huggingface/pytorch-image-models

• What's New
• Introduction
• Models
• Features
• Results
• Getting Started (Documentation)
• Train, Validation, Inference Scripts
• Awesome PyTorch Resources
• Licenses
• Citing

• Initial NaFlexVit model code. NaFlexVit is a Vision Transformer with:
  1. Encapsulated embedding and position encoding in a single module
  2. Support for nn.Linear embedding on pre-ified (dictionary) inputs
  3. Support for NaFlex variable aspect, variable resolution (SigLip-2: https://arxiv.org/abs/2502.14786)
  4. Support for FlexiViT variable size (https://arxiv.org/abs/2212.08013)
  5. Support for NaViT fractional/factorized position embedding (https://arxiv.org/abs/2307.06304)
• Existing vit models in vision_transformer.py can be loaded into the NaFlexVit model by adding the use_naflex=True flag to create_model
  • Some native weights coming soon
• A full NaFlex data pipeline is available that allows training / fine-tuning / evaluating with variable aspect / size images
  • To enable in train.py and validate.py add the --naflex-loader arg, must be used with a NaFlexVit
• To evaluate an existing (classic) ViT loaded in NaFlexVit model w/ NaFlex data pipe:
  • python validate.py /imagenet --amp -j 8 --model vit_base_16_224 --model-kwargs use_naflex=True --naflex-loader --naflex-max-seq-len 256
• The training has some extra args features worth noting
  • The --naflex-train-seq-lens' argument specifies which sequence lengths to randomly pick from per batch during training
  • The --naflex-max-seq-len argument sets the target sequence length for validation
  • Adding --model-kwargs enable__interpolator=True --naflex--sizes 12 16 24 will enable random size selection per-batch w/ interpolation
  • The --naflex-loss-scale arg changes loss scaling mode per batch relative to the batch size, timm NaFlex loading changes the batch size for each seq len

• Add a number of small/fast models thanks to https://.com/brianhou0208
  • SwiftFormer - (ICCV2023) SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
  • FasterNet - (CVPR2023) Run, Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks
  • SHViT - (CVPR2024) SHViT: Single-Head Vision Transformer with Memory Efficient
  • StarNet - (CVPR2024) Rewrite the Stars
  • GhostNet-V3 GhostNetV3: Exploring the Training Strategies for Compact Models
• Update EVA ViT (closest match) to support Perception Encoder models (https://arxiv.org/abs/2504.13181) from Meta, loading Hub weights but I still need to push dedicated timm weights
  • Add some flexibility to ROPE impl
• Big increase in number of models supporting forward_intermediates() and some additional fixes thanks to https://.com/brianhou0208
  • DaViT, EdgeNeXt, EfficientFormerV2, EfficientViT(MIT), EfficientViT(MSRA), FocalNet, GCViT, HGNet /V2, InceptionNeXt, Inception-V4, MambaOut, MetaFormer, NesT, Next-ViT, PiT, PVT V2, RepGhostNet, RepViT, ResNetV2, ReXNet, TinyViT, TResNet, VoV
• TNT model updated w/ new weights forward_intermediates() thanks to https://.com/brianhou0208
• Add local-dir: pretrained schema, can use local-dir:/path/to/model/folder for model name to source model / pretrained cfg & weights Hugging Face Hub models (config.json + weights file) from a local folder.
• Fixes, improvements for onnx export

• SigLIP 2 ViT image encoders added (https://huggingface.co/collections/timm/siglip-2-67b8e72ba08b09dd97aecaf9)
  • Variable resolution / aspect NaFlex versions are a WIP
• Add 'SO150M2' ViT weights trained with SBB recipes, great results, better for ImageNet than previous attempt w/ less training.
  • vit_so150m2_16_reg1_gap_448.sbb_e200_in12k_ft_in1k - 88.1% top-1
  • vit_so150m2_16_reg1_gap_384.sbb_e200_in12k_ft_in1k - 87.9% top-1
  • vit_so150m2_16_reg1_gap_256.sbb_e200_in12k_ft_in1k - 87.3% top-1
  • vit_so150m2_16_reg4_gap_256.sbb_e200_in12k
• Updated InternViT-300M '2.5' weights
• Release 1.0.15

