobileViT models w/ weights adapted from https://github.com/apple/ml-cvnets
  • PoolFormer models w/ weights adapted from https://github.com/sail-sg/poolformer
  • VOLO models w/ weights adapted from https://github.com/sail-sg/volo
  • Significant work experimenting with non-BatchNorm norm layers such as EvoNorm, FilterResponseNorm, GroupNorm, etc
  • Enhance support for alternate norm + act ('NormAct') layers added to a number of models, esp EfficientNet/MobileNetV3, RegNet, and aligned Xception
  • Grouped conv support added to EfficientNet family
  • Add 'group matching' API to all models to allow grouping model parameters for application of 'layer-wise' LR decay, lr scale added to LR scheduler
  • Gradient checkpointing support added to many models
  • forward_head(x, pre_logits=False) fn added to all models to allow separate calls of forward_features + forward_head
  • All vision transformer and vision MLP models update to return non-pooled / non-token selected features from foward_features, for consistency with CNN models, token selection or pooling now applied in forward_head

Feb 2, 2022

  • Chris Hughes posted an exhaustive run through of timm on his blog yesterday. Well worth a read. Getting Started with PyTorch Image Models (timm): A Practitioner’s Guide
  • I'm currently prepping to merge the norm_norm_norm branch back to master (ver 0.6.x) in next week or so.
    • The changes are more extensive than usual and may destabilize and break some model API use (aiming for full backwards compat). So, beware pip install git+https://github.com/rwightman/pytorch-image-models installs!
    • 0.5.x releases and a 0.5.x branch will remain stable with a cherry pick or two until dust clears. Recommend sticking to pypi install for a bit if you want stable.

Jan 14, 2022

  • Version 0.5.4 w/ release to be pushed to pypi. It's been a while since last pypi update and riskier changes will be merged to main branch soon....
  • Add ConvNeXT models /w weights from official impl (https://github.com/facebookresearch/ConvNeXt), a few perf tweaks, compatible with timm features
  • Tried training a few small (~1.8-3M param) / mobile optimized models, a few are good so far, more on the way...
    • mnasnet_small - 65.6 top-1
    • mobilenetv2_050 - 65.9
    • lcnet_100/075/050 - 72.1 / 68.8 / 63.1
    • semnasnet_075 - 73
    • fbnetv3_b/d/g - 79.1 / 79.7 / 82.0
  • TinyNet models added by rsomani95
  • LCNet added via MobileNetV3 architecture

Nov 22, 2021

  • A number of updated weights anew new model defs
    • eca_halonext26ts - 79.5 @ 256
    • resnet50_gn (new) - 80.1 @ 224, 81.3 @ 288
    • resnet50 - 80.7 @ 224, 80.9 @ 288 (trained at 176, not replacing current a1 weights as default since these don't scale as well to higher res, weights)
    • resnext50_32x4d - 81.1 @ 224, 82.0 @ 288
    • sebotnet33ts_256 (new) - 81.2 @ 224
    • lamhalobotnet50ts_256 - 81.5 @ 256
    • halonet50ts - 81.7 @ 256
    • halo2botnet50ts_256 - 82.0 @ 256
    • resnet101 - 82.0 @ 224, 82.8 @ 288
    • resnetv2_101 (new) - 82.1 @ 224, 83.0 @ 288
    • resnet152 - 82.8 @ 224, 83.5 @ 288
    • regnetz_d8 (new) - 83.5 @ 256, 84.0 @ 320
    • regnetz_e8 (new) - 84.5 @ 256, 85.0 @ 320
  • vit_base_patch8_224 (85.8 top-1) & in21k variant weights added thanks Martins Bruveris
  • Groundwork in for FX feature extraction thanks to Alexander Soare
    • models updated for tracing compatibility (almost full support with some distlled transformer exceptions)

