GStars
    huggingface

    huggingface/pytorch-image-models

    The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

    machine-learning
    augmix
    convnext
    distributed-training
    efficientnet
    image-classification
    imagenet
    maxvit
    mixnet
    mobile-deep-learning
    mobilenet-v2
    mobilenetv3
    nfnets
    normalization-free-training
    optimizer
    pretrained-models
    pretrained-weights
    pytorch
    randaugment
    resnet
    vision-transformer-models
    Python
    Apache-2.0
    36.1K stars
    5.1K forks
    36.1K watching
    Updated 2/27/2026
    View on GitHub
    Backblaze Advertisement

    Loading star history...

    Health Score

    75

    Weekly Growth

    +0

    +0.0% this week

    Contributors

    1

    Total contributors

    Open Issues

    71

    Generated Insights

    About pytorch-image-models

    PyTorch Image Models

    What's New

    Nov 4, 2025

    Oct 31, 2025 🎃

    • Update imagenet & OOD variant result csv files to include a few new models and verify correctness over several torch & timm versions
    • EfficientNet-X and EfficientNet-H B5 model weights added as part of a hparam search for AdamW vs Muon (still iterating on Muon runs)

    Oct 16-20, 2025

    • Add an impl of the Muon optimizer (based on https://github.com/KellerJordan/Muon) with customizations
      • extra flexibility and improved handling for conv weights and fallbacks for weight shapes not suited for orthogonalization
      • small speedup for NS iterations by reducing allocs and using fused (b)add(b)mm ops
      • by default uses AdamW (or NAdamW if nesterov=True) updates if muon not suitable for parameter shape (or excluded via param group flag)
      • like torch impl, select from several LR scale adjustment fns via adjust_lr_fn
      • select from several NS coefficient presets or specify your own via ns_coefficients
    • First 2 steps of 'meta' device model initialization supported
      • Fix several ops that were breaking creation under 'meta' device context
      • Add device & dtype factory kwarg support to all models and modules (anything inherting from nn.Module) in timm
    • License fields added to pretrained cfgs in code
    • Release 1.0.21

    Sept 21, 2025

    • Remap DINOv3 ViT weight tags from lvd_1689m -> lvd1689m to match (same for sat_493m -> sat493m)
    • Release 1.0.20

    Sept 17, 2025

    July 23, 2025

    • Add set_input_size() method to EVA models, used by OpenCLIP 3.0.0 to allow resizing for timm based encoder models.
    • Release 1.0.18, needed for PE-Core S & T models in OpenCLIP 3.0.0
    • Fix small typing issue that broke Python 3.9 compat. 1.0.19 patch release.

    July 21, 2025

    • ROPE support added to NaFlexViT. All models covered by the EVA base (eva.py) including EVA, EVA02, Meta PE ViT, timm SBB ViT w/ ROPE, and Naver ROPE-ViT can be now loaded in NaFlexViT when use_naflex=True passed at model creation time
    • More Meta PE ViT encoders added, including small/tiny variants, lang variants w/ tiling, and more spatial variants.
    • PatchDropout fixed with NaFlexViT and also w/ EVA models (regression after adding Naver ROPE-ViT)
    • Fix XY order with grid_indexing='xy', impacted non-square image use in 'xy' mode (only ROPE-ViT and PE impacted).