• FYI PyTorch 2.6 & Python 3.13 are tested and working w/ current main and released version of timm

• Add Kron Optimizer (PSGD w/ Kronecker-factored preconditioner)
  • Code from https://.com/evanatyourservice/kron_torch
  • See also https://sites.google.com/site/lixilinx/home/psgd

• Fix loading of LeViT safetensor weights, remove conversion code which should have been deactivated
• Add 'SO150M' ViT weights trained with SBB recipes, decent results, but not optimal shape for ImageNet-12k/1k pretrain/ft
  • vit_so150m_16_reg4_gap_256.sbb_e250_in12k_ft_in1k - 86.7% top-1
  • vit_so150m_16_reg4_gap_384.sbb_e250_in12k_ft_in1k - 87.4% top-1
  • vit_so150m_16_reg4_gap_256.sbb_e250_in12k
• Misc typing, typo, etc. cleanup
• 1.0.14 release to get above LeViT fix out

• Add support to train and validate in pure bfloat16 or float16
• wandb project name arg added by https://.com/caojiaolong, use arg.experiment for name
• Fix old issue w/ checkpoint saving not working on filesystem w/o hard-link support (e.g. FUSE fs mounts)
• 1.0.13 release

• Add torch.utils.checkpoint.checkpoint() wrapper in timm.models that defaults use_reentrant=False, unless TIMM_REENTRANT_CKPT=1 is set in env.

• convnext_nano 384x384 ImageNet-12k pretrain & fine-tune. https://huggingface.co/models?search=convnext_nano%20r384
• Add AIM-v2 encoders from https://.com/apple/ml-aim, see on Hub: https://huggingface.co/models?search=timm%20aimv2
• Add PaliGemma2 encoders from https://.com/google-research/big_vision to existing PaliGemma, see on Hub: https://huggingface.co/models?search=timm%20pali2
• Add missing L/14 DFN2B 39B CLIP ViT, vit_large_14_clip_224.dfn2b_s39b
• Fix existing RmsNorm layer & fn to match standard formulation, use PT 2.5 impl when possible. Move old impl to SimpleNorm layer, it's LN w/o centering or bias. There were only two timm models using it, and they have been updated.
• Allow override of cache_dir arg for model creation
• Pass through trust_remote_code for HF datasets wrapper
• inception_next_atto model added by creator
• Adan optimizer caution, and Lamb decoupled weighgt decay options
• Some feature_info metadata fixed by https://.com/brianhou0208
• All OpenCLIP and JAX (CLIP, SigLIP, Pali, etc) model weights that used load time remapping were given their own HF Hub instances so that they work with hf-hub: based loading, and thus will work with new Transformers TimmWrapperModel

• More optimizers
  • Add MARS optimizer (https://arxiv.org/abs/2411.10438, https://.com/AGI-Arena/MARS)
  • Add LaProp optimizer (https://arxiv.org/abs/2002.04839, https://.com/Z-T-WANG/LaProp-Optimizer)
  • Add masking from 'Cautious Optimizers' (https://arxiv.org/abs/2411.16085, https://.com/kyleliang919/C-Optim) to Adafactor, Adafactor Big Vision, AdamW (legacy), Adopt, Lamb, LaProp, Lion, NadamW, RMSPropTF, SGDW
  • Cleanup some docstrings and type annotations re optimizers and factory
• Add MobileNet-V4 Conv Medium models pretrained on in12k and fine-tuned in1k @ 384x384
  • https://huggingface.co/timm/mobilenetv4_conv_medium.e250_r384_in12k_ft_in1k
  • https://huggingface.co/timm/mobilenetv4_conv_medium.e250_r384_in12k
  • https://huggingface.co/timm/mobilenetv4_conv_medium.e180_ad_r384_in12k
  • https://huggingface.co/timm/mobilenetv4_conv_medium.e180_r384_in12k
• Add small cs3darknet, quite good for the speed
  • https://huggingface.co/timm/cs3darknet_focus_s.ra4_e3600_r256_in1k

