mmdet
OpenMMLab Detection Toolbox and Benchmark
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- PyTorch 1.8+ must be installed separately; GPU support requires CUDA/cuDNN setup for efficient inference and training.
- Low install friction with a pure Python wheel.
- Depends on 8 common scientific libraries (numpy, scipy, matplotlib, pycocotools, shapely, terminaltables, tqdm, six).
License · maintenance · safety
Apache License 2.0 (permissive) — Apache License 2.0 (permissive) allows commercial and private use with minimal restrictions, requiring only license and copyright notice retention.
last release 2024-01-05 (952 days) · last repo commit 2024-08-21 · 32,876 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 629,226 downloads/mo, #5,667 on PyPI
Alternatives
Verify before relying
pip install mmdet
from mmdet.apis import DetInferencer
inferencer = DetInferencer(model='rtmdet_tiny')
inferencer(img='image.jpg', out_dir='results')- 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
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 on this page. Verify before relying on it.
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
mmdet on PyPI
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.
PyTorch 1.8+ must be installed separately; GPU support requires CUDA/cuDNN setup for efficient inference and training.
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')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 | Not specified |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 8 packagesmatplotlibnumpypycocotoolsscipyshapelysixterminaltablestqdm |
| Maintenance | Dormant 952 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 629,226 / month, #5,667 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.7Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9 |
Evidence: mmdet-3.3.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “object detection framework pytorch”
- mmdetMMDetection is an object detection and instance segmentation…
- icevisionIceVision provides a unified framework for training and deploying…
- ultralyticsUltralytics YOLO provides a unified framework for training and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also groundingdino-py · mmcv · mmengine · nuscenes-devkit · effdet · openmim · sahi · segmentation-models-pytorch · torchvision · rfdetr