    July 7, 2025

    • MobileNet-v5 backbone tweaks for improved Google Gemma 3n behaviour (to pair with updated official weights)
      • Add stem bias (zero'd in updated weights, compat break with old weights)
      • GELU -> GELU (tanh approx). A minor change to be closer to JAX
    • Add two arguments to layer-decay support, a min scale clamp and 'no optimization' scale threshold
    • Add 'Fp32' LayerNorm, RMSNorm, SimpleNorm variants that can be enabled to force computation of norm in float32
    • Some typing, argument cleanup for norm, norm+act layers done with above
    • Support Naver ROPE-ViT (https://github.com/naver-ai/rope-vit) in eva.py, add RotaryEmbeddingMixed module for mixed mode, weights on HuggingFace Hub
    modelimg_sizetop1top5param_count
    vit_large_patch16_rope_mixed_ape_224.naver_in1k22484.8497.122304.4
    vit_large_patch16_rope_mixed_224.naver_in1k22484.82897.116304.2
    vit_large_patch16_rope_ape_224.naver_in1k22484.6597.154304.37
    vit_large_patch16_rope_224.naver_in1k22484.64897.122304.17
    vit_base_patch16_rope_mixed_ape_224.naver_in1k22483.89496.75486.59
    vit_base_patch16_rope_mixed_224.naver_in1k22483.80496.71286.44
    vit_base_patch16_rope_ape_224.naver_in1k22483.78296.6186.59
    vit_base_patch16_rope_224.naver_in1k22483.71896.67286.43
    vit_small_patch16_rope_224.naver_in1k22481.2395.02221.98
    vit_small_patch16_rope_mixed_224.naver_in1k22481.21695.02221.99
    vit_small_patch16_rope_ape_224.naver_in1k22481.00495.01622.06
    vit_small_patch16_rope_mixed_ape_224.naver_in1k22480.98694.97622.06
    • Some cleanup of ROPE modules, helpers, and FX tracing leaf registration
    • Preparing version 1.0.17 release

    June 26, 2025

    • MobileNetV5 backbone (w/ encoder only variant) for Gemma 3n image encoder
    • Version 1.0.16 released

    June 23, 2025

    • Add F.grid_sample based 2D and factorized pos embed resize to NaFlexViT. Faster when lots of different sizes (based on example by https://github.com/stas-sl).
    • Further speed up patch embed resample by replacing vmap with matmul (based on snippet by https://github.com/stas-sl).
    • Add 3 initial native aspect NaFlexViT checkpoints created while testing, ImageNet-1k and 3 different pos embed configs w/ same hparams.
    ModelTop-1 AccTop-5 AccParams (M)Eval Seq Len
    naflexvit_base_patch16_par_gap.e300_s576_in1k83.6796.4586.63576
    naflexvit_base_patch16_parfac_gap.e300_s576_in1k83.6396.4186.46576
    naflexvit_base_patch16_gap.e300_s576_in1k83.5096.4686.63576
    • Support gradient checkpointing for forward_intermediates and fix some checkpointing bugs. Thanks https://github.com/brianhou0208
    • Add 'corrected weight decay' (https://arxiv.org/abs/2506.02285) as option to AdamW (legacy), Adopt, Kron, Adafactor (BV), Lamb, LaProp, Lion, NadamW, RmsPropTF, SGDW optimizers
    • Switch PE (perception encoder) ViT models to use native timm weights instead of remapping on the fly
    • Fix cuda stream bug in prefetch loader

    June 5, 2025

    • 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 patch embedding on pre-patchified (dictionary) inputs
      3. Support for NaFlex variable aspect, variable resolution (SigLip-2: https://arxiv.org/abs/2502.14786)
      4. Support for FlexiViT variable patch 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_patch16_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_patch_interpolator=True --naflex-patch-sizes 12 16 24 will enable random patch 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

    May 28, 2025

    Feb 21, 2025

    • 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_patch16_reg1_gap_448.sbb_e200_in12k_ft_in1k - 88.1% top-1
      • vit_so150m2_patch16_reg1_gap_384.sbb_e200_in12k_ft_in1k - 87.9% top-1
      • vit_so150m2_patch16_reg1_gap_256.sbb_e200_in12k_ft_in1k - 87.3% top-1
      • vit_so150m2_patch16_reg4_gap_256.sbb_e200_in12k
    • Updated InternViT-300M '2.5' weights
    • Release 1.0.15

