[6] dataset 만들기-1 retinaFace 함수알아보기

• https://ichi.pro/ko/opencv-dlibleul-sayonghan-anmyeon-maseukeu-obeolei-85300355583053
• 학습시킬 이미지들에 대한 주석들
• 주석 형식
  • [class_id] [center_x] [center_y] [w] [h]
    • 3 0.256 0.326 0.345 .643
    • 34 0.234 0.555 0.115 0.472
  • 각 이미지 마다 주석들이 담긴 텍스트 파일 필요
    • 0000001.txt
    • 0000002.txt
    • ...

OpenCV-dlib를 사용한 안면 마스크 오버레이

(읭 이런것도있다:Yolo mark 프로그램- Darknet - YOLO 데이타셋 만들기 http://ngmsoftware.com/bbs/board.php?bo_table=study&wr_id=34&sca=%EB%94%A5%EB%9F%AC%EB%8B%9D)

엔지엠소프트웨어

1. RetinaFace :

https://www.youtube.com/watch?v=Wm1DucuQk70 

1. 문제1 ModuleNotFoundError: No module named 'retinaface'
   • setting.json 수정

{
    "workbench.colorTheme": "Default High Contrast",
    "workbench.editor.enablePreview": false,
    "python.defaultInterpreterPath": "C:\\Users\\joj10\\anaconda3\\envs\\apple\\python.exe",
    "python.autoComplete.extraPaths": [
        "C:/Users/joj10/anaconda3/envs/apple/Lib/",
        "C:/Users/joj10/anaconda3/envs/apple/Lib/site-packages",
        "C:/Users/joj10/anaconda3/Lib/",
        "C:/Users/joj10/anaconda3/Lib/site-packages"
    ],
    "python.analysis.extraPaths": [
        "C:/Users/joj10/anaconda3/envs/apple/Lib/",
        "C:/Users/joj10/anaconda3/envs/apple/Lib/site-packages",
        "C:/Users/joj10/anaconda3/Lib/",
        "C:/Users/joj10/anaconda3/Lib/site-packages"
    ]

}

안됨

(apple) C:\Users\joj10\anaconda3\envs\apple\Scripts>pip install retina-face
Requirement already satisfied: retina-face in c:\users\joj10\anaconda3\envs\apple\lib\site-packages (0.0.10)

깔렸다는데 왜안됨

 

print(sys.path)
#sys.path.append('c:/users/joj10/anaconda3/envs/apple/lib/site-packages')

• launch.json 파일에 환경변수 추가해도 안됨
• 시스템 환경변수설정에도 다 들어가있으나 안됨
• 애초에 sys.path에 가상환경이 미포함돼있음
• 환경변수에 apple DLL도 추가, (기본, Lib, DLLs)

 

• 아예 아나콘다 새로하나 생성해서새로하기
  • pip -V했을때 

pip 21.2.4 from C:\Users\joj10\anaconda3\envs\apple\lib\site-packages\pip (python 3.9) 이렇게 뜸

• 아래 참고하여 저기다가 설치 

$ pip install --target=<conda 경로> <패키지명>

[출처] pip 설치 경로 바꾸기|

pip install --target=C:\Users\joj10\anaconda3\envs\python36\lib\site-packages retina-face

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
tensorflow-gpu 2.6.0 requires absl-py~=0.10, but you have absl-py 1.0.0 which is incompatible.
tensorflow-gpu 2.6.0 requires flatbuffers~=1.12.0, but you have flatbuffers 2.0 which is incompatible.
tensorflow-gpu 2.6.0 requires gast==0.4.0, but you have gast 0.5.3 which is incompatible.
tensorflow-gpu 2.6.0 requires h5py~=3.1.0, but you have h5py 3.6.0 which is incompatible.
tensorflow-gpu 2.6.0 requires numpy~=1.19.2, but you have numpy 1.22.3 which is incompatible.
tensorflow-gpu 2.6.0 requires six~=1.15.0, but you have six 1.16.0 which is incompatible.
tensorflow-gpu 2.6.0 requires typing-extensions~=3.7.4, but you have typing-extensions 4.1.1 which is incompatible.
tensorflow-gpu 2.6.0 requires wrapt~=1.12.1, but you have wrapt 1.14.0 which is incompatible.

