English | 简体中文
PaddleDetection 昆仑芯 XPU Python部署示例
本目录下提供infer.py快速完成PPYOLOE模型在昆仑芯 XPU上的加速部署的示例。
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XPU的FastDeploy python wheel包并安装，参考文档昆仑芯XPU部署环境
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/python
# 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
# 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
# 昆仑芯推理
python infer.py --model_dir ppyoloe_crn_l_300e_coco --image_file 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
# 下载部署示例代码
git clone https://github.com/PaddlePaddle/PaddleDetection.git
cd PaddleDetection/deploy/fastdeploy/kunlunxin/python
# 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
# 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
python pptinypose_infer.py --model_dir PP_TinyPose_256x192_infer --image_file 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
5. 部署示例选项说明
| 参数 | 含义 | 默认值 |
|---|---|---|
| --model_dir | 指定模型文件夹所在的路径 | None |
| --image_file | 指定测试图片所在的路径 | None |
6. PaddleDetection Python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。
6.1 目标检测及实例分割模型
fastdeploy.vision.detection.PPYOLOE(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.PicoDet(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.PaddleYOLOX(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.YOLOv3(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.PPYOLO(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.FasterRCNN(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.MaskRCNN(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.SSD(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.PaddleYOLOv5(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.PaddleYOLOv6(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.PaddleYOLOv7(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.RTMDet(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.CascadeRCNN(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.PSSDet(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.RetinaNet(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.PPYOLOESOD(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.FCOS(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.TTFNet(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.TOOD(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
fastdeploy.vision.detection.GFL(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
6.2 关键点检测模型
fd.vision.keypointdetection.PPTinyPose(model_file, params_file, config_file, runtime_option=None, 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