    Feb 1, 2025

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

    Jan 27, 2025

    Jan 19, 2025

    • 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_patch16_reg4_gap_256.sbb_e250_in12k_ft_in1k - 86.7% top-1
      • vit_so150m_patch16_reg4_gap_384.sbb_e250_in12k_ft_in1k - 87.4% top-1
      • vit_so150m_patch16_reg4_gap_256.sbb_e250_in12k
    • Misc typing, typo, etc. cleanup
    • 1.0.14 release to get above LeViT fix out

    Jan 9, 2025

    • Add support to train and validate in pure bfloat16 or float16
    • wandb project name arg added by https://github.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

    Jan 6, 2025

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

    Dec 31, 2024

    Nov 28, 2024

    Nov 12, 2024

    • 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://github.com/iShohei220/adopt) optimizer
    • Add 'Big Vision' variant of Adafactor (https://github.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 patch grids, thanks https://github.com/wojtke

    Oct 31, 2024

    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

    Oct 19, 2024

    • 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.

    Oct 16, 2024

    Oct 14, 2024

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

    Oct 11, 2024

    • MambaOut (https://github.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.
    modelimg_sizetop1top5param_count
    mambaout_base_plus_rw.sw_e150_r384_in12k_ft_in1k38487.50698.428101.66
    mambaout_base_plus_rw.sw_e150_in12k_ft_in1k28886.91298.236101.66
    mambaout_base_plus_rw.sw_e150_in12k_ft_in1k22486.63298.156101.66
    mambaout_base_tall_rw.sw_e500_in1k28884.97497.33286.48
    mambaout_base_wide_rw.sw_e500_in1k28884.96297.20894.45
    mambaout_base_short_rw.sw_e500_in1k28884.83297.2788.83
    mambaout_base.in1k28884.7296.9384.81
    mambaout_small_rw.sw_e450_in1k28884.59897.09848.5
    mambaout_small.in1k28884.596.97448.49
    mambaout_base_wide_rw.sw_e500_in1k22484.45496.86494.45
    mambaout_base_tall_rw.sw_e500_in1k22484.43496.95886.48
    mambaout_base_short_rw.sw_e500_in1k22484.36296.95288.83
    mambaout_base.in1k22484.16896.6884.81
    mambaout_small.in1k22484.08696.6348.49
    mambaout_small_rw.sw_e450_in1k22484.02496.75248.5
    mambaout_tiny.in1k28883.44896.53826.55
    mambaout_tiny.in1k22482.73696.126.55
    mambaout_kobe.in1k28881.05495.7189.14
    mambaout_kobe.in1k22479.98694.9869.14
    mambaout_femto.in1k28879.84895.147.3
    mambaout_femto.in1k22478.8794.4087.3

    Sept 2024

    Aug 21, 2024

    • Updated SBB ViT models trained on ImageNet-12k and fine-tuned on ImageNet-1k, challenging quite a number of much larger, slower models
    modeltop1top5param_countimg_size
    vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k87.43898.25664.11384
    vit_mediumd_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k86.60897.93464.11256
    vit_betwixt_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k86.59498.0260.4384
    vit_betwixt_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k85.73497.6160.4256
    • MobileNet-V1 1.25, EfficientNet-B1, & ResNet50-D weights w/ MNV4 baseline challenge recipe
    modeltop1top5param_countimg_size
    resnet50d.ra4_e3600_r224_in1k81.83895.92225.58288
    efficientnet_b1.ra4_e3600_r240_in1k81.44095.7007.79288
    resnet50d.ra4_e3600_r224_in1k80.95295.38425.58224
    efficientnet_b1.ra4_e3600_r240_in1k80.40695.1527.79240
    mobilenetv1_125.ra4_e3600_r224_in1k77.60093.8046.27256
    mobilenetv1_125.ra4_e3600_r224_in1k76.92493.2346.27224
    • Add SAM2 (HieraDet) backbone arch & weight loading support
    • Add Hiera Small weights trained w/ abswin pos embed on in12k & fine-tuned on 1k
    modeltop1top5param_count
    hiera_small_abswin_256.sbb2_e200_in12k_ft_in1k84.91297.26035.01
    hiera_small_abswin_256.sbb2_pd_e200_in12k_ft_in1k84.56097.10635.01