• Optimizer factory refactor
  • New factory works by registering optimizers using an OptimInfo dataclass w/ some key traits
  • Add list_optimizers, get_optimizer_class, get_optimizer_info to reworked create_optimizer_v2 fn to explore optimizers, get info or class
  • deprecate optim.optim_factory, move fns to optim/_optim_factory.py and optim/_param_groups.py and encourage import via timm.optim
• Add Adopt (https://.com/iShohei220/adopt) optimizer
• Add 'Big Vision' variant of Adafactor (https://.com/google-research/big_vision/blob/main/big_vision/optax.py) optimizer
• Fix original Adafactor to pick better factorization dims for convolutions
• Tweak LAMB optimizer with some improvements in torch.where functionality since original, refactor clipping a bit
• dynamic img size support in vit, deit, eva improved to support resize from non-square grids, thanks https://.com/wojtke

Add 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

• Cleanup torch amp usage to avoid cuda specific calls, merge support for Ascend (NPU) devices from MengqingCao that should work now in PyTorch 2.5 w/ new device extension autoloading feature. Tested Intel Arc (XPU) in Pytorch 2.5 too and it (mostly) worked.

• Fix error on importing from deprecated path timm.models.registry, increased priority of existing deprecation warnings to be visible
• Port weights of InternViT-300M (https://huggingface.co/OpenGVLab/InternViT-300M-448px) to timm as vit_intern300m_14_448

• Pre-activation (ResNetV2) version of 18/18d/34/34d ResNet model defs added by request (weights pending)
• Release 1.0.10

• MambaOut (https://.com/yuweihao/MambaOut) model & weights added. A cheeky take on SSM vision models w/o the SSM (essentially ConvNeXt w/ gating). A mix of original weights + custom variations & weights.

• SigLIP SO400M ViT fine-tunes on ImageNet-1k @ 378x378, added 378x378 option for existing SigLIP 384x384 models
  • vit_so400m_14_siglip_378.webli_ft_in1k - 89.42 top-1
  • vit_so400m_14_siglip_gap_378.webli_ft_in1k - 89.03
• SigLIP SO400M ViT encoder from recent multi-lingual (i18n) variant, 16 @ 256x256 (https://huggingface.co/timm/ViT-SO400M-16-SigLIP-i18n-256). OpenCLIP update pending.
• Add two ConvNeXt 'Zepto' models & weights (one w/ overlapped stem and one w/ stem). Uses RMSNorm, smaller than previous 'Atto', 2.2M params.
  • convnext_zepto_rms_ols.ra4_e3600_r224_in1k - 73.20 top-1 @ 224
  • convnext_zepto_rms.ra4_e3600_r224_in1k - 72.81 @ 224

• Add a suite of tiny test models for improved unit tests and niche low-resource applications (https://huggingface.co/blog/rwightman/timm-tiny-test)
• Add MobileNetV4-Conv-Small (0.5x) model (https://huggingface.co/posts/rwightman/793053396198664)
  • mobilenetv4_conv_small_050.e3000_r224_in1k - 65.81 top-1 @ 256, 64.76 @ 224
• Add MobileNetV3-Large variants trained with MNV4 Small recipe
  • mobilenetv3_large_150d.ra4_e3600_r256_in1k - 81.81 @ 320, 80.94 @ 256
  • mobilenetv3_large_100.ra4_e3600_r224_in1k - 77.16 @ 256, 76.31 @ 224

• Updated SBB ViT models trained on ImageNet-12k and fine-tuned on ImageNet-1k, challenging quite a number of much larger, slower models

• MobileNet-V1 1.25, EfficientNet-B1, & ResNet50-D weights w/ MNV4 baseline challenge recipe

