OpenPose Installation

 

https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/installation.md#prerequisites

 

1. 나의 환경 확인하기

Operating Systems

  • Windows 7, 8, 10  

 

2. 사양 확인하기

Requirements and Dependencies

CUDA (Nvidia GPU) version:

  • NVIDIA graphics card with at least 1.6 GB available (the nvidia-smi command checks the available GPU memory in Ubuntu).
  • At least 2.5 GB of free RAM memory for BODY_25 model or 2 GB for COCO model (assuming cuDNN installed).
  • Highly recommended: cuDNN.

OpenCL (AMD GPU) version:

  • Vega series graphics card
  • At least 2 GB of free RAM memory.

CPU-only (no GPU) version:

  • Around 8GB of free RAM memory.
  • Highly recommended: a CPU with at least 8 cores.

 

3. OpenPose 레포지토리 만들거나, 동기화하기 

Clone OpenPose

The first step is to clone the OpenPose repository.

  1. Windows: You might use GitHub Desktop.
  2. git clone https://github.com/CMU-Perceptual-Computing-Lab/openpose

오픈포즈와 clone해줄 폴더 생성후, synchronization

 

4. CMake, CUDA, cuDNN 설치

https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/prerequisites.md#windows-prerequisites

3rdparty는 clone한 openpose 폴더 안에 존재~ 이곳에서 3rdparty/windows/ 에 caffee들을 설치하면 된다. 

 

openpose 설치한 폴더를 다음과같이 설정해주고, build_windows는 내가 만들어도 되고, 없는데 configure누르면 만들까요? 라고 물어본다 .

경로 설정
설치되는 중 웅앵옹 10분정도 걸리는듯

 

설치는 했다만....

내 노트북은 가성비는 오지지만 GPU가 없는 노트북이라 결국 오픈포즈는 돌릴 수 없다는 것이 함정이다. 

 

BELATED ARTICLES

more