python 识别出自己得人脸（二训练得到得人脸数据，得到训练模型）
上一节中我介绍了怎么得到自己得人脸数据，那么得到数据以后我们肯定要进行训练，训练得话我们就需要用到神经网络得一些框架，这里我使用现在比较流行得基于geogle下的tenserflow框架来训练得到模型。
看代码：
import tensorflow as tf
import cv2
import numpy as np
import os
import random
import sys
from sklearn.model_selection import train_test_split
my_faces_path = '/home/dong/PycharmProjects/untitled/人脸识别/data/me'
other_faces_path = '/home/dong/PycharmProjects/untitled/人脸识别/data/zhang'
size = 64
imgs = []
labs = []
def getPaddingSize(img):
h, w, _ = img.shape
top, bottom, left, right = (0, 0, 0, 0)
longest = max(h, w)
if w < longest:
tmp = longest - w # 相当于 h-w
# //表示整除符号
left = tmp // 2
right = tmp - left
elif h < longest:
tmp = longest - h
top = tmp // 2
bottom = tmp - top
else:
pass
return top, bottom, left, right
def readData(path, h=size, w=size):
for filename in os.listdir(path):
if filename.endswith('.jpg'):
filename = path + '/' + filename
img = cv2.imread(filename)
top, bottom, left, right = getPaddingSize(img)
# 将图片放大， 扩充图片边缘部分
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=[0, 0, 0])
img = cv2.resize(img, (h, w))
imgs.append(img)
labs.append(path)
readData(my_faces_path)
readData(other_faces_path)
# 将图片数据与标签转换成数组
imgs = np.array(imgs)
labs = np.array([[1, 0] if lab == my_faces_path else [0, 1] for lab in labs])
# 随机划分测试集与训练集
train_x, test_x, train_y, test_y = train_test_split(imgs, labs, test_size=0.05, random_state=random.randint(0, 100))
print(train_x[0].shape)
# 参数：图片数据的总数，图片的高、宽、通道
train_x = train_x.reshape(train_x.shape[0], size, size, 3)
test_x = test_x.reshape(test_x.shape[0], size, size, 3)
# 将数据转换成小于1的数
train_x = train_x.astype('float32') / 255.0
test_x = test_x.astype('float32') / 255.0
print('train size:%s, test size:%s' % (len(train_x), len(test_x)))
# 图片块，每次取100张图片
batch_size = 100
num_batch = len(train_x) // batch_size
x = tf.placeholder(tf.float32, [None, size, size, 3])
y_ = tf.placeholder(tf.float32, [None, 2])
keep_prob_5 = tf.placeholder(tf.float32)
keep_prob_75 = tf.placeholder(tf.float32)
# 权重w
def weightVariable(shape):
init = tf.random_normal(shape, stddev=0.01)
return tf.Variable(init)
# 权重b
def biasVariable(shape):
init = tf.random_normal(shape)
return tf.Variable(init)
#卷积
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
# 池化
def maxPool(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
#全连接
def dropout(x, keep):
return tf.nn.dropout(x, keep)
def cnnLayer():
# 第一层
W1 = weightVariable([3, 3, 3, 32]) # 卷积核大小(3,3)， 输入通道(3)， 输出通道(32)
