mxnet部署版本升级问题

在flask部署时，mxnet用cu101mkl-1.5.0 ，报错信息

[10:12:36] src/nnvm/legacy_json_util.cc:209: Loading symbol saved by previous version v1.2.0. Attempting to upgrade...
[10:12:36] src/nnvm/legacy_json_util.cc:217: Symbol successfully upgraded!

正常情况，升级完就完事，但是会一直重复此信息。

另外 最新的insightface 0.2.0 把retinaface移除了，换成了arcface人脸识别了，即无法用

detector = insightface.model_zoo.get_model('retinaface_mnet025_v2')

或者

insightface.model_zoo.face_detection.retinaface_mnet025_v2()

retinaface 安装

pip install retina-face

运用

from retinaface import RetinaFace
resp = RetinaFace.detect_faces("img1.jpg",align=False) # 默认不align
===>
{
    "face_1": {
        "score": 0.9993440508842468,
        "facial_area": [155, 81, 434, 443],
        "landmarks": {
          "right_eye": [257.82974, 209.64787],
          "left_eye": [374.93427, 251.78687],
          "nose": [303.4773, 299.91144],
          "mouth_right": [228.37329, 338.73193],
          "mouth_left": [320.21982, 374.58798]
        }
  }
}

arcface跟retinaface还封装在deepface中

pip install deepface

from deepface import DeepFace
obj = DeepFace.verify("img1.jpg", "img2.jpg"
          , model_name = 'ArcFace', detector_backend = 'retinaface')
print(obj["verified"])