算法部署 | 使用TensorRT在Jetson-Xavier-AGX上部署YOLOv4目标检测算法

• 项目应用场景

• • 面向 NVIDIA Jetson Xavier AGX 平台部署 YOLOv4 目标检测算法场景，项目采用 TensorRT 进行 GPU 算法加速推理。

• 项目效果

• 项目细节 ==> 具体参见项目 README.md

• • (1) 安装依赖

Install pycuda (takes awhile)
$ cd ${HOME}/catkin_ws/src/yolov4_trt_ros/dependencies
$ ./install_pycuda.sh
 
Install Protobuf (takes awhile)
$ cd ${HOME}/catkin_ws/src/yolov4_trt_ros/dependencies
$ ./install_protobuf-3.8.0.sh
 
Install onnx (depends on Protobuf above)
$ sudo pip3 install onnx==1.4.1

• • (2) 编译

$ cd ~/catkin_ws && catkin_make
$ source devel/setup.bash
 
$ cd ${HOME}/catkin_ws/src/yolov4_trt_ros/plugins
$ make

• • (3) 模型转换

$ ./convert_yolo_trt

• • (4) 执行推理

# For YOLOv3 (single input)
$ roslaunch yolov4_trt_ros yolov3_trt.launch
 
# For YOLOv4 (single input)
$ roslaunch yolov4_trt_ros yolov4_trt.launch
 
# For YOLOv4 (multiple input)
$ roslaunch yolov4_trt_ros yolov4_trt_batch.launch

• 项目获取

• • https://download.csdn.net/download/weixin_42405819/89110957