• Add SAM2 (HieraDet) backbone arch & weight loading support
• Add Hiera Small weights trained w/ abswin pos embed on in12k & fine-tuned on 1k

• Add RDNet ('DenseNets Reloaded', https://arxiv.org/abs/2403.19588), thanks Donghyun Kim

• Add mobilenet_edgetpu_v2_m weights w/ ra4 mnv4-small based recipe. 80.1% top-1 @ 224 and 80.7 @ 256.
• Release 1.0.8

• More MobileNet-v4 weights, ImageNet-12k pretrain w/ fine-tunes, and anti-aliased ConvLarge models

• Impressive MobileNet-V1 and EfficientNet-B0 baseline challenges (https://huggingface.co/blog/rwightman/mobilenet-baselines)

• of set_input_size() added to vit and swin v1/v2 models to allow changing image size, size, window size after model creation.
• Improved support in swin for different size handling, in addition to set_input_size, always_partition and strict_img_size args have been added to __init__ to allow more flexible input size constraints
• Fix out of order indices info for intermediate 'Getter' feature wrapper, check out or range indices for same.
• Add several tiny < .5M param models for testing that are actually trained on ImageNet-1k

• Fix vit reg token init, thanks Promisery
• Other misc fixes

• 3 more MobileNetV4 hyrid weights with different MQA weight init scheme

• florence2 weight loading in DaViT model

• MobileNetV4 models and initial set of timm trained weights added:

• Apple MobileCLIP (https://arxiv.org/pdf/2311.17049, FastViT and ViT-B) image tower model support & weights added (part of OpenCLIP support).
• ViTamin (https://arxiv.org/abs/2404.02132) CLIP image tower model & weights added (part of OpenCLIP support).
• OpenAI CLIP Modified ResNet image tower modelling & weight support (via ByobNet). Refactor AttentionPool2d.

• Support loading PaliGemma jax weights into SigLIP ViT models with average pooling.
• Add Hiera models from Meta (https://.com/facebookresearch/hiera).
• Add normalize= flag for transforms, return non-normalized torch.Tensor with original dytpe (for chug)
• Version 1.0.3 release

• Searching for Better ViT Baselines (For the GPU Poor) weights and vit variants released. Exploring model shapes between Tiny and Base.

• AttentionExtract helper added to extract attention maps from timm models. See example in #1232 (comment)
• forward_intermediates() API refined and added to more models including some ConvNets that have other extraction methods.
• 1017 of 1047 model architectures support features_only=True feature extraction. Remaining 34 architectures can be supported but based on priority requests.
• Remove torch.jit.script annotated functions including old JIT activations. Conflict with dynamo and dynamo does a much better job when used.

• Prepping for a long overdue 1.0 release, things have been stable for a while now.
• Significant feature that's been missing for a while, 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*')
• Above feature support achieved through a new forward_intermediates() API that can be used with a feature wrapping module or directly.

model = timm.create_model('vit_base_16_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_16_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])

• TinyCLIP vision tower weights added, thx Thien Tran

• Next-ViT models added. Adapted from https://.com/bytedance/Next-ViT
• HGNet and PP-HGNetV2 models added. Adapted from https://.com/PaddlePaddle/PaddleClas by SeeFun
• Removed setup.py, moved to pyproject.toml based build supported by PDM
• Add updated model EMA impl using _for_each for less overhead
• Support device args in train script for non GPU devices
• Other misc fixes and small additions
• Min supported Python version increased to 3.8
• Release 0.9.16

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 , 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.

