当前位置:网站首页>一、AMD - OpenVINO环境配置
一、AMD - OpenVINO环境配置
2022-07-28 05:23:00 【Aaaaaki】
一、AMD - OpenVINO环境配置
1. 环境
| 硬件环境 | 软件环境 |
|---|---|
| Ryzen 5800X | Visual Studio 2022 |
| Win 10 | Python 3.7.13 + Cmake 3.24.0 + Anaconda |
依赖环境配置
Visual Studio 为 2022版本

CMake安装
官网下载最新版本CMake,建议选择msi安装,比较省事。
官网下载速度巨慢,建议去镜像

2. 离线下载OpenVINO-Toolkit
如图下载离线安装包

运行exe文件安装Toolkit组件,一路NEXT即可。


闪退问题
经测试,5800X + Win 10 环境下安装组件时会出现闪退问题,此情况为系统不兼容所致,需开启兼容模式

安装完成后,会自动弹出官网引导初始化界面,关闭即可。
3. Anaconda 安装OpenVINO
创建Anaconda虚拟环境,Python版本设置为3.7.13

运行命令安装OpenVINO,建议选择2021.4.2版本,最新版2022存在OpenCV问题。
pip install openvino-dev[pytorch]==2021.4.2
运行ie.available_device命令

4. PyCharm 配置OpenVINO
在PyCharm终端中切换至步骤3中创建的Anaconda虚拟环境

PyCharm中打开终端,进入步骤2中OpenVINO安装路径下运行setupvars.bat文件,弹出Python版本,以及OpenVINO environment initialized ,说明初始化OpenVINO成功

初始化完成后,终端运行face-detection.py,生成out.png后即可


目前OpenVINO存在问题,每次启动都需重新运行bat文件进行初始化后才能正常运行。
5. 加载OpenVINO踩坑
运行face-detection.py文件
python face-detection.py
若出现上述错误,可能是由于opencv没有cmake导致,可尝试下列命令解决
pip install opencv-python-inference-engine个人OpenCV版本:
anaconda 终端运行
pip list | findstr open*,结果如下图所示
若出现下述错误,是由于pip中OpenCV异常且未初始化OpenVINO导致,我自己是未离线安装OpenVINO Toolkit组件,直接在Anaconda envs环境中pip install openvino-dev会出现这种情况。此时重新运行OpenVINO.exe离线安装包,并初始化即可。我自己是未离线安装OpenVINO Toolkit组件,直接在Anaconda envs环境中pip install openvino-dev会出现这种情况。此时重新运行OpenVINO.exe离线安装包,并初始化即可

边栏推荐
- Marsnft: how do individuals distribute digital collections?
- Four perspectives to teach you to choose applet development tools?
- 深度学习(自监督:SimSiam)——Exploring Simple Siamese Representation Learning
- What are the advantages of small program development system? Why choose it?
- How to improve the efficiency of small program development?
- Scenario solution of distributed cluster architecture: cluster clock synchronization
- Deep learning (self supervision: CPC V2) -- data efficient image recognition with contractual predictive coding
- 强化学习——不完全观测问题、MCTS
- There is a problem with MySQL paging
- 用于快速低分辨率人脸识别模型训练的改进知识蒸馏《Improved Knowledge Distillation for Training Fast LR_FR》
猜你喜欢

深度学习(增量学习)——ICCV2021:SS-IL: Separated Softmax for Incremental Learning

UNL-类图

Why is the kotlin language not popular now? What's your opinion?

Pytorch deep learning single card training and multi card training

Four perspectives to teach you to choose applet development tools?

深度学习——Pay Attention to MLPs

深度学习(自监督:MoCo v2)——Improved Baselines with Momentum Contrastive Learning

无约束低分辨率人脸识别综述一:用于低分辨率人脸识别的数据集

微信小程序开发语言一般有哪些?

小程序开发流程详细是什么呢?
随机推荐
小程序搭建制作流程是怎样的?
Dataset class loads datasets in batches
self-attention学习笔记
深度学习(增量学习)——ICCV2022:Contrastive Continual Learning
word2vec和bert的基本使用方法
vscode uniapp
Deep learning (self supervised: Moco V3): An Empirical Study of training self supervised vision transformers
《On Low-Resolution Face Recognition in the Wild:Comparisons and New Techniques》低分辨率人脸识别论文解读
tf.keras搭建神经网络功能扩展
Reinforcement learning -- SARS in value learning
flutter webivew input唤起相机相册
Wechat applet development and production should pay attention to these key aspects
【2】 Redis basic commands and usage scenarios
D2SC-GAN:基于双深浅通道生成对抗网络的课堂场景低分辨率人脸识别
uniapp webview监听页面加载后回调
Solution to the crash after setting up a cluster
Deep learning (self supervision: CPC V2) -- data efficient image recognition with contractual predictive coding
What are the points for attention in the development and design of high-end atmospheric applets?
神经网络学习
What is the detail of the applet development process?