YOLOv9 with Quantization-Aware Training (QAT) for TensorRT

https://github.com/levipereira/yolov9-qat/
This repository hosts an implementation of YOLOv9 integrated with Quantization-Aware Training (QAT), optimized for deployment on TensorRT-supported platforms to achieve hardware-accelerated inference. It aims to deliver an efficient, low-latency version of YOLOv9 for real-time object detection applications. If you're not planning to deploy your model using TensorRT, it's advisable not to proceed with this implementation.

Implementation Details:

• The repository provides a patch that adds QAT functionality to the original YOLOv9 codebase.
• The patch is designed to be applied to the main YOLOv9 repository, enabling training with QAT.
• This implementation is finely tuned for TensorRT, a hardware-accelerated inference library, enhancing performance.
• Users interested in object detection using YOLOv9 with QAT on TensorRT platforms can leverage this repository, offering a ready-to-use solution.

Perfomance Report

@WongKinYiu I've successfully created a comprehensive implementation of Quantization in a separate repository. It works as a patch for the original YOLOv9 version. However, there are still some challenges to address as the implementation is functional but has room for improvement.

I'm closing the issue #253 and will continue the discussion in this thread. If possible, please replace the reference to issue #253 with this new issue #327 in the Useful Links section.

I'll provide the latency reports shortly.