跳到主要内容

YOLO环境搭建

YOLO环境搭建1、系统信息2、前期准备3、安装Ultralytics4、配置GPU加速4、验证安装常见报错Cannot uninstall sympy报错现象解决办法CSI摄像头无法调用验证环境参考资料

1、系统信息​

image-20250121150858152

2、前期准备​

sudo apt update sudo apt install python3-pip -y sudo pip install -U pip

3、安装Ultralytics​

xxxxxxxxxx sudo pip3 install ultralytics[export] xxxxxxxxxx sudo reboot

4、配置GPU加速​

由于我们前面教程已经安装torch 2.5.0和 torchvision 0.20，这里无需运行torch和torchvision安装命令，只需要将其它软件包进行安装。

torch

xxxxxxxxxx sudo pip3 install https://github.com/ultralytics/assets/releases/download/v0.0.0/torch-2.5.0a0+872d972e41.nv24.08-cp310-cp310-linux_aarch64.whl

torchvision

xxxxxxxxxx sudo pip3 install https://github.com/ultralytics/assets/releases/download/v0.0.0/torchvision-0.20.0a0+afc54f7-cp310-cp310-linux_aarch64.whl

cuSPARSELt

xxxxxxxxxx wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/arm64/cuda-keyring_1.1-1_all.deb sudo dpkg -i cuda-keyring_1.1-1_all.deb sudo apt-get update sudo apt-get -y install libcusparselt0 libcusparselt-dev

onnxruntime-gpu

xxxxxxxxxx sudo pip3 install https://github.com/ultralytics/assets/releases/download/v0.0.0/onnxruntime_gpu-1.20.0-cp310-cp310-linux_aarch64.whl

注意：使用onnxruntime-gpu需要安装numpy指定版本，若不是1.23.5，可以运行下面命令安装指定版本

xxxxxxxxxx sudo pip3 install numpy==1.23.5

4、验证安装​

验证Ultralytics

xxxxxxxxxx python3 -c "import ultralytics; print(ultralytics.__version__)"

验证Torch

xxxxxxxxxx python3 -c "import torch; print(torch.__version__); print(torch.cuda.is_available())"

验证Torchvision

xxxxxxxxxx python3 -c "import torchvision; print(torchvision.__version__)"

验证Numpy

xxxxxxxxxx python3 -c "import numpy; print(numpy.__version__)"

注意：ultralytics版本后期会更新，以系统内查询的版本信息为准

image-20241230112550391

常见报错​

Cannot uninstall sympy​

报错现象​

无法卸载sympy

image-20241230111303169

解决办法​

卸载python3-sympy：卸载完成后重新安装PyTorch

xxxxxxxxxx sudo apt remove python3-sympy -y

CSI摄像头无法调用​

源码编译OpenCV，开启GStreamer支持：基本整个过程自动安装，建议卸载旧版本安装新版本（脚本自动开启CUDA和GStreamer功能）

xxxxxxxxxx git clone https://github.com/AastaNV/JEP.git cd JEP/script bash install_opencv4.10.0_Jetpack6.1.sh

image-20250111110031036

image-20250111115337639

验证环境​

xxxxxxxxxx python3 -c "import cv2; print(cv2.getBuildInformation())" | grep GStreamer python3 -c "import ultralytics; print(ultralytics.__version__)" python3 -c "import torch; print(torch.__version__); print(torch.cuda.is_available())" python3 -c "import torchvision; print(torchvision.__version__)" python3 -c "import numpy; print(numpy.__version__)" jtop

image-20250111115433425

image-20250121215225996

参考资料​

https://docs.ultralytics.com/guides/nvidia-jetson/

https://github.com/AastaNV/JEP