    Aug 8, 2024

    July 28, 2024

    • 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

    July 26, 2024

    • More MobileNet-v4 weights, ImageNet-12k pretrain w/ fine-tunes, and anti-aliased ConvLarge models
    modeltop1top1_errtop5top5_errparam_countimg_size
    mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k84.9915.0197.2942.70632.59544
    mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k84.77215.22897.3442.65632.59480
    mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k84.6415.3697.1142.88632.59448
    mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k84.31415.68697.1022.89832.59384
    mobilenetv4_conv_aa_large.e600_r384_in1k83.82416.17696.7343.26632.59480
    mobilenetv4_conv_aa_large.e600_r384_in1k83.24416.75696.3923.60832.59384
    mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k82.9917.0196.673.3311.07320
    mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k82.36417.63696.2563.74411.07256
    modeltop1top1_errtop5top5_errparam_countimg_size
    efficientnet_b0.ra4_e3600_r224_in1k79.36420.63694.7545.2465.29256
    efficientnet_b0.ra4_e3600_r224_in1k78.58421.41694.3385.6625.29224
    mobilenetv1_100h.ra4_e3600_r224_in1k76.59623.40493.2726.7285.28256
    mobilenetv1_100.ra4_e3600_r224_in1k76.09423.90693.0046.9964.23256
    mobilenetv1_100h.ra4_e3600_r224_in1k75.66224.33892.5047.4965.28224
    mobilenetv1_100.ra4_e3600_r224_in1k75.38224.61892.3127.6884.23224
    • Prototype of set_input_size() added to vit and swin v1/v2 models to allow changing image size, patch 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
    modeltop1top1_errtop5top5_errparam_countimg_sizecrop_pct
    test_efficientnet.r160_in1k47.15652.84471.72628.2740.361921.0
    test_byobnet.r160_in1k46.69853.30271.67428.3260.461921.0
    test_efficientnet.r160_in1k46.42653.57470.92829.0720.361600.875
    test_byobnet.r160_in1k45.37854.62270.57229.4280.461600.875
    test_vit.r160_in1k42.058.068.66431.3360.371921.0
    test_vit.r160_in1k40.82259.17867.21232.7880.371600.875
    • Fix vit reg token init, thanks Promisery
    • Other misc fixes

    June 24, 2024

    • 3 more MobileNetV4 hybrid weights with different MQA weight init scheme
    modeltop1top1_errtop5top5_errparam_countimg_size
    mobilenetv4_hybrid_large.ix_e600_r384_in1k84.35615.64496.8923.10837.76448
    mobilenetv4_hybrid_large.ix_e600_r384_in1k83.99016.01096.7023.29837.76384
    mobilenetv4_hybrid_medium.ix_e550_r384_in1k83.39416.60696.7603.24011.07448
    mobilenetv4_hybrid_medium.ix_e550_r384_in1k82.96817.03296.4743.52611.07384
    mobilenetv4_hybrid_medium.ix_e550_r256_in1k82.49217.50896.2783.72211.07320
    mobilenetv4_hybrid_medium.ix_e550_r256_in1k81.44618.55495.7044.29611.07256
    • florence2 weight loading in DaViT model

