Ubuntu16+cuda10.1 下安装AlphePose人体姿态检测框架

最新推荐文章于 2025-09-20 04:32:05 发布

原创最新推荐文章于 2025-09-20 04:32:05 发布 · 657 阅读

3 ·

CC 4.0 BY-SA版权

文章标签：

#深度学习 #cuda #神经网络

人工智能专栏收录该内容

64 篇文章

订阅专栏

本文详细介绍AlphaPose人体姿态估计模型的安装与运行步骤，包括Anaconda环境搭建、CUDA及CUDNN配置、PyTorch安装、AlphaPose代码克隆与编译、模型下载以及视频与图片识别命令行参数说明。

部署运行你感兴趣的模型镜像

1.安装anaconda, 可参考网上的安装教程，这里不再赘述。

官网下载：https://www.anaconda.com/distribution/#download-section

2.安装显卡驱动和cuda-10.1+cudnn.,可以参考我之前博客

https://mp.youkuaiyun.com/console/editor/html/105434809

3.AlphePose代码安装:

# 1.1 Create a conda virtual environment.
conda create -n alphapose python=3.6 -y
conda activate alphapose

# 1.2 Install PyTorch 
conda install pytorch torchvision cudatoolkit=10.1 -c pytorch

# 1.3 Get AlphaPose
git clone https://github.com/MVIG-SJTU/AlphaPose.git
cd AlphaPose

# 1.4 install
export PATH=/usr/local/cuda/bin/:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda/lib64/:$LD_LIBRARY_PATH
python -m pip install cython
sudo apt-get install libyaml-dev
python setup.py build develop


Install with pip

# 1. Install PyTorch
pip install torch torchvision

# 2. Get AlphaPose
git clone https://github.com/MVIG-SJTU/AlphaPose.git
cd AlphaPose

# 3. install
export PATH=/usr/local/cuda/bin/:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda/lib64/:$LD_LIBRARY_PATH
pip install cython
sudo apt-get install libyaml-dev
python setup.py build develop --user

4.模型下载

4.1 Download the object detection model manually: yolov3-spp.weights(Google Drive | Baidu pan). Place it into detector/yolo/data.

4.2 For pose tracking, download the object tracking model manually: JDE-1088x608-uncertainty(Google Drive | Baidu pan). Place it into detector/tracker/data.

4.3 Download our pose models. Place them into pretrained_models. All models and details are available in our Model Zoo.

只是测试识别的话可以不用下载4.2的模型

5.运行

识别视频

python scripts/demo_inference.py --cfg configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml --checkpoint pretrained_models/fast_res50_256x192.pth --video AlphaPose_video.avi  --outdir examples/res  --detector yolo  --save_img --save_video

识别图片

python scripts/demo_inference.py --cfg configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml --checkpoint pretrained_models/fast_res50_256x192.pth --indir examples/demo/

您可能感兴趣的与本文相关的镜像