#55th of 9 in ML frameworks and libraries
pytorch-image-models
PyTorch library of image models, pretrained weights and reference training scripts
- Stars
- 37.2k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- Python
36,305 on 24 Mar 202637,215 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
timm is a Python library of image model architectures (ConvNeXt, EfficientNet, EVA, DINOv3, Swin and many more), most with pretrained weights, plus layers, optimizers, LR schedulers, data loaders and augmentations. It includes train.py, validate.py, inference.py and a sweep.py for hyperparameter search, aimed at reproducing ImageNet results. Recent work covers multi-label training, Muon-family optimizers and NaFlexViT variable-resolution models.
Who it is for: ML engineers training or fine-tuning image backbones in PyTorch
Strengths
- Very wide architecture coverage; every family has variants with pretrained weights
- Reference train, validate, inference and sweep scripts with YAML config and resume support
- Large optimizer and scheduler set, including Muon, LAMB, Kron and WSD
- Active: release 1.0.30 on 2026-09-22, commits through October 2026
Weaknesses
- Some model variants ship without pretrained weights
- Vision backbones only; no serving layer or UI
- Frequent behaviour changes: RoPE precision fixes alter low-precision model outputs
- Maintainer left Hugging Face; maintenance releases continue but project direction is less clear
What it needs
- GPU optional
- Needs PyTorch
- Models: PyTorch checkpoints, Hugging Face Hub weights, ONNX export
Also in ML frameworks and libraries
See all 9| Rank | Project | Score |
|---|---|---|
| 1 | transformersModel-definition library for text, vision, audio and multimodal models | 93 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 90 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 81 out of 100 |
| #4 | tensorflowTensor and neural network framework with Python and C++ APIs | 80 out of 100 |
| #6 | kerasMulti-backend deep learning library running on JAX, TensorFlow and PyTorch | 74 out of 100 |