I'm using this code to predict the score for each face in the image, but I can't understand the difference between vgg-face and resnet50 in the code.
def get_model_scores(detected_faces):
samples = asarray(detected_faces, 'float32')
# prepare the data for the model
samples = preprocess_input(samples, version=2)
# create a vggface model object
model = VGGFace(model='resnet50', include_top=False, input_shape=(224, 224, 3), pooling='avg')
# perform prediction
return model.predict(samples)
which one of them calculates the score? my output shape is a 2048 vector based on resnet50. thank you
