English | 简体中文
PaddleDetection 昆仑芯 XPU C++部署示例
本目录下提供infer.cc快速完成PPYOLOE模型包括PPYOLOE在昆仑芯 XPU加速部署的示例。
1. 说明
PaddleDetection支持利用FastDeploy在NVIDIA GPU、X86 CPU、飞腾CPU、ARM CPU、Intel GPU(独立显卡/集成显卡)硬件上快速部署PaddleDetection模型。FastDeploy目前支持的模型系列，包括但不限于PPYOLOE, PicoDet, PaddleYOLOX, PPYOLO, FasterRCNN，SSD,PaddleYOLOv5,PaddleYOLOv6,PaddleYOLOv7,RTMDet,CascadeRCNN,PSSDet,RetinaNet,PPYOLOESOD,FCOS,TTFNet,TOOD,GFL所有类名的构造函数和预测函数在参数上完全一致。所有模型的调用，只需要参考PPYOLOE的示例，即可快速调用。
2. 部署环境准备
在部署前，需自行编译基于昆仑芯XPU的预测库，参考文档昆仑芯XPU部署环境编译安装
3. 部署模型准备
在部署前，请准备好您所需要运行的推理模型，你可以选择使用预导出的推理模型或者自行导出PaddleDetection部署模型。
4. 运行部署示例
以Linux上推理为例，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1.0.4以上(x.x.x>=1.0.4)
4.1 目标检测示例
# 下载部署示例代码
git clone https://github.com/PaddlePaddle/PaddleDetection.git
cd PaddleDetection/deploy/fastdeploy/kunlunxin/cpp
# 注意：如果当前分支找不到下面的fastdeploy测试代码，请切换到develop分支
# git checkout develop
# 编译部署示例
mkdir build
cd build
# 使用编译完成的FastDeploy库编译infer_demo
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-kunlunxin
make -j
# 下载PPYOLOE模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
tar xvf ppyoloe_crn_l_300e_coco.tgz
# 运行部署示例
./infer_demo ./ppyoloe_crn_l_300e_coco 000000014439.jpg
运行完成可视化结果如下图所示
4.2 关键点检测示例
# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-x.x.x.tgz
tar xvf fastdeploy-linux-x64-gpu-x.x.x.tgz
# 下载部署示例代码
git clone https://github.com/PaddlePaddle/PaddleDetection.git
cd PaddleDetection/deploy/fastdeploy/kunlunxin/cpp
# 注意：如果当前分支找不到下面的fastdeploy测试代码，请切换到develop分支
# git checkout develop
# 编译部署示例
mkdir build && cd build
mv ../fastdeploy-linux-x64-gpu-x.x.x .
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-gpu-x.x.x
make -j
# 下载PP-TinyPose模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_256x192_infer.tgz
tar -xvf PP_TinyPose_256x192_infer.tgz
wget https://bj.bcebos.com/paddlehub/fastdeploy/hrnet_demo.jpg
# 运行部署示例
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.jpg
运行完成可视化结果如下图所示
关于如何进行多人关键点检测，请参考PPTinyPose Pipeline示例
- 关于如何通过FastDeploy使用更多不同的推理后端，以及如何使用不同的硬件，请参考文档：如何切换模型推理后端引擎
5. PaddleDetection C++接口
FastDeploy目前支持的模型系列，包括但不限于PPYOLOE, PicoDet, PaddleYOLOX, PPYOLO, FasterRCNN，SSD,PaddleYOLOv5,PaddleYOLOv6,PaddleYOLOv7,RTMDet,CascadeRCNN,PSSDet,RetinaNet,PPYOLOESOD,FCOS,TTFNet,TOOD,GFL所有类名的构造函数和预测函数在参数上完全一致。所有模型的调用，只需要参考PPYOLOE的示例，即可快速调用。
5.1 目标检测及实例分割模型
fastdeploy::vision::detection::PicoDet(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::SOLOv2(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::PPYOLOE(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::PPYOLO(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::YOLOv3(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::PaddleYOLOX(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::FasterRCNN(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::MaskRCNN(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::SSD(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::PaddleYOLOv5(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::PaddleYOLOv6(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::PaddleYOLOv7(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::PaddleYOLOv8(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::CascadeRCNN(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::PSSDet(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::RetinaNet(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::PPYOLOESOD(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::FCOS(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::TOOD(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
fastdeploy::vision::detection::GFL(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
5.2 关键点检测模型
fastdeploy::vision::keypointdetection::PPTinyPose(const string& model_file, const string& params_file, const string& config_file, const RuntimeOption& runtime_option = RuntimeOption(), const ModelFormat& model_format = ModelFormat::PADDLE);
PaddleDetection模型加载和初始化，其中model_file， params_file为导出的Paddle部署模型格式, config_file为PaddleDetection同时导出的部署配置yaml文件