# doods2

> Self-hosted REST API for object detection in images and video streams with TensorFlow, PyTorch, GPU and EdgeTPU support.

- **Category:** Computer Vision
- **Licence:** MIT
- **Latest version:** tf-v2.7.0-deps
- **Open source:** oss
- **Languages:** Python
- **Platforms:** Docker, Docker Compose
- **Tags:** Tensorflow, Pytorch, REST API, WebSocket, Mqtt, Gpu, Object Detection, Rtsp, Docker, Yolo, Computer vision, Edgetpu

## Description

DOODS2 (Dedicated Open Object Detection Service) is a Python rewrite of the original DOODS project that provides a REST API for object detection in images and video streams. It supports multiple detector backends including TensorFlow Lite, TensorFlow 1.x frozen graphs, PyTorch/YOLOv5, DeepStack, and Ultralytics YOLO models. The service can process single images via base64 or URL, and handle live video streams (RTSP, HTTP) with real-time detection feedback via MJPEG or WebSocket. It includes a simple web UI for testing, supports hardware acceleration via NVIDIA GPUs and Google Coral EdgeTPU, and offers an MQTT mode for asynchronous integration. Configuration is done via YAML file or environment variables. The project is distributed as multi-architecture Docker images (amd64, arm64, armv7) with GPU-enabled variants.

## Links

- [Homepage](https://github.com/snowzach/doods2)
- [Docker](snowzach/doods2)
- [GitHub Repository](https://github.com/snowzach/doods2)

---
Source: https://selfhost.directory/project/doods2