Clarifai/mmdetection

Clarifai/mmdetection

Description: Clarifai's Fork of OpenMMLab Detection Toolbox and Benchmark

Language: Python

License: Apache-2.0

Stars: 0

Forks: 0

Open issues: 0

Created: 2022-05-09T19:04:26Z

Pushed: 2024-09-27T15:55:24Z

Default branch: master

Fork: yes

Parent repository: open-mmlab/mmdetection

Archived: no

README:

   

📘Documentation | 🛠️Installation | 👀Model Zoo | 🆕Update News | 🚀Ongoing Projects | 🤔Reporting Issues

Introduction

MMDetection is an open source object detection toolbox based on PyTorch. It is a part of the OpenMMLab project.

The master branch works with PyTorch 1.5+.

Major features

• Modular Design

We decompose the detection framework into different components and one can easily construct a customized object detection framework by combining different modules.

• Support of multiple frameworks out of box

The toolbox directly supports popular and contemporary detection frameworks, *e.g.* Faster RCNN, Mask RCNN, RetinaNet, etc.

• High efficiency

All basic bbox and mask operations run on GPUs. The training speed is faster than or comparable to other codebases, including Detectron2, maskrcnn-benchmark and SimpleDet.

• State of the art

The toolbox stems from the codebase developed by the *MMDet* team, who won COCO Detection Challenge in 2018, and we keep pushing it forward.

Apart from MMDetection, we also released a library mmcv for computer vision research, which is heavily depended on by this toolbox.

What's New

💎 Stable version

2.28.2 was released in 27/2/2023:

• Fixed some known documentation, configuration and linking error issues

Please refer to [changelog.md](docs/en/changelog.md) for details and release history.

For compatibility changes between different versions of MMDetection, please refer to [compatibility.md](docs/en/compatibility.md).

🌟 Preview of 3.x version

Highlight

We are excited to announce our latest work on real-time object recognition tasks, RTMDet, a family of fully convolutional single-stage detectors. RTMDet not only achieves the best parameter-accuracy trade-off on object detection from tiny to extra-large model sizes but also obtains new state-of-the-art performance on instance segmentation and rotated object detection tasks. Details can be found in the technical report. Pre-trained models are here.

| Task | Dataset | AP | FPS(TRT FP16 BS1 3090) | | ------------------------ | ------- | ------------------------------------ | ---------------------- | | Object Detection | COCO | 52.8 | 322 | | Instance Segmentation | COCO | 44.6 | 188 | | Rotated Object Detection | DOTA | 78.9(single-scale)/81.3(multi-scale) | 121 |

A brand new version of MMDetection v3.0.0rc6 was released in 27/2/2023:

• Support Boxinst, Objects365 Dataset, and Separated and Occluded COCO metric
• Support ConvNeXt-V2, DiffusionDet, and inference of EfficientDet and Detic in Projects
• Refactor DETR series and support Conditional-DETR, DAB-DETR, and DINO
• Support DetInferencer, Test Time Augmentation, and auto import modules from registry
• Support RTMDet-Ins ONNXRuntime and TensorRT deployment
• Support calculating FLOPs of detectors

Find more new features in 3.x branch. Issues and PRs are welcome!

Installation

Please refer to [Installation](docs/en/get_started.md/#Installation) for installation instructions.

Getting Started

Please see [get_started.md](docs/en/get_started.md) for the basic usage of MMDetection. We provide [colab tutorial](demo/MMDet_Tutorial.ipynb) and [instance segmentation colab tutorial](demo/MMDet_InstanceSeg_Tutorial.ipynb), and other tutorials for:

• [with existing dataset](docs/en/1_exist_data_model.md)
• [with new dataset](docs/en/2_new_data_model.md)
• [with existing dataset_new_model](docs/en/3_exist_data_new_model.md)
• [learn about configs](docs/en/tutorials/config.md)
• [customize_datasets](docs/en/tutorials/customize_dataset.md)
• [customize data pipelines](docs/en/tutorials/data_pipeline.md)
• [customize_models](docs/en/tutorials/customize_models.md)
• [customize runtime…