• Aggregating Nested Transformers - https://arxiv.org/abs/2105.12723
• BEiT - https://arxiv.org/abs/2106.08254
• Big Transfer ResNetV2 (BiT) - https://arxiv.org/abs/1912.11370
• Bottleneck Transformers - https://arxiv.org/abs/2101.11605
• CaiT (Class-Attention in Image Transformers) - https://arxiv.org/abs/2103.17239
• CoaT (Co-Scale Conv-Attentional Image Transformers) - https://arxiv.org/abs/2104.06399
• CoAtNet (Convolution and Attention) - https://arxiv.org/abs/2106.04803
• ConvNeXt - https://arxiv.org/abs/2201.03545
• ConvNeXt-V2 - http://arxiv.org/abs/2301.00808
• ConViT (Soft Convolutional Inductive Biases Vision Transformers)- https://arxiv.org/abs/2103.10697
• CspNet (Cross-Stage Partial Networks) - https://arxiv.org/abs/1911.11929
• DeiT - https://arxiv.org/abs/2012.12877
• DeiT-III - https://arxiv.org/pdf/2204.07118.pdf
• DenseNet - https://arxiv.org/abs/1608.06993
• DLA - https://arxiv.org/abs/1707.06484
• DPN (Dual-Path Network) - https://arxiv.org/abs/1707.01629
• EdgeNeXt - https://arxiv.org/abs/2206.10589
• EfficientFormer - https://arxiv.org/abs/2206.01191
• EfficientNet (MBConvNet Family)
  • EfficientNet NoisyStudent (B0-B7, L2) - https://arxiv.org/abs/1911.04252
  • EfficientNet AdvProp (B0-B8) - https://arxiv.org/abs/1911.09665
  • EfficientNet (B0-B7) - https://arxiv.org/abs/1905.11946
  • EfficientNet-EdgeTPU (S, M, L) - https://ai.googleblog.com/2019/08/efficientnet-edgetpu-creating.html
  • EfficientNet V2 - https://arxiv.org/abs/2104.00298
  • FBNet-C - https://arxiv.org/abs/1812.03443
  • MixNet - https://arxiv.org/abs/1907.09595
  • MNASNet B1, A1 (Squeeze-Excite), and Small - https://arxiv.org/abs/1807.11626
  • MobileNet-V2 - https://arxiv.org/abs/1801.04381
  • Single-Path NAS - https://arxiv.org/abs/1904.02877
  • TinyNet - https://arxiv.org/abs/2010.14819
• EfficientViT (MIT) - https://arxiv.org/abs/2205.14756
• EfficientViT (MSRA) - https://arxiv.org/abs/2305.07027
• EVA - https://arxiv.org/abs/2211.07636
• EVA-02 - https://arxiv.org/abs/2303.11331
• FastViT - https://arxiv.org/abs/2303.14189
• FlexiViT - https://arxiv.org/abs/2212.08013
• FocalNet (Focal Modulation Networks) - https://arxiv.org/abs/2203.11926
• GCViT (Global Context Vision Transformer) - https://arxiv.org/abs/2206.09959
• GhostNet - https://arxiv.org/abs/1911.11907
• GhostNet-V2 - https://arxiv.org/abs/2211.12905
• gMLP - https://arxiv.org/abs/2105.08050
• GPU-Efficient Networks - https://arxiv.org/abs/2006.14090
• Halo Nets - https://arxiv.org/abs/2103.12731
• HGNet / HGNet-V2 - TBD
• HRNet - https://arxiv.org/abs/1908.07919
• InceptionNeXt - https://arxiv.org/abs/2303.16900
• Inception-V3 - https://arxiv.org/abs/1512.00567
• Inception-ResNet-V2 and Inception-V4 - https://arxiv.org/abs/1602.07261
• Lambda Networks - https://arxiv.org/abs/2102.08602
• LeViT (Vision Transformer in ConvNet's Clothing) - https://arxiv.org/abs/2104.01136
• MambaOut - https://arxiv.org/abs/2405.07992
• MaxViT (Multi-Axis Vision Transformer) - https://arxiv.org/abs/2204.01697
• MetaFormer (PoolFormer-v2, ConvFormer, CAFormer) - https://arxiv.org/abs/2210.13452
• MLP-Mixer - https://arxiv.org/abs/2105.01601
• MobileCLIP - https://arxiv.org/abs/2311.17049
• MobileNet-V3 (MBConvNet w/ Efficient Head) - https://arxiv.org/abs/1905.02244
