mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 00:57:33 +08:00

* add onnx_ort_runtime demo * rm in requirements * support batch eval * fixed MattingResults bug * move assignment for DetectionResult * integrated x2paddle * add model convert readme * update readme * re-lint * add processor api * Add MattingResult Free * change valid_cpu_backends order * add ppocr benchmark * mv bs from 64 to 32 * fixed quantize.md * fixed quantize bugs * Add Monitor for benchmark * update mem monitor * Set trt_max_batch_size default 1 * fixed ocr benchmark bug * support yolov5 in serving * Fixed yolov5 serving * Fixed postprocess * update yolov5 to 7.0 * add poros runtime demos * update readme * Support poros abi=1 * rm useless note * deal with comments * support pp_trt for ppseg * fixed symlink problem * Add is_mini_pad and stride for yolov5 * Add yolo series for paddle format * fixed bugs * fixed bug * support yolov5seg * fixed bug * refactor yolov5seg * fixed bug * mv Mask int32 to uint8 * add yolov5seg example * rm log info * fixed code style * add yolov5seg example in python * fixed dtype bug * update note * deal with comments * get sorted index * add yolov5seg test case * Add GPL-3.0 License * add round func * deal with comments * deal with commens Co-authored-by: Jason <jiangjiajun@baidu.com>
3.0 KiB
3.0 KiB
YOLOv5Seg C++部署示例
本目录下提供infer.cc
快速完成YOLOv5Seg在CPU/GPU,以及GPU上通过TensorRT加速部署的示例。
在部署前,需确认以下两个步骤
-
- 软硬件环境满足要求,参考FastDeploy环境要求
-
- 根据开发环境,下载预编译部署库和samples代码,参考FastDeploy预编译库
以Linux上CPU推理为例,在本目录执行如下命令即可完成编译测试,支持此模型需保证FastDeploy版本1.0.3以上(x.x.x>=1.0.3)
mkdir build
cd build
# 下载 FastDeploy 预编译库,用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
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
# 1. 下载官方转换好的 YOLOv5Seg ONNX 模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s-seg.onnx
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
# CPU推理
./infer_demo yolov5s-seg.onnx 000000014439.jpg 0
# GPU推理
./infer_demo yolov5s-seg.onnx 000000014439.jpg 1
# GPU上TensorRT推理
./infer_demo yolov5s-seg.onnx 000000014439.jpg 2
运行完成可视化结果如下图所示

以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
YOLOv5Seg C++接口
YOLOv5Seg类
fastdeploy::vision::detection::YOLOv5Seg(
const string& model_file,
const string& params_file = "",
const RuntimeOption& runtime_option = RuntimeOption(),
const ModelFormat& model_format = ModelFormat::ONNX)
YOLOv5Seg模型加载和初始化,其中model_file为导出的ONNX模型格式。
参数
- model_file(str): 模型文件路径
- params_file(str): 参数文件路径,当模型格式为ONNX时,此参数传入空字符串即可
- runtime_option(RuntimeOption): 后端推理配置,默认为None,即采用默认配置
- model_format(ModelFormat): 模型格式,默认为ONNX格式
Predict函数
YOLOv5Seg::Predict(const cv::Mat& img, DetectionResult* result)
参数
- im: 输入图像,注意需为HWC,BGR格式
- result: 检测结果,包括检测框,各个框的置信度, DetectionResult说明参考视觉模型预测结果