--- id: mmdet version: "3.3.0" license: Apache License 2.0 license_treatment: permissive maintenance: dormant --- # mmdet — OpenMMLab Detection Toolbox and Benchmark License: permissive · Maintenance: dormant · Downloads: 629.2K/mo ## What it is and what it does MMDetection is a modular object detection framework built on PyTorch that decomposes detection pipelines into reusable components. It supports multiple detection tasks out of the box: object detection, instance segmentation, panoptic segmentation, and semi-supervised detection. The framework includes a model zoo with state-of-the-art architectures and tools for training on standard datasets, fine-tuning on custom data, and running inference. The package is designed for researchers and practitioners who need a flexible, production-ready detection pipeline. It depends on matplotlib, numpy, scipy, shapely, pycocotools, terminaltables, tqdm, and six. While maintenance is dormant (last release January 2024), the underlying repository remains active and the framework is stable and widely used in the computer vision community. Use it for: - Train a custom object detector on your own dataset using predefined architectures and transfer learning from pre-trained weights. - Run inference with pre-trained detection models from the model zoo to detect objects in images or video frames. - Implement instance segmentation to detect objects and generate pixel-level masks for each instance. - Benchmark detection architectures on standard datasets to compare performance. - Fine-tune a pre-trained detector for domain-specific tasks like rotated object detection or panoptic segmentation. - Build a semi-supervised detection pipeline when labeled data is limited. ## Worth the install? AI-flagged interpretation of the facts above — verify before relying. MMDetection is an object detection and instance segmentation framework built on PyTorch that provides modular, pre-trained detection models and tools for training and inference on custom datasets. Yes, if you need a mature, modular object detection framework with extensive model zoo and multi-task support. The permissive Apache 2.0 license and low install friction make it accessible. However, maintenance is dormant (last release 2024-01-05), so expect no new features or bug fixes—use it only if the current stable version meets your needs. ## Install pip install mmdet uv add mmdet poetry add mmdet ## Installing mmdet Before you install: Low install friction with a pure Python wheel. Depends on 8 common scientific libraries (numpy, scipy, matplotlib, pycocotools, shapely, terminaltables, tqdm, six). Maintenance is dormant—last release was 2024-01-05, though the repository remains active with recent commits. License in practice: Apache License 2.0 (permissive) allows commercial and private use with minimal restrictions, requiring only license and copyright notice retention. Quickstart: pip install mmdet from mmdet.apis import DetInferencer inferencer = DetInferencer(model='rtmdet_tiny') inferencer(img='image.jpg', out_dir='results') PyTorch 1.8+ must be installed separately; GPU support requires CUDA/cuDNN setup for efficient inference and training. Verify before relying: - Whether PyTorch 1.8+ requirement is enforced by the package or only documented - GPU acceleration support and whether CUDA/cuDNN dependencies are optional or required - Whether all model zoo pre-trained weights are freely available or some require registration ## Package facts - License: Apache License 2.0 (permissive) - Python support: unspecified - Install friction: low - Maintenance: dormant - Downloads: 629.2K/month (top 15,000 on PyPI) - Known vulnerabilities: none known ## Tags object detection framework pytorch, instance segmentation toolbox, pre-trained detection models, computer vision detection pipeline, detection model zoo, panoptic segmentation pytorch, rotated object detection, semi-supervised object detection, object-detection, instance-segmentation, pytorch [View on SkillFed](https://skillfed.io/packages/mmdet) · [View on PyPI](https://pypi.org/project/mmdet/)