jupyter-server 1.13.5 requires pywinpty<2; os_name == "nt", but you have pywinpty 2.0.2 which is incompatible.
Successfully installed Pillow-9.0.1 PySocks-1.7.1 absl-py-1.0.0 astunparse-1.6.3 beautifulsoup4-4.10.0 cachetools-5.0.0 certifi-2021.10.8 charset-normalizer-2.0.12 colorama-0.4.4 filelock-3.6.0 flatbuffers-2.0 gast-0.5.3 gdown-4.4.0 google-auth-2.6.2 google-auth-oauthlib-0.4.6 google-pasta-0.2.0 grpcio-1.44.0 h5py-3.6.0 idna-3.3 importlib-metadata-4.11.3 keras-2.8.0 keras-preprocessing-1.1.2 libclang-13.0.0 markdown-3.3.6 numpy-1.22.3 oauthlib-3.2.0 opencv-python-4.5.5.64 opt-einsum-3.3.0 protobuf-3.19.4 pyasn1-0.4.8 pyasn1-modules-0.2.8 requests-2.27.1 requests-oauthlib-1.3.1 retina-face-0.0.10 rsa-4.8 setuptools-61.2.0 six-1.16.0 soupsieve-2.3.1 tensorboard-2.8.0 tensorboard-data-server-0.6.1 tensorboard-plugin-wit-1.8.1 tensorflow-2.8.0 tensorflow-io-gcs-filesystem-0.24.0 termcolor-1.1.0 tf-estimator-nightly-2.8.0.dev2021122109 tqdm-4.63.1 
typing-extensions-4.1.1 urllib3-1.26.9 werkzeug-2.1.0 wheel-0.37.1 wrapt-1.14.0 zipp-3.7.0

WARNING: Target directory C:\Users\joj10\anaconda3\envs\python36\lib\site-packages\certifi already exists. Specify --upgrade to force replacement.
WARNING: Target directory C:\Users\joj10\anaconda3\envs\python36\lib\site-packages\distutils-precedence.pth already exists. Specify --upgrade to force replacement.
WARNING: Target directory C:\Users\joj10\anaconda3\envs\python36\lib\site-packages\pkg_resources already exists. Specify --upgrade to force replacement.
WARNING: Target directory C:\Users\joj10\anaconda3\envs\python36\lib\site-packages\setuptools already exists. Specify --upgrade to force replacement.
WARNING: Target directory C:\Users\joj10\anaconda3\envs\python36\lib\site-packages\wheel already exists. Specify --upgrade to force replacement.
WARNING: Target directory C:\Users\joj10\anaconda3\envs\python36\lib\site-packages\_distutils_hack already exists. Specify --upgrade to force replacement.
WARNING: Target directory C:\Users\joj10\anaconda3\envs\python36\lib\site-packages\__pycache__ already exists. Specify --upgrade to force replacement.

 

어짜고저짜고 뭐많이깔더만 저에러가 뜸

 

>> 아나콘다 다시깔고 파이참으로 하니 어찌저찌 실행은 된다ㅠㅠㅠ뭔가 vscode설정할때 문제가있었던듯ㅇㅇ

 

 

• extract_face 는 이렇게나오고

import matplotlib.pyplot as plt
from retinaface import RetinaFace

#print(os.getcwd())

img_path = "/dataset/dataTest/test1.jpg"

faces = RetinaFace.extract_faces(img_path= img_path, align= True)
for face in faces:
    plt.imshow(face)
    plt.show()

• bb처리하기
•  

import cv2
import matplotlib.pyplot as plt
from retinaface import RetinaFace

#print(os.getcwd())

img_path = "/dataset/dataTest/ori/test1.jpg"
img = cv2.imread(img_path)
obj = RetinaFace.detect_faces(img_path)

#len(obj.keys()) >> 사진에 얼굴수대로 나옴. 한명이라 face_1

for key in obj.keys():
    identity = obj[key]
    print(identity)

    facial_area = identity['facial_area']

    #cv2.rectangle(img, pt1(x,y:시작점), pt2(x,y:종료점), color, thickness)
    cv2.rectangle(img, (facial_area[2], facial_area[3]),(facial_area[0], facial_area[1]),(255, 255, 255), 1)

plt.figure(figsize = (20, 20))
plt.imshow(img[:,:,: :-1])
plt.show()

• face recognition

from deepface import DeepFace

img_path = "/dataset/dataTest/ori/test1.jpg"

# face recognition
# 사진두개 너혹, 결과돌리면 obj['verified']값이 true or false 나올거
obj = DeepFace.verify(img1_path=img_path, img2_path='img2.jpg', model_name='ArcFace', detector_backend='retinaface')

 

 

2. insightFace

Traceback (most recent call last):

  File "c:\insightFace\insightTest.py", line 3, in <module>

    import insightface

  File "C:\Users\joj10\anaconda3\lib\site-packages\insightface\__init__.py", line 10, in <module>

    raise ImportError(

ImportError: Unable to import dependency onnxruntime.

여기저기 오류뜨고 난리남