텐서 플로우 : Object Detection CoCo API / CoCo API 다운받기
coco API 란?
이미지나 비디오에 여러 사물/동물/사람을 학습을 통해 판단하는 인공지능을 말한다.
window 코드
pip install cython
pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI
리눅스 코드
git clone https://github.com/cocodataset/cocoapi.git
cd cocoapi/PythonAPI
make
cp -r pycocotools <PATH_TO_TF>/TensorFlow/models/research/
아래의 사이트는 다운로드하는 가이드라인 페이지 이다 꼭 참고하길 바란다.!!
https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/install.html
Installation — TensorFlow 2 Object Detection API tutorial documentation
Anaconda Python 3.8 (Optional) Although having Anaconda is not a requirement in order to install and use TensorFlow, I suggest doing so, due to it’s intuitive way of managing packages and setting up new virtual environments. Anaconda is a pretty useful t
tensorflow-object-detection-api-tutorial.readthedocs.io
Mac 으로 설치하는 경우 ------------------------
------------------------------------coco 관련 각종 사이트 --------------------------------------
https://cocodataset.org/#home
COCO - Common Objects in Context
cocodataset.org
CoCo API
https://github.com/cocodataset/cocoapi
GitHub - cocodataset/cocoapi: COCO API - Dataset @ http://cocodataset.org/
COCO API - Dataset @ http://cocodataset.org/ . Contribute to cocodataset/cocoapi development by creating an account on GitHub.
github.com
CoCo API 사용예제
https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoDemo.ipynb
GitHub - cocodataset/cocoapi: COCO API - Dataset @ http://cocodataset.org/
COCO API - Dataset @ http://cocodataset.org/ . Contribute to cocodataset/cocoapi development by creating an account on GitHub.
github.com
출처 :https://jjeamin.github.io/posts/coco_api/ (좋은 게시물 많으니 참고하면 좋겠다.)