MotionBert，AlphaPose环境配置教程(ubuntu版本)

MotionBert，AlphaPose环境配置教程(ubuntu版本)

使用MotionBert进行生成3D位姿，MotionBert依赖AlphaPose进行二维提取

Ubuntu Environment Setup

# 建立一个Conda环境
conda create -n PoseGenerate python=3.7
conda activate PoseGenerate

# 下载对应CUDA版本的torch环境
# conda install pytorch torchvision torchaudio pytorch-cuda=11.6 -c pytorch -c nvidia
conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -c nvidia

# 安装各种包，已整合
pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
    requirements.txt：
    tensorboardX
    tqdm
    easydict
    prettytable
    chumpy
    opencv-python
    imageio-ffmpeg
    matplotlib==3.1.1
    roma
    ipdb
    pytorch-metric-learning                         # For one-shot action recognition
    # smplx[all]                                      # For mesh recovery
    numpy
    Cythony
# 因为报错需要安装这个
pip install setuptools==57.5.0 -i https://pypi.tuna.tsinghua.edu.cn/simple, reported by one issue
# 又因为报错需要安装这个
pip install -e git+https://github.com/samson-wan