📘 Documentation | 🛠️ Installation | 👀 Model Zoo | 🆕 Update News | 🤔 Reporting Issues
English | 简体中文
MMClassification is an open source image classification toolbox based on PyTorch. It is a part of the OpenMMLab project.
The master branch works with PyTorch 1.5+.
- Various backbones and pretrained models
- Bag of training tricks
- Large-scale training configs
- High efficiency and extensibility
- Powerful toolkits
v0.21.0 was released in 4/3/2022.
Highlights of the new version:
- Support ResNetV1c and Wide-ResNet, and provide pre-trained models.
- Support dynamic input shape for ViT-based algorithms. Now our ViT, DeiT, Swin-Transformer and T2T-ViT support forwarding with any input shape.
- Reproduce training results of DeiT. And our DeiT-T and DeiT-S have higher accuracy comparing with the official weights.
v0.20.0 was released in 30/1/2022.
Highlights of the new version:
- Support K-fold cross-validation. The tutorial will be released later.
- Support HRNet, ConvNeXt, Twins and EfficientNet.
- Support model conversion from PyTorch to Core ML by a tool.
Please refer to changelog.md for more details and other release history.
Please refer to install.md for installation and dataset preparation.
Please see Getting Started for the basic usage of MMClassification. There are also tutorials:
- Learn about Configs
- Fine-tune Models
- Add New Dataset
- Customizie Data Pipeline
- Add New Modules
- Customizie Schedule
- Customizie Runtime Settings
Colab tutorials are also provided:
- Learn about MMClassification Python API: Preview the notebook or directly run on Colab.
- Learn about MMClassification CLI tools: Preview the notebook or directly run on Colab.
Results and models are available in the model zoo.
Supported backbones
We appreciate all contributions to improve MMClassification. Please refer to CONTRUBUTING.md for the contributing guideline.
MMClassification is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new classifiers.
If you find this project useful in your research, please consider cite:
@misc{2020mmclassification,
title={OpenMMLab's Image Classification Toolbox and Benchmark},
author={MMClassification Contributors},
howpublished = {\url{https://github.com/open-mmlab/mmclassification}},
year={2020}
}This project is released under the Apache 2.0 license.
- MMCV: OpenMMLab foundational library for computer vision.
- MIM: MIM installs OpenMMLab packages.
- MMClassification: OpenMMLab image classification toolbox and benchmark.
- MMDetection: OpenMMLab detection toolbox and benchmark.
- MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
- MMRotate: OpenMMLab rotated object detection toolbox and benchmark.
- MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
- MMOCR: OpenMMLab text detection, recognition, and understanding toolbox.
- MMPose: OpenMMLab pose estimation toolbox and benchmark.
- MMHuman3D: OpenMMLab 3D human parametric model toolbox and benchmark.
- MMSelfSup: OpenMMLab self-supervised learning toolbox and benchmark.
- MMRazor: OpenMMLab model compression toolbox and benchmark.
- MMFewShot: OpenMMLab fewshot learning toolbox and benchmark.
- MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
- MMTracking: OpenMMLab video perception toolbox and benchmark.
- MMFlow: OpenMMLab optical flow toolbox and benchmark.
- MMEditing: OpenMMLab image and video editing toolbox.
- MMGeneration: OpenMMLab image and video generative models toolbox.
- MMDeploy: OpenMMLab model deployment framework.