This repository is an extension of the popular mmdetection open source repository for object detection training. While mmdetection focuses on a wide variety of models, typically at high complexity, we focus on models that are optimized for speed and accuracy so that they run efficiently on embedded devices.

Kindly take time to read through the documentation of the original mmdetection before attempting to use this repository.

Also, please read the documentation at our landing page jacinto-ai-devkit before using this repository. Please also read the documentation of pytorch-jacinto-ai-devkit and its quantization documentation for guidelines on how to get best accuracy with quantization.

The models trained with this repository can be inferred using TI Deep Learning Library (TIDL) that is part of the Processor SDK RTOS for Jacinto7. TIDL natively supports Post Training Quantization (PTQ) to quantize these models.

However, in case there is more than expected accuracy degradation with PTQ even after making sure that the guidelines are followed, this repository provides instructions and functionality required to do Quantization Aware Training (QAT).

This repository also provides a description of trained models with their accuracy and complexity. Recommendations on models friendly for embedded inference with quantization are also provided.


This repository requires mmdetection and mmcv to be installed.

Please refer to installation instructions for mmdetection for installation instructions. If you get any issues with the master branch of mmdetection, please try after checking out the latest release tag. After installation, a python package called "mmdet" will be listed if you do pip list

To install mmcv, browse to the github page of mmcv, and see the section that says "Install with pip". Install the full version of mmcv using the instruction given there. Please check your CUDA version and PyTorch version and select the appropriate installation instructions.

After installing mmdetection and mmcv, please clone and install PyTorch-Jacinto-AI-DevKit using the link given in jacinto-ai-devkit as this repository uses several components from there - especially to define low complexity models and to do Quantization Aware Training (QAT) or Calibration.

Please see our minimal installation script setup.sh and modify for your system.

Get Started

Please see Getting Started with MMDetection for the basic usage of mmdetection. Note: Some of these may not apply to this repository.

Please see Usage for training and testing with this repository.

Object Detection Model Zoo

Complexity and Accuracy report of several trained models is available at the Detection Model Zoo


This tutorial explains more about quantization and how to do Quantization Aware Training (QAT) of detection models.

ONNX & Prototxt Export

Export of ONNX model (.onnx) and additional meta information (.prototxt) is supported. The .prototxt contains meta information specified in TIDL for object detectors.

The export of meta information is now supported for SSD and RetinaNet detectors.

For more information please see Usage


This is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks.

We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to train existing detectors and also to develop their own new detectors.


This package/toolbox is an extension of mmdetection (https://github.com/open-mmlab/mmdetection). If you use this repository or benchmark in your research or work, please cite the following:

  title   = {{PyTorch-Jacinto-AI-Detection}: An Extension To Open MMLab Detection Toolbox and Benchmark},
  author  = {Jacinto AI Team, jacinto-ai-devkit@list.ti.com},
  journal = {https://github.com/TexasInstruments/jacinto-ai-devkit},
  title   = {{MMDetection}: Open MMLab Detection Toolbox and Benchmark},
  author  = {Chen, Kai and Wang, Jiaqi and Pang, Jiangmiao and Cao, Yuhang and
             Xiong, Yu and Li, Xiaoxiao and Sun, Shuyang and Feng, Wansen and
             Liu, Ziwei and Xu, Jiarui and Zhang, Zheng and Cheng, Dazhi and
             Zhu, Chenchen and Cheng, Tianheng and Zhao, Qijie and Li, Buyu and
             Lu, Xin and Zhu, Rui and Wu, Yue and Dai, Jifeng and Wang, Jingdong
             and Shi, Jianping and Ouyang, Wanli and Loy, Chen Change and Lin, Dahua},
  journal= {arXiv preprint arXiv:1906.07155},


Please see LICENSE file.


This extension of MMDetection is part of Jacinto-AI-DevKit and is maintained by the Jacinto AI team (jacinto-ai-devkit@list.ti.com). For more details, please visit: https://github.com/TexasInstruments/jacinto-ai-devkit


[1] MMDetection: Open MMLab Detection Toolbox and Benchmark, https://arxiv.org/abs/1906.07155, Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu, Zheng Zhang, Dazhi Cheng, Chenchen Zhu, Tianheng Cheng, Qijie Zhao, Buyu Li, Xin Lu, Rui Zhu, Yue Wu, Jifeng Dai, Jingdong Wang, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin