list_optimizers, get_optimizer_class, get_optimizer_info to reworked create_optimizer_v2 fn to explore optimizers, get info or classoptim.optim_factory, move fns to optim/_optim_factory.py and optim/_param_groups.py and encourage import via timm.optimAdd a set of new very well trained ResNet & ResNet-V2 18/34 (basic block) weights. See https://huggingface.co/blog/rwightman/resnet-trick-or-treat
timm.models.registry, increased priority of existing deprecation warnings to be visibletimm as vit_intern300m_patch14_448| model | top1 | top5 | param_count | img_size |
|---|---|---|---|---|
| vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k | 87.438 | 98.256 | 64.11 | 384 |
| vit_mediumd_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k | 86.608 | 97.934 | 64.11 | 256 |
| vit_betwixt_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k | 86.594 | 98.02 | 60.4 | 384 |
| vit_betwixt_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k | 85.734 | 97.61 | 60.4 | 256 |
| model | top1 | top5 | param_count | img_size |
|---|---|---|---|---|
| resnet50d.ra4_e3600_r224_in1k | 81.838 | 95.922 | 25.58 | 288 |
| efficientnet_b1.ra4_e3600_r240_in1k | 81.440 | 95.700 | 7.79 | 288 |
| resnet50d.ra4_e3600_r224_in1k | 80.952 | 95.384 | 25.58 | 224 |
| efficientnet_b1.ra4_e3600_r240_in1k | 80.406 | 95.152 | 7.79 | 240 |
| mobilenetv1_125.ra4_e3600_r224_in1k | 77.600 | 93.804 | 6.27 | 256 |
| mobilenetv1_125.ra4_e3600_r224_in1k | 76.924 | 93.234 | 6.27 | 224 |
| model | top1 | top5 | param_count |
|---|---|---|---|
| hiera_small_abswin_256.sbb2_e200_in12k_ft_in1k | 84.912 | 97.260 | 35.01 |
| hiera_small_abswin_256.sbb2_pd_e200_in12k_ft_in1k | 84.560 | 97.106 | 35.01 |
mobilenet_edgetpu_v2_m weights w/ ra4 mnv4-small based recipe. 80.1% top-1 @ 224 and 80.7 @ 256.| model | top1 | top1_err | top5 | top5_err | param_count | img_size |
|---|---|---|---|---|---|---|
| mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k | 84.99 | 15.01 | 97.294 | 2.706 | 32.59 | 544 |
| mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k | 84.772 | 15.228 | 97.344 | 2.656 | 32.59 | 480 |
| mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k | 84.64 | 15.36 | 97.114 | 2.886 | 32.59 | 448 |
| mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k | 84.314 | 15.686 | 97.102 | 2.898 | 32.59 | 384 |
| mobilenetv4_conv_aa_large.e600_r384_in1k | 83.824 | 16.176 | 96.734 | 3.266 | 32.59 | 480 |
| mobilenetv4_conv_aa_large.e600_r384_in1k | 83.244 | 16.756 | 96.392 | 3.608 | 32.59 | 384 |
| mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k | 82.99 | 17.01 | 96.67 | 3.33 | 11.07 | 320 |
| mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k | 82.364 | 17.636 | 96.256 | 3.744 | 11.07 | 256 |
| model | top1 | top1_err | top5 | top5_err | param_count | img_size |
|---|---|---|---|---|---|---|
| efficientnet_b0.ra4_e3600_r224_in1k | 79.364 | 20.636 | 94.754 | 5.246 | 5.29 | 256 |
| efficientnet_b0.ra4_e3600_r224_in1k | 78.584 | 21.416 | 94.338 | 5.662 | 5.29 | 224 |
| mobilenetv1_100h.ra4_e3600_r224_in1k | 76.596 | 23.404 | 93.272 | 6.728 | 5.28 | 256 |
| mobilenetv1_100.ra4_e3600_r224_in1k | 76.094 | 23.906 | 93.004 | 6.996 | 4.23 | 256 |
| mobilenetv1_100h.ra4_e3600_r224_in1k | 75.662 | 24.338 | 92.504 | 7.496 | 5.28 | 224 |
| mobilenetv1_100.ra4_e3600_r224_in1k | 75.382 | 24.618 | 92.312 | 7.688 | 4.23 | 224 |
set_input_size() added to vit and swin v1/v2 models to allow changing image size, patch size, window size after model creation.set_input_size, always_partition and strict_img_size args have been added to __init__ to allow more flexible input size constraintstiny < .5M param models for testing that are actually trained on ImageNet-1k| model | top1 | top1_err | top5 | top5_err | param_count | img_size | crop_pct |
|---|---|---|---|---|---|---|---|
| test_efficientnet.r160_in1k | 47.156 | 52.844 | 71.726 | 28.274 | 0.36 | 192 | 1.0 |
| test_byobnet.r160_in1k | 46.698 | 53.302 | 71.674 | 28.326 | 0.46 | 192 | 1.0 |
| test_efficientnet.r160_in1k | 46.426 | 53.574 | 70.928 | 29.072 | 0.36 | 160 | 0.875 |
| test_byobnet.r160_in1k | 45.378 | 54.622 | 70.572 | 29.428 | 0.46 | 160 | 0.875 |
