English | 简体中文

Before deployment, two steps require confirmation

• 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

This directory provides examples that infer.py fast finishes the deployment of FSANet on CPU/GPU and GPU accelerated by TensorRT. FastDeploy version 0.6.0 or above is required to support this model. The script is as follows

# Download deployment example code 
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/headpose/fsanet/python

# Download the FSANet model files and test images
## Original ONNX Model
wget https://bj.bcebos.com/paddlehub/fastdeploy/fsanet-var.onnx
wget https://bj.bcebos.com/paddlehub/fastdeploy/headpose_input.png
# CPU inference
python infer.py --model fsanet-var.onnx --image headpose_input.png --device cpu
# GPU inference
python infer.py --model fsanet-var.onnx --image headpose_input.png --device gpu
# TRT inference
python infer.py --model fsanet-var.onnx --image headpose_input.png --device gpu --backend trt

The visualized result after running is as follows

fd.vision.headpose.FSANet(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)

FSANet model loading and initialization, among which model_file is the exported ONNX model format

Parameter

• model_file(str): Model file path
• params_file(str): Parameter file path. No need to set when the model is in ONNX format
• runtime_option(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
• model_format(ModelFormat): Model format. ONNX format by default

FSANet.predict(input_image)

Model prediction interface. Input images and output head pose prediction results.

Parameter

• input_image(np.ndarray): Input data in HWC or BGR format Return

Return fastdeploy.vision.HeadPoseResult structure. Refer to Vision Model Prediction Results for the description of the structure

• FSANet Model Description
• FSANet C++ Deployment
• Model Prediction Results
• How to switch the model inference backend engine