python

English | 简体中文

YOLOv6 Quantification Model Python Deployment Example

This directory provides examples that infer.py fast finishes the deployment of YOLOv6 quantification models on CPU/GPU.

Prepare the deployment

FastDeploy Environment Preparation

• 1. Software and hardware should meet the requirements. Please refer to FastDeploy Environment Requirements
• 2. Install FastDeploy Python whl package. Refer to FastDeploy Python Installation

Prepare the quantification model

• 1. Users can directly deploy quantized models provided by FastDeploy.
• 2. ii. Or users can use the One-click auto-compression tool provided by FastDeploy to automatically conduct quantification model for deployment.

Example: quantized YOLOv6 model

# Download the example code for deployment
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/slim/yolov6/python

# Download yolov6 quantification model files and test images provided by FastDeploy
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s_qat_model_new.tar
tar -xvf yolov6s_qat_model.tar
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg

# Use ONNX Runtime quantification model on CPU
python infer.py --model yolov6s_qat_model --image 000000014439.jpg --device cpu --backend ort
# Use TensorRT quantification model on GPU
python infer.py --model yolov6s_qat_model --image 000000014439.jpg --device gpu --backend trt
# Use Paddle-TensorRT quantification model on GPU
python infer.py --model yolov6s_qat_model --image 000000014439.jpg --device gpu --backend pptrt