b1 = biasVariable([32])
# 卷积
conv1 = tf.nn.relu(conv2d(x, W1) + b1)
# 池化
pool1 = maxPool(conv1)
# 减少过拟合，随机让某些权重不更新
drop1 = dropout(pool1, keep_prob_5)
# 第二层
W2 = weightVariable([3, 3, 32, 64])
b2 = biasVariable([64])
conv2 = tf.nn.relu(conv2d(drop1, W2) + b2)
pool2 = maxPool(conv2)
drop2 = dropout(pool2, keep_prob_5)
# 第三层
W3 = weightVariable([3, 3, 64, 64])
b3 = biasVariable([64])
conv3 = tf.nn.relu(conv2d(drop2, W3) + b3)
pool3 = maxPool(conv3)
drop3 = dropout(pool3, keep_prob_5)
# 全连接层
Wf = weightVariable([8 * 8 * 64, 512])
bf = biasVariable([512])
drop3_flat = tf.reshape(drop3, [-1, 8 * 8 * 64])
dense = tf.nn.relu(tf.matmul(drop3_flat, Wf) + bf)
dropf = dropout(dense, keep_prob_75)
# 输出层
Wout = weightVariable([512, 2])
bout = biasVariable([2])
# out = tf.matmul(dropf, Wout) + bout
out = tf.add(tf.matmul(dropf, Wout), bout)
return out
def cnnTrain():
out = cnnLayer()
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=out, labels=y_))
# 梯度下降函数，优化器就会按照循环的次数一次次沿着loss最小值的方向优化参数了。
# train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
train_step = tf.train.AdamOptimizer(0.01).minimize(cross_entropy)
# 比较标签是否相等，再求的所有数的平均值，tf.cast(强制转换类型)
accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(out, 1), tf.argmax(y_, 1)), tf.float32))
# 将loss与accuracy保存以供tensorboard使用
tf.summary.scalar('loss', cross_entropy)
tf.summary.scalar('accuracy', accuracy)
merged_summary_op = tf.summary.merge_all()
# 数据保存器的初始化
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for n in range(10):
# 每次取12(batch_size)张图片
for i in range(num_batch):
#[i * batch_size: (i + 1) * batch_size] 假设i=1即为12：24，所以一次12个图片
batch_x = train_x[i * batch_size: (i + 1) * batch_size]
batch_y = train_y[i * batch_size: (i + 1) * batch_size]
# 开始训练数据，同时训练三个变量，返回三个数据
_, loss, summary = sess.run([train_step, cross_entropy, merged_summary_op],
feed_dict={x: batch_x, y_: batch_y, keep_prob_5: 0.5, keep_prob_75: 0.75})
# 打印损失
'''
with tf.Session() as sess:
print(accuracy.eval({x:mnist.test.images,y_: mnist.test.labels}))
with tf.Session() as sess:
print(sess.run(accuracy, {x:mnist.test.images,y_: mnist.test.labels}))
'''
acc = accuracy.eval({x: test_x, y_: test_y, keep_prob_5: 1.0, keep_prob_75: 1.0})
print(n * num_batch + i, loss, acc)
if (n * num_batch + i) % 100 == 0:
# 获取测试数据的准确率
acc = accuracy.eval({x: test_x, y_: test_y, keep_prob_5: 1.0, keep_prob_75: 1.0})
print(n * num_batch + i, acc)
# 准确率大于0.98时保存并退出
if acc > 0.98 and n > 2:
sys.exit(0)
print('accuracy less 0.98, exited!')