  • FBNet-V3 - https://arxiv.org/abs/2006.02049
  • HardCoRe-NAS - https://arxiv.org/abs/2102.11646
  • LCNet - https://arxiv.org/abs/2109.15099
• MobileNetV4 - https://arxiv.org/abs/2404.10518
• MobileOne - https://arxiv.org/abs/2206.04040
• MobileViT - https://arxiv.org/abs/2110.02178
• MobileViT-V2 - https://arxiv.org/abs/2206.02680
• MViT-V2 (Improved Multiscale Vision Transformer) - https://arxiv.org/abs/2112.01526
• NASNet-A - https://arxiv.org/abs/1707.07012
• NesT - https://arxiv.org/abs/2105.12723
• Next-ViT - https://arxiv.org/abs/2207.05501
• NFNet-F - https://arxiv.org/abs/2102.06171
• NF-RegNet / NF-ResNet - https://arxiv.org/abs/2101.08692
• PNasNet - https://arxiv.org/abs/1712.00559
• PoolFormer (MetaFormer) - https://arxiv.org/abs/2111.11418
• Pooling-based Vision Transformer (PiT) - https://arxiv.org/abs/2103.16302
• PVT-V2 (Improved Pyramid Vision Transformer) - https://arxiv.org/abs/2106.13797
• RDNet (DenseNets Reloaded) - https://arxiv.org/abs/2403.19588
• RegNet - https://arxiv.org/abs/2003.13678
• RegNetZ - https://arxiv.org/abs/2103.06877
• RepVGG - https://arxiv.org/abs/2101.03697
• RepGhostNet - https://arxiv.org/abs/2211.06088
• RepViT - https://arxiv.org/abs/2307.09283
• ResMLP - https://arxiv.org/abs/2105.03404
• ResNet/ResNeXt
  • ResNet (v1b/v1.5) - https://arxiv.org/abs/1512.03385
  • ResNeXt - https://arxiv.org/abs/1611.05431
  • 'Bag of Tricks' / Gluon C, D, E, S variations - https://arxiv.org/abs/1812.01187
  • Weakly-supervised (WSL) Instagram pretrained / ImageNet tuned ResNeXt101 - https://arxiv.org/abs/1805.00932
  • Semi-supervised (SSL) / Semi-weakly Supervised (SWSL) ResNet/ResNeXts - https://arxiv.org/abs/1905.00546
  • ECA-Net (ECAResNet) - https://arxiv.org/abs/1910.03151v4
  • Squeeze-and-Excitation Networks (SEResNet) - https://arxiv.org/abs/1709.01507
  • ResNet-RS - https://arxiv.org/abs/2103.07579
• Res2Net - https://arxiv.org/abs/1904.01169
• ResNeSt - https://arxiv.org/abs/2004.08955
• ReXNet - https://arxiv.org/abs/2007.00992
• SelecSLS - https://arxiv.org/abs/1907.00837
• Selective Kernel Networks - https://arxiv.org/abs/1903.06586
• Sequencer2D - https://arxiv.org/abs/2205.01972
• SigLIP (image encoder) - https://arxiv.org/abs/2303.15343
• SigLIP 2 (image encoder) - https://arxiv.org/abs/2502.14786
• Swin S3 (AutoFormerV2) - https://arxiv.org/abs/2111.14725
• Swin Transformer - https://arxiv.org/abs/2103.14030
• Swin Transformer V2 - https://arxiv.org/abs/2111.09883
• Transformer-iN-Transformer (TNT) - https://arxiv.org/abs/2103.00112
• TResNet - https://arxiv.org/abs/2003.13630
• Twins (Spatial Attention in Vision Transformers) - https://arxiv.org/pdf/2104.13840.pdf
• Visformer - https://arxiv.org/abs/2104.12533
• Vision Transformer - https://arxiv.org/abs/2010.11929
• ViTamin - https://arxiv.org/abs/2404.02132
• VOLO (Vision Outlooker) - https://arxiv.org/abs/2106.13112
• VovNet V2 and V1 - https://arxiv.org/abs/1911.06667
• Xception - https://arxiv.org/abs/1610.02357
• Xception (Modified Aligned, Gluon) - https://arxiv.org/abs/1802.02611
• Xception (Modified Aligned, TF) - https://arxiv.org/abs/1802.02611
• XCiT (Cross-Covariance Image Transformers) - https://arxiv.org/abs/2106.09681

