English | 简体中文
This directory provides examples that infer.cc fast finishes the deployment of YOLOv5Face on CPU/GPU and GPU accelerated by TensorRT.
Before deployment, two steps require confirmation
-
- Software and hardware should meet the requirements. Please refer to FastDeploy Environment Requirements
-
- Download the precompiled deployment library and samples code according to your development environment. Refer to FastDeploy Precompiled Library
Taking the CPU inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
mkdir build
cd build
# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
# Download the official converted YOLOv5Face model files and test images
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s-face.onnx
wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
# CPU inference
./infer_demo yolov5s-face.onnx test_lite_face_detector_3.jpg 0
# GPU inference
./infer_demo yolov5s-face.onnx test_lite_face_detector_3.jpg 1
# TensorRT inference on GPU
./infer_demo yolov5s-face.onnx test_lite_face_detector_3.jpg 2The visualized result after running is as follows
The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
fastdeploy::vision::facedet::YOLOv5Face(
const string& model_file,
const string& params_file = "",
const RuntimeOption& runtime_option = RuntimeOption(),
const ModelFormat& model_format = ModelFormat::ONNX)YOLOv5Face model loading and initialization, among which model_file is the exported ONNX model format.
Parameters
- model_file(str): Model file path
- params_file(str): Parameter file path. Only passing an empty string 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
YOLOv5Face::Predict(cv::Mat* im, FaceDetectionResult* result, float conf_threshold = 0.25, float nms_iou_threshold = 0.5)Model prediction interface. Input images and output detection results.
Parameter
- im: Input images in HWC or BGR format
- result: Detection results, including detection box and confidence of each box. Refer to Vision Model Prediction Results for FaceDetectionResult
- conf_threshold: Filtering threshold of detection box confidence
- nms_iou_threshold: iou threshold during NMS processing
Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
- size(vector<int>): This parameter changes the size of the resize used during preprocessing, containing two integer elements for [width, height] with default value [640, 640]
- padding_value(vector<float>): This parameter is used to change the padding value of images during resize, containing three floating-point elements that represent the value of three channels. Default value [114, 114, 114]
- is_no_pad(bool): Specify whether to resize the image through padding or not.
is_no_pad=turerepresents no paddling. Defaultis_no_pad=false- is_mini_pad(bool): This parameter sets the width and height of the image after resize to the value nearest to the
sizemember variable and to the point where the padded pixel size is divisible by thestridemember variable. Defaultis_mini_pad=false- stride(int): Used with the
is_mini_padmember variable. Defaultstride=32- landmarks_per_face(int): Specify the number of keypoints in the face detected. Default 5.