我正在使用python的人脸识别库,但识别一个人脸太慢了,我需要它来识别多个人脸。
我已经尝试过人脸识别库,这就是我所做的
import face_recognition
known_image = face_recognition.load_image_file("known.jpg")
unknown_image = face_recognition.load_image_file("unknown.jpg")
known_encoding = face_recognition.face_encodings(known_image)[0]
unknown_encoding = face_recognition.face_encodings(unknown_image)[0]
results = face_recognition.compare_faces([known_encoding], unknown_encoding)但是当我想为成千上万的人做这件事的时候会花很多时间,有没有更快的方法呢?或者我应该在gpu上运行它?
另外,线程会对性能产生影响吗?
发布于 2020-11-30 18:46:57
我推荐你使用deepface。它涵盖了基于Keras的人脸识别模型。我的实验表明,VGG-Face是构建最快的,但对所有模型的预测几乎是相同的。
#!pip install deepface
from deepface import DeepFace
models = ["VGG-Face", "Facenet", "OpenFace", "DeepFace", "DeepID"]
pairs = [
["img1.jpg", "img2.jpg"],
["img1.jpg", "img3.jpg"],
["img1.jpg", "img4.jpg"]
]
result = DeepFace.verify(pairs, model_name = models[0])https://stackoverflow.com/questions/65064886
复制相似问题