Where does code be used to recognition in file detect_facese_real_time.py ?

[mactiendinh]

And Where does code be used Facenet algorithm to recognition in file detect_facese_real_time.py ? Does you use file detect_facese_real_time.py only detect ?
Thank you !!!

[habrman]

detect_facese_real_time.py does not exist. Assuming that you mean detect_and_align.py you have 3 questions:

1. The function align_image in detect_and_align.py finds faces and facial landmarks in an image.

2. I'm using Inception Resnet and not Facenet but the usage is the same so it doesn't really matter. It's not used in detect_and_align.py. Instead you use it by calling these lines:

feed_dict = {images_placeholder: face_patches, phase_train_placeholder: False}
embs = sess.run(embeddings, feed_dict=feed_dict)

The embeddings that come out can then be seen as multidimensional points. If 2 points are close to each other they correspond to the same person.

3. detect_facese_real_time.py is only used to detect faces and landmarks