人脸识别可以分为两个方向,人脸识别(1:1),人脸验证(1:n):
“如下网络,一个放入基准照片,另一个放入测试照片,然后将两者的f(x),即encoding传入逻辑回归网络,做二分类的判断。实际操作中,基准照片的encoding可以事先准备好,来节省计算开销。例如有1000个员工,只需要用测试员工照片得到encoding值,然后依次和这1000个encoding值做对比。”
from keras.models import Sequential
from keras.layers import Conv2D, ZeroPadding2D, Activation, Input, concatenate
from keras.models import Model
from keras.layers.normalization import BatchNormalization
from keras.layers.pooling import MaxPooling2D, AveragePooling2D
from keras.layers.merge import Concatenate
from keras.layers.core import Lambda, Flatten, Dense
from keras.initializers import glorot_uniform
from keras.engine.topology import Layer
from keras import backend as K
K.set_image_data_format('channels_first')
import cv2
import os
import numpy as np
from numpy import genfromtxt
import pandas as pd
import tensorflow as tf
from fr_utils import *
from inception_blocks import *
# %matplotlib inline
# %load_ext autoreload
# %autoreload 2
import datetime
np.set_printoptions(threshold=np.nan)
# GRADED FUNCTION: triplet_loss
def triplet_loss(y_true, y_pred, alpha=0.2):
"""
Implementation of the triplet loss as defined by formula (3)
Arguments:
y_true -- true labels, required when you define a loss in Keras, you don't need it in this function.
y_pred -- python list containing three objects:
anchor -- the encodings for the anchor images, of shape (None, 128)
positive -- the encodings for the positive images, of shape (None, 128)
negative -- the encodings for the negative images, of shape (None, 128)
Returns:
loss -- real number, value of the loss
"""
anchor, positive, negative = y_pred[0], y_pred[1], y_pred[2]
### START CODE HERE ### (≈ 4 lines)
# Step 1: Compute the (encoding) distance between the anchor and the positive
pos_dist = tf.reduce_sum(tf.square(tf.subtract(anchor, positive)))
# Step 2: Compute the (encoding) distance between the anchor and the negative
neg_dist = tf.reduce_sum(tf.square(tf.subtract(anchor, negative)))
# Step 3: subtract the two previous distances and add alpha.
basic_loss = tf.add(tf.subtract(pos_dist, neg_dist), alpha)
# Step 4: Take the maximum of basic_loss and 0.0. Sum over the training examples.
loss = tf.reduce_sum(tf.maximum(basic_loss, 0))
### END CODE HERE ###
return loss
# GRADED FUNCTION: verify
def verify(image_path, identity, database, model):
"""
Function that verifies if the person on the "image_path" image is "identity".
Arguments:
image_path -- path to an image
identity -- string, name of the person you'd like to verify the identity. Has to be a resident of the Happy house.
database -- python dictionary mapping names of allowed people's names (strings) to their encodings (vectors).
model -- your Inception model instance in Keras
Returns:
dist -- distance between the image_path and the image of "identity" in the database.
door_open -- True, if the door should open. False otherwise.
"""
### START CODE HERE ###
# Step 1: Compute the encoding for the image. Use img_to_encoding() see example above. (≈ 1 line)
encoding = img_to_encoding(image_path, model)
# Step 2: Compute distance with identity's image (≈ 1 line)
dist = np.linalg.norm(encoding-database[identity])
# Step 3: Open the door if dist < 0.7, else don't open (≈ 3 lines)
if dist < 0.7:
print("It's " + str(identity) + ", welcome home!")
door_open = True
else:
print("It's not " + str(identity) + ", please go away")
door_open = False
### END CODE HERE ###
return dist, door_open
# GRADED FUNCTION: who_is_it
def who_is_it(image_path, database, model):
"""
Implements face recognition for the happy house by finding who is the person on the image_path image.
Arguments:
image_path -- path to an image
database -- database containing image encodings along with the name of the person on the image
model -- your Inception model instance in Keras
Returns:
min_dist -- the minimum distance between image_path encoding and the encodings from the database
identity -- string, the name prediction for the person on image_path
"""
### START CODE HERE ###
## Step 1: Compute the target "encoding" for the image. Use img_to_encoding() see example above. ## (≈ 1 line)
encoding = img_to_encoding(image_path, model)
## Step 2: Find the closest encoding ##
# Initialize "min_dist" to a large value, say 100 (≈1 line)
min_dist = 100
# Loop over the database dictionary's names and encodings.
for (name, db_enc) in database:
# Compute L2 distance between the target "encoding" and the current "emb" from the database. (≈ 1 line)
dist = np.linga.norm(encoding - db_enc)
# If this distance is less than the min_dist, then set min_dist to dist, and identity to name. (≈ 3 lines)
if dist < min_dist:
min_dist = dist
identity = name
### END CODE HERE ###
if min_dist > 0.7:
print("Not in the database.")
else:
print("it's " + str(identity) + ", the distance is " + str(min_dist))
return min_dist, identity
if __name__ == '__main__':
starttime = datetime.datetime.now()
################################################
FRmodel = faceRecoModel(input_shape=(3, 96, 96))
print("Total Params:", FRmodel.count_params())
FRmodel.compile(optimizer='adam', loss=triplet_loss, metrics=['accuracy'])
load_weights_from_FaceNet(FRmodel)
database = {}
database["danielle"] = img_to_encoding("images/danielle.png", FRmodel)
database["younes"] = img_to_encoding("images/younes.jpg", FRmodel)
database["tian"] = img_to_encoding("images/tian.jpg", FRmodel)
database["andrew"] = img_to_encoding("images/andrew.jpg", FRmodel)
database["kian"] = img_to_encoding("images/kian.jpg", FRmodel)
database["dan"] = img_to_encoding("images/dan.jpg", FRmodel)
database["sebastiano"] = img_to_encoding("images/sebastiano.jpg", FRmodel)
database["bertrand"] = img_to_encoding("images/bertrand.jpg", FRmodel)
database["kevin"] = img_to_encoding("images/kevin.jpg", FRmodel)
database["felix"] = img_to_encoding("images/felix.jpg", FRmodel)
database["benoit"] = img_to_encoding("images/benoit.jpg", FRmodel)
database["arnaud"] = img_to_encoding("images/arnaud.jpg", FRmodel)
dist1, open1 = verify("images/camera_0.jpg", "younes", database, FRmodel)
dist2, open2 = verify("images/camera_2.jpg", "kian", database, FRmodel)
print(dist1, dist2)
dist3, identity3 = who_is_it("images/camera_0.jpg", database, FRmodel)
print(dist3, identity3)
#################################################
endtime = datetime.datetime.now()
print("the running time :" + str((endtime - starttime).seconds))
print("END!")
What you should remember:
- Face verification solves an easier 1:1 matching problem; face recognition addresses a harder 1:K matching problem.
- The triplet loss is an effective loss function for training a neural network to learn an encoding of a face image.
- The same encoding can be used for verification and recognition. Measuring distances between two images’ encodings allows you to determine whether they are pictures of the same person.
使用keres框架自带的模型可视化工具,得到如下结果,中间并行的是GoogleNet(inception_block):