Oct 19, 2021

Aug 18, 2021

  • Optimizer bonanza!
    • Add LAMB and LARS optimizers, incl trust ratio clipping options. Tweaked to work properly in PyTorch XLA (tested on TPUs w/ timm bits branch)
    • Add MADGRAD from FB research w/ a few tweaks (decoupled decay option, step handling that works with PyTorch XLA)
    • Some cleanup on all optimizers and factory. No more .data, a bit more consistency, unit tests for all!
    • SGDP and AdamP still won't work with PyTorch XLA but others should (have yet to test Adabelief, Adafactor, Adahessian myself).
  • EfficientNet-V2 XL TF ported weights added, but they don't validate well in PyTorch (L is better). The pre-processing for the V2 TF training is a bit diff and the fine-tuned 21k -> 1k weights are very sensitive and less robust than the 1k weights.
  • Added PyTorch trained EfficientNet-V2 'Tiny' w/ GlobalContext attn weights. Only .1-.2 top-1 better than the SE so more of a curiosity for those interested.

Introduction

PyTorch Image Models (timm) is a collection of image models, layers, utilities, optimizers, schedulers, data-loaders / augmentations, and reference training / validation scripts that aim to pull together a wide variety of SOTA models with ability to reproduce ImageNet training results.

The work of many others is present here. I've tried to make sure all source material is acknowledged via links to github, arxiv papers, etc in the README, documentation, and code docstrings. Please let me know if I missed anything.

Models

All model architecture families include variants with pretrained weights. There are specific model variants without any weights, it is NOT a bug. Help training new or better weights is always appreciated. Here are some example training hparams to get you started.

A full version of the list below with source links can be found in the documentation.

Features

Several (less common) features that I often utilize in my projects are included. Many of their additions are the reason why I maintain my own set of models, instead of using others' via PIP:

Results

Model validation results can be found in the documentation and in the results tables

Getting Started (Documentation)

My current documentation for timm covers the basics.

Hugging Face timm docs will be the documentation focus going forward and will eventually replace the github.io docs above.

Getting Started with PyTorch Image Models (timm): A Practitioner’s Guide by Chris Hughes is an extensive blog post covering many aspects of timm in detail.

timmdocs is quickly becoming a much more comprehensive set of documentation for timm. A big thanks to Aman Arora for his efforts creating timmdocs.

paperswithcode is a good resource for browsing the models within timm.

Train, Validation, Inference Scripts

The root folder of the repository contains reference train, validation, and inference scripts that work with the included models and other features of this repository. They are adaptable for other datasets and use cases with a little hacking. See documentation for some basics and training hparams for some train examples that produce SOTA ImageNet results.

Awesome PyTorch Resources

One of the greatest assets of PyTorch is the community and their contributions. A few of my favourite resources that pair well with the models and components here are listed below.

Object Detection, Instance and Semantic Segmentation

Computer Vision / Image Augmentation

Knowledge Distillation

Metric Learning

Training / Frameworks

Licenses

Code

The code here is licensed Apache 2.0. I've taken care to make sure any third party code included or adapted has compatible (permissive) licenses such as MIT, BSD, etc. I've made an effort to avoid any GPL / LGPL conflicts. That said, it is your responsibility to ensure you comply with licenses here and conditions of any dependent licenses. Where applicable, I've linked the sources/references for various components in docstrings. If you think I've missed anything please create an issue.

Pretrained Weights

So far all of the pretrained weights available here are pretrained on ImageNet with a select few that have some additional pretraining (see extra note below). ImageNet was released for non-commercial research purposes only (https://image-net.org/download). It's not clear what the implications of that are for the use of pretrained weights from that dataset. Any models I have trained with ImageNet are done for research purposes and one should assume that the original dataset license applies to the weights. It's best to seek legal advice if you intend to use the pretrained weights in a commercial product.

Pretrained on more than ImageNet

Several weights included or references here were pretrained with proprietary datasets that I do not have access to. These include the Facebook WSL, SSL, SWSL ResNe(Xt) and the Google Noisy Student EfficientNet models. The Facebook models have an explicit non-commercial license (CC-BY-NC 4.0, https://github.com/facebookresearch/semi-supervised-ImageNet1K-models, https://github.com/facebookresearch/WSL-Images). The Google models do not appear to have any restriction beyond the Apache 2.0 license (and ImageNet concerns). In either case, you should contact Facebook or Google with any questions.

Citing

BibTeX

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/rwightman/pytorch-image-models}}
}

Latest DOI

DOI