    June 12, 2024

    • MobileNetV4 models and initial set of timm trained weights added:
    modeltop1top1_errtop5top5_errparam_countimg_size
    mobilenetv4_hybrid_large.e600_r384_in1k84.26615.73496.9363.06437.76448
    mobilenetv4_hybrid_large.e600_r384_in1k83.80016.20096.7703.23037.76384
    mobilenetv4_conv_large.e600_r384_in1k83.39216.60896.6223.37832.59448
    mobilenetv4_conv_large.e600_r384_in1k82.95217.04896.2663.73432.59384
    mobilenetv4_conv_large.e500_r256_in1k82.67417.32696.313.6932.59320
    mobilenetv4_conv_large.e500_r256_in1k81.86218.13895.694.3132.59256
    mobilenetv4_hybrid_medium.e500_r224_in1k81.27618.72495.7424.25811.07256
    mobilenetv4_conv_medium.e500_r256_in1k80.85819.14295.7684.2329.72320
    mobilenetv4_hybrid_medium.e500_r224_in1k80.44219.55895.384.6211.07224
    mobilenetv4_conv_blur_medium.e500_r224_in1k80.14219.85895.2984.7029.72256
    mobilenetv4_conv_medium.e500_r256_in1k79.92820.07295.1844.8169.72256
    mobilenetv4_conv_medium.e500_r224_in1k79.80820.19295.1864.8149.72256
    mobilenetv4_conv_blur_medium.e500_r224_in1k79.43820.56294.9325.0689.72224
    mobilenetv4_conv_medium.e500_r224_in1k79.09420.90694.775.239.72224
    mobilenetv4_conv_small.e2400_r224_in1k74.61625.38492.0727.9283.77256
    mobilenetv4_conv_small.e1200_r224_in1k74.29225.70892.1167.8843.77256
    mobilenetv4_conv_small.e2400_r224_in1k73.75626.24491.4228.5783.77224
    mobilenetv4_conv_small.e1200_r224_in1k73.45426.54691.348.663.77224
    • 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.

    May 14, 2024

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

    May 11, 2024

    • Searching for Better ViT Baselines (For the GPU Poor) weights and vit variants released. Exploring model shapes between Tiny and Base.
    modeltop1top5param_countimg_size
    vit_mediumd_patch16_reg4_gap_256.sbb_in12k_ft_in1k86.20297.87464.11256
    vit_betwixt_patch16_reg4_gap_256.sbb_in12k_ft_in1k85.41897.4860.4256
    vit_mediumd_patch16_rope_reg1_gap_256.sbb_in1k84.32296.81263.95256
    vit_betwixt_patch16_rope_reg4_gap_256.sbb_in1k83.90696.68460.23256
    vit_base_patch16_rope_reg1_gap_256.sbb_in1k83.86696.6786.43256
    vit_medium_patch16_rope_reg1_gap_256.sbb_in1k83.8196.82438.74256
    vit_betwixt_patch16_reg4_gap_256.sbb_in1k83.70696.61660.4256
    vit_betwixt_patch16_reg1_gap_256.sbb_in1k83.62896.54460.4256
    vit_medium_patch16_reg4_gap_256.sbb_in1k83.4796.62238.88256
    vit_medium_patch16_reg1_gap_256.sbb_in1k83.46296.54838.88256
    vit_little_patch16_reg4_gap_256.sbb_in1k82.51496.26222.52256
    vit_wee_patch16_reg1_gap_256.sbb_in1k80.25695.36013.42256
    vit_pwee_patch16_reg1_gap_256.sbb_in1k80.07295.13615.25256
    vit_mediumd_patch16_reg4_gap_256.sbb_in12kN/AN/A64.11256
    vit_betwixt_patch16_reg4_gap_256.sbb_in12kN/AN/A60.4256
    • AttentionExtract helper added to extract attention maps from timm models. See example in https://github.com/huggingface/pytorch-image-models/discussions/1232#discussioncomment-9320949
    • 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.

    April 11, 2024

    • 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_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])
    • TinyCLIP vision tower weights added, thx Thien Tran

    Feb 19, 2024

    • Next-ViT models added. Adapted from https://github.com/bytedance/Next-ViT
    • HGNet and PP-HGNetV2 models added. Adapted from https://github.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

    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.

    Features

    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.

    Optimizers

    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:

    Augmentations

    Regularization

    Other

    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 results tables

    Getting Started (Documentation)

    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.

    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.

    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

    Discover Repositories

    Search across tracked repositories by name or description