| test_vit.r160_in1k | 42.0 | 58.0 | 68.664 | 31.336 | 0.37 | 192 | 1.0 |
| test_vit.r160_in1k | 40.822 | 59.178 | 67.212 | 32.788 | 0.37 | 160 | 0.875 |
| model | top1 | top1_err | top5 | top5_err | param_count | img_size |
|---|---|---|---|---|---|---|
| mobilenetv4_hybrid_large.ix_e600_r384_in1k | 84.356 | 15.644 | 96.892 | 3.108 | 37.76 | 448 |
| mobilenetv4_hybrid_large.ix_e600_r384_in1k | 83.990 | 16.010 | 96.702 | 3.298 | 37.76 | 384 |
| mobilenetv4_hybrid_medium.ix_e550_r384_in1k | 83.394 | 16.606 | 96.760 | 3.240 | 11.07 | 448 |
| mobilenetv4_hybrid_medium.ix_e550_r384_in1k | 82.968 | 17.032 | 96.474 | 3.526 | 11.07 | 384 |
| mobilenetv4_hybrid_medium.ix_e550_r256_in1k | 82.492 | 17.508 | 96.278 | 3.722 | 11.07 | 320 |
| mobilenetv4_hybrid_medium.ix_e550_r256_in1k | 81.446 | 18.554 | 95.704 | 4.296 | 11.07 | 256 |
timm trained weights added:normalize= flag for transorms, return non-normalized torch.Tensor with original dytpe (for chug)Searching for Better ViT Baselines (For the GPU Poor) weights and vit variants released. Exploring model shapes between Tiny and Base.| model | top1 | top5 | param_count | img_size |
|---|---|---|---|---|
| vit_mediumd_patch16_reg4_gap_256.sbb_in12k_ft_in1k | 86.202 | 97.874 | 64.11 | 256 |
| vit_betwixt_patch16_reg4_gap_256.sbb_in12k_ft_in1k | 85.418 | 97.48 | 60.4 | 256 |
| vit_mediumd_patch16_rope_reg1_gap_256.sbb_in1k | 84.322 | 96.812 | 63.95 | 256 |
| vit_betwixt_patch16_rope_reg4_gap_256.sbb_in1k | 83.906 | 96.684 | 60.23 | 256 |
| vit_base_patch16_rope_reg1_gap_256.sbb_in1k | 83.866 | 96.67 | 86.43 | 256 |
| vit_medium_patch16_rope_reg1_gap_256.sbb_in1k | 83.81 | 96.824 | 38.74 | 256 |
| vit_betwixt_patch16_reg4_gap_256.sbb_in1k | 83.706 | 96.616 | 60.4 | 256 |
| vit_betwixt_patch16_reg1_gap_256.sbb_in1k | 83.628 | 96.544 | 60.4 | 256 |
| vit_medium_patch16_reg4_gap_256.sbb_in1k | 83.47 | 96.622 | 38.88 | 256 |
| vit_medium_patch16_reg1_gap_256.sbb_in1k | 83.462 | 96.548 | 38.88 | 256 |
| vit_little_patch16_reg4_gap_256.sbb_in1k | 82.514 | 96.262 | 22.52 | 256 |
| vit_wee_patch16_reg1_gap_256.sbb_in1k | 80.256 | 95.360 | 13.42 | 256 |
| vit_pwee_patch16_reg1_gap_256.sbb_in1k | 80.072 | 95.136 | 15.25 | 256 |
| vit_mediumd_patch16_reg4_gap_256.sbb_in12k | N/A | N/A | 64.11 | 256 |
| vit_betwixt_patch16_reg4_gap_256.sbb_in12k | N/A | N/A | 60.4 | 256 |
timm models. See example in https://github.com/huggingface/pytorch-image-models/discussions/1232#discussioncomment-9320949forward_intermediates() API refined and added to more models including some ConvNets that have other extraction methods.features_only=True feature extraction. Remaining 34 architectures can be supported but based on priority requests.features_only=True support for ViT models with flat hidden states or non-std module layouts (so far covering 'vit_*', 'twins_*', 'deit*', 'beit*', 'mvitv2*', 'eva*', 'samvit_*', 'flexivit*')forward_intermediates() API that can be used with a feature wrapping module or direclty.model = timm.create_model('vit_base_patch16_224')
final_feat, intermediates = model.forward_intermediates(input)
output = model.forward_head(final_feat) # pooling + classifier head
print(final_feat.shape)
torch.Size([2, 197, 768])
for f in intermediates:
print(f.shape)
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
print(output.shape)
torch.Size([2, 1000])
model = timm.create_model('eva02_base_patch16_clip_224', pretrained=True, img_size=512, features_only=True, out_indices=(-3, -2,))
output = model(torch.randn(2, 3, 512, 512))
for o in output:
print(o.shape)
torch.Size([2, 768, 32, 32])
torch.Size([2, 768, 32, 32])
Datasets & transform refactoring
--dataset hfids:org/dataset)datasets and webdataset wrapper streaming from HF hub with recent timm ImageNet uploads to https://huggingface.co/timm--input-size 1 224 224 or --in-chans 1, sets PIL image conversion appropriately in dataset--val-split '') in train script--bce-sum (sum over class dim) and --bce-pos-weight (positive weighting) args for training as they're common BCE loss tweaks I was often hard codingmodel_args config entry. model_args will be passed as kwargs through to models on creation.