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://.com/juntang-zhuang/Adabelief-Optimizer - https://arxiv.org/abs/2010.07468
• adafactor adapted from FAIRSeq impl - https://arxiv.org/abs/1804.04235
• adafactorbv adapted from Big Vision - https://arxiv.org/abs/2106.04560
• adahessian by David Samuel - https://arxiv.org/abs/2006.00719
• adamp and sgdp by Naver ClovAI - https://arxiv.org/abs/2006.08217
• adan an implementation of Adan adapted from https://.com/sail-sg/Adan - https://arxiv.org/abs/2208.06677
• adopt ADOPT adapted from https://.com/iShohei220/adopt - https://arxiv.org/abs/2411.02853
• kron PSGD w/ Kronecker-factored preconditioner from https://.com/evanatyourservice/kron_torch - https://sites.google.com/site/lixilinx/home/psgd
• lamb an implementation of Lamb and LambC (w/ trust-clipping) cleaned up and modified to support use with XLA - https://arxiv.org/abs/1904.00962
• laprop optimizer from https://.com/Z-T-WANG/LaProp-Optimizer - https://arxiv.org/abs/2002.04839
• lars an implementation of LARS and LARC (w/ trust-clipping) - https://arxiv.org/abs/1708.03888
• lion and implementation of Lion adapted from https://.com/google/automl/tree/master/lion - https://arxiv.org/abs/2302.06675
• lookahead adapted from impl by Liam - https://arxiv.org/abs/1907.08610
• madgrad an implementation of MADGRAD adapted from https://.com/facebookresearch/madgrad - https://arxiv.org/abs/2101.11075
• mars MARS optimizer from https://.com/AGI-Arena/MARS - https://arxiv.org/abs/2411.10438
• nadam an implementation of Adam w/ Nesterov momentum
• nadamw an implementation of AdamW (Adam w/ decoupled weight-decay) w/ Nesterov momentum. A simplified impl based on https://.com/mlcommons/algorithmic-efficiency
• novograd by Masashi Kimura - https://arxiv.org/abs/1905.11286
• radam by Liyuan Liu - https://arxiv.org/abs/1908.03265
• rmsprop_tf adapted from PyTorch RMSProp by myself. Reproduces much improved Tensorflow RMSProp behaviour
• sgdw and implementation of SGD w/ decoupled weight-decay
• fused<name> optimizers by name with NVIDIA Apex installed
• bnb<name> optimizers by name with BitsAndBytes installed
• cadamw, clion, and more 'Cautious' optimizers from https://.com/kyleliang919/C-Optim - https://arxiv.org/abs/2411.16085
• adam, adamw, rmsprop, adadelta, adagrad, and sgd pass through to torch.optim implementations

