MMEditing: OpenMMLab image and video editing toolbox. MMFlow: OpenMMLab optical flow toolbox and benchmark. MMTracking: OpenMMLab video perception toolbox and benchmark. MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark. MMFewShot: OpenMMLab fewshot learning toolbox and benchmark. MMRazor: OpenMMLab model compression toolbox and benchmark. MMSelfSup: OpenMMLab self-supervised learning toolbox and benchmark. MMHuman3D: OpenMMLab 3D human parametric model toolbox and benchmark. MMPose: OpenMMLab pose estimation toolbox and benchmark. MMOCR: OpenMMLab text detection, recognition, and understanding toolbox. MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark. MMRotate: OpenMMLab rotated object detection toolbox and benchmark. MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection. MMDetection: OpenMMLab detection toolbox and benchmark. MMClassification: OpenMMLab image classification toolbox and benchmark. MMCV: OpenMMLab foundational library for computer vision. This project is released under the Apache 2.0 license. If you use this toolbox or benchmark in your research, please cite this = , 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 detectors. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks. MMDetection is an open source project that is contributed by researchers and engineers from various colleges and companies. Please refer to CONTRIBUTING.md for the contributing guideline. Welcome community users to participate in these projects. Ongoing projects can be found in out GitHub Projects. We appreciate all contributions to improve MMDetection. Please refer to FAQ for frequently asked questions. Some other methods are also supported in projects using MMDetection. Label Assignment Distillation (WACV'2022). Side-Aware Boundary Localization (ECCV'2020). Results and models are available in the model zoo. 
We provide colab tutorial and instance segmentation colab tutorial, and other tutorials for: Please see get_started.md for the basic usage of MMDetection. Please refer to Installation for installation instructions. Please refer to changelog.md for details and release history.įor compatibility changes between different versions of MMDetection, please refer to compatibility.md.
Support Mask2Former for instance segmentation. The toolbox stems from the codebase developed by the MMDet team, who won COCO Detection Challenge in 2018, and we keep pushing it forward.Īpart from MMDetection, we also released a library mmcv for computer vision research, which is heavily depended on by this toolbox. The training speed is faster than or comparable to other codebases, including Detectron2, maskrcnn-benchmark and SimpleDet. Faster RCNN, Mask RCNN, RetinaNet, etc.Īll basic bbox and mask operations run on GPUs. The toolbox directly supports popular and contemporary detection frameworks, e.g. 
Support of multiple frameworks out of box We decompose the detection framework into different components and one can easily construct a customized object detection framework by combining different modules. The master branch works with PyTorch 1.5+. MMDetection is an open source object detection toolbox based on PyTorch.
0 kommentar(er)