vision_transformer.py typing and doc cleanup by Laureηtquickgelu ViT variants for OpenAI, DFN, MetaCLIP weights that use it (less efficient)convnext_xxlargevision_transformer.py.
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.
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.
To see full list of optimizers w/ descriptions: timm.optim.list_optimizers(with_description=True)
Included optimizers available via timm.optim.create_optimizer_v2 factory method:
adabelief an implementation of AdaBelief adapted from https://github.com/juntang-zhuang/Adabelief-Optimizer - https://arxiv.org/abs/2010.07468adafactor adapted from FAIRSeq impl - https://arxiv.org/abs/1804.04235adafactorbv adapted from Big Vision - https://arxiv.org/abs/2106.04560adahessian by David Samuel - https://arxiv.org/abs/2006.00719adamp and sgdp by Naver ClovAI - https://arxiv.org/abs/2006.08217adan an implementation of Adan adapted from https://github.com/sail-sg/Adan - https://arxiv.org/abs/2208.06677adopt ADOPT adapted from https://github.com/iShohei220/adopt - https://arxiv.org/abs/2411.02853lamb an implementation of Lamb and LambC (w/ trust-clipping) cleaned up and modified to support use with XLA - https://arxiv.org/abs/1904.00962laprop optimizer from https://github.com/Z-T-WANG/LaProp-Optimizer - https://arxiv.org/abs/2002.04839lars an implementation of LARS and LARC (w/ trust-clipping) - https://arxiv.org/abs/1708.03888lion and implementation of Lion adapted from https://github.com/google/automl/tree/master/lion - https://arxiv.org/abs/2302.06675lookahead adapted from impl by Liam - https://arxiv.org/abs/1907.08610madgrad an implementation of MADGRAD adapted from https://github.com/facebookresearch/madgrad - https://arxiv.org/abs/2101.11075mars MARS optimizer from https://github.com/AGI-Arena/MARS - https://arxiv.org/abs/2411.10438nadam an implementation of Adam w/ Nesterov momentumnadamw an impementation of AdamW (Adam w/ decoupled weight-decay) w/ Nesterov momentum. A simplified impl based on https://github.com/mlcommons/algorithmic-efficiencynovograd by Masashi Kimura - https://arxiv.org/abs/1905.11286radam by Liyuan Liu - https://arxiv.org/abs/1908.03265rmsprop_tf adapted from PyTorch RMSProp by myself. Reproduces much improved Tensorflow RMSProp behavioursgdw and implementation of SGD w/ decoupled weight-decayfused<name> optimizers by name with NVIDIA Apex installedbnb<name> optimizers by name with BitsAndBytes installedcadamw, clion, and more 'Cautious' optimizers from https://github.com/kyleliang919/C-Optim - https://arxiv.org/abs/2411.16085adam, adamw, rmsprop, adadelta, adagrad, and sgd pass through to torch.optim implementationsSeveral (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:
get_classifier and reset_classifierforward_features (see documentation)create_model(name, features_only=True, out_indices=..., output_stride=...)out_indices creation arg specifies which feature maps to return, these indices are 0 based and generally correspond to the C(i + 1) feature level.output_stride creation arg controls output stride of the network by using dilated convolutions. Most networks are stride 32 by default. Not all networks support this..feature_info memberstep, cosine w/ restarts, tanh w/ restarts, plateauModel validation results can be found in the results tables
The official documentation can be found at https://huggingface.co/docs/hub/timm. Documentation contributions are welcome.
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 an alternate 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.
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.
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.
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.
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.
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.
@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}}
}
FAQs
PyTorch Image Models
We found that timm demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
Research
The Socket Research Team breaks down a malicious wrapper package that uses obfuscation to harvest credentials and exfiltrate sensitive data.
Research
Security News
Attackers used a malicious npm package typosquatting a popular ESLint plugin to steal sensitive data, execute commands, and exploit developer systems.
Security News
The Ultralytics' PyPI Package was compromised four times in one weekend through GitHub Actions cache poisoning and failure to rotate previously compromised API tokens.