• Random Erasing from Zhun Zhong - https://arxiv.org/abs/1708.04896)
• Mixup - https://arxiv.org/abs/1710.09412
• CutMix - https://arxiv.org/abs/1905.04899
• AutoAugment (https://arxiv.org/abs/1805.09501) and RandAugment (https://arxiv.org/abs/1909.13719) ImageNet configurations modeled after impl for EfficientNet training (https://.com/tensorflow/tpu/blob/master/models/official/efficientnet/autoaugment.py)
• AugMix w/ JSD loss, JSD w/ clean + augmented mixing support works with AutoAugment and RandAugment as well - https://arxiv.org/abs/1912.02781
• SplitBachNorm - allows splitting batch norm layers between clean and augmented (auxiliary batch norm) data

• DropPath aka "Stochastic Depth" - https://arxiv.org/abs/1603.09382
• DropBlock - https://arxiv.org/abs/1810.12890
• Blur Pooling - https://arxiv.org/abs/1904.11486

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:

• All models have a common default configuration interface and API for
  • accessing/changing the classifier - get_classifier and reset_classifier
  • doing a forward pass on just the features - forward_features (see documentation)
  • these makes it easy to write consistent network wrappers that work with any of the models
• All models support multi-scale feature map extraction (feature pyramids) via create_model (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 map channel counts, reduction level (stride) can be queried AFTER model creation via the .feature_info member
• All models have a consistent pretrained weight loader that adapts last linear if necessary, and from 3 to 1 channel input if desired
• High performance reference training, validation, and inference scripts that work in several process/GPU modes:
  • NVIDIA DDP w/ a single GPU per process, multiple processes with APEX present (AMP mixed-precision optional)
  • PyTorch DistributedDataParallel w/ multi-gpu, single process (AMP disabled as it crashes when enabled)
  • PyTorch w/ single GPU single process (AMP optional)
• A dynamic global pool implementation that allows selecting from average pooling, max pooling, average + max, or concat([average, max]) at model creation. All global pooling is adaptive average by default and compatible with pretrained weights.
• A 'Test Time Pool' wrapper that can wrap any of the included models and usually provides improved performance doing inference with input images larger than the training size. Idea adapted from original DPN implementation when I ported (https://.com/cypw/DPNs)
• Learning rate schedulers
  • Ideas adopted from
    • AllenNLP schedulers
    • FAIRseq lr_scheduler
    • SGDR: Stochastic Gradient Descent with Warm Restarts (https://arxiv.org/abs/1608.03983)
  • Schedulers include step, cosine w/ restarts, tanh w/ restarts, plateau
• Space-to-Depth by mrT23 (https://arxiv.org/abs/1801.04590) -- original paper?
• Adaptive Gradient Clipping (https://arxiv.org/abs/2102.06171, https://.com/deepmind/deepmind-research/tree/master/nfnets)
• An extensive selection of channel and/or spatial attention modules:
  • Bottleneck Transformer - https://arxiv.org/abs/2101.11605
  • CBAM - https://arxiv.org/abs/1807.06521
  • Effective Squeeze-Excitation (ESE) - https://arxiv.org/abs/1911.06667
  • Efficient Channel Attention (ECA) - https://arxiv.org/abs/1910.03151
  • Gather-Excite (GE) - https://arxiv.org/abs/1810.12348
  • Global Context (GC) - https://arxiv.org/abs/1904.11492
  • Halo - https://arxiv.org/abs/2103.12731
  • Involution - https://arxiv.org/abs/2103.06255
  • Lambda Layer - https://arxiv.org/abs/2102.08602
  • Non-Local (NL) - https://arxiv.org/abs/1711.07971
  • Squeeze-and-Excitation (SE) - https://arxiv.org/abs/1709.01507
  • Selective Kernel (SK) - (https://arxiv.org/abs/1903.06586
  • Split (SPLAT) - https://arxiv.org/abs/2004.08955
  • Shifted Window (SWIN) - https://arxiv.org/abs/2103.14030

Model 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.

• Detectron2 - https://.com/facebookresearch/detectron2
• Segmentation Models (Semantic) - https://.com/qubvel/segmentation_models.pytorch
• EfficientDet (Obj Det, Semantic soon) - https://.com/rwightman/efficientdet-pytorch

• Albumentations - https://.com/albumentations-team/albumentations
• Kornia - https://.com/kornia/kornia

• RepDistiller - https://.com/HobbitLong/RepDistiller
• torchdistill - https://.com/yoshitomo-matsubara/torchdistill

• PyTorch Metric Learning - https://.com/KevinMusgrave/pytorch-metric-learning

• fastai - https://.com/fastai/fastai
• lightly_train - https://.com/lightly-ai/lightly-train

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://.com/facebookresearch/semi-supervised-ImageNet1K-models, https://.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 = {},
  journal = { repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://.com/rwightman/pytorch-image-models}}
}