# 保存为训练模型
saver.save(sess, '模型')
cnnTrain()
这里用到了很多三方库tensorflow
opencv
numpy
os
random
sys
sklearn
my_faces_path = '/home/dong/PycharmProjects/untitled/人脸识别/data/me'
other_faces_path = '/home/dong/PycharmProjects/untitled/人脸识别/data/zhang'
我把刚刚获得得人脸数据分别放到这两个目录下,my 里边放的我舍友董，other放着我舍友zhang。
接下来我们需要对图片进行下简单的处理，
def getPaddingSize(img):
#得到图片得长宽
h, w, _ = img.shape
#四个方位需要填充得值开始为0
top, bottom, left, right = (0, 0, 0, 0)
#找出较长得一边
longest = max(h, w)
#如果长大于宽
if w < longest:
tmp = longest - w # 相当于 h-w
# //表示整除符号
left = tmp // 2 # 左边填充值
right = tmp - left #右边填充值
elif h < longest:
tmp = longest - h
top = tmp // 2
bottom = tmp - top
else:
pass
return top, bottom, left, right
这一段代码得作用是使图片得长宽一样。例
原始图片：长方形
处理后得图片：正方形，用黑色进行填充。
def readData(path, h=size, w=size):
for filename in os.listdir(path):
if filename.endswith('.jpg'):
filename = path + '/' + filename
img = cv2.imread(filename)
# 将图片放大， 扩充图片边缘部分
top, bottom, left, right = getPaddingSize(img)
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=[0, 0, 0])
img = cv2.resize(img, (h, w))
imgs.append(img)
labs.append(path)
这里是用来读取图片。
def cnnLayer():
# 第一层
W1 = weightVariable([3, 3, 3, 32]) # 卷积核大小(3,3)， 输入通道(3)， 输出通道(32)
b1 = biasVariable([32])
# 卷积
conv1 = tf.nn.relu(conv2d(x, W1) + b1)
# 池化
pool1 = maxPool(conv1)
# 减少过拟合，随机让某些权重不更新
drop1 = dropout(pool1, keep_prob_5)
# 第二层
W2 = weightVariable([3, 3, 32, 64])
b2 = biasVariable([64])
conv2 = tf.nn.relu(conv2d(drop1, W2) + b2)
pool2 = maxPool(conv2)
drop2 = dropout(pool2, keep_prob_5)
# 第三层
W3 = weightVariable([3, 3, 64, 64])
b3 = biasVariable([64])
conv3 = tf.nn.relu(conv2d(drop2, W3) + b3)
pool3 = maxPool(conv3)
drop3 = dropout(pool3, keep_prob_5)
# 全连接层
Wf = weightVariable([8 * 8 * 64, 512])
bf = biasVariable([512])
drop3_flat = tf.reshape(drop3, [-1, 8 * 8 * 64])
dense = tf.nn.relu(tf.matmul(drop3_flat, Wf) + bf)
dropf = dropout(dense, keep_prob_75)
# 输出层
Wout = weightVariable([512, 2])
bout = biasVariable([2])
# out = tf.matmul(dropf, Wout) + bout
out = tf.add(tf.matmul(dropf, Wout), bout)
return out
这是卷积神经网络相应层得函数
def cnnLayer():
# 第一层
W1 = weightVariable([3, 3, 3, 32]) # 卷积核大小(3,3)， 输入通道(3)， 输出通道(32)
b1 = biasVariable([32])
# 卷积
conv1 = tf.nn.relu(conv2d(x, W1) + b1)
# 池化
pool1 = maxPool(conv1)
# 减少过拟合，随机让某些权重不更新
drop1 = dropout(pool1, keep_prob_5)
# 第二层
# 输出64
W2 = weightVariable([3, 3, 32, 64])
b2 = biasVariable([64])
conv2 = tf.nn.relu(conv2d(drop1, W2) + b2)
pool2 = maxPool(conv2)
drop2 = dropout(pool2, keep_prob_5)
# 第三层
# 输出64
W3 = weightVariable([3, 3, 64, 64])
b3 = biasVariable([64])
conv3 = tf.nn.relu(conv2d(drop2, W3) + b3)
pool3 = maxPool(conv3)
drop3 = dropout(pool3, keep_prob_5)
# 全连接层
Wf = weightVariable([8 * 8 * 64, 512])
bf = biasVariable([512])
drop3_flat = tf.reshape(drop3, [-1, 8 * 8 * 64])
dense = tf.nn.relu(tf.matmul(drop3_flat, Wf) + bf)
dropf = dropout(dense, keep_prob_75)
# 输出层
Wout = weightVariable([512, 2])
bout = biasVariable([2])
# out = tf.matmul(dropf, Wout) + bout
out = tf.add(tf.matmul(dropf, Wout), bout)
return out
这里用来训练神经网络
W1 = weightVariable([3, 3, 3, 32]) # 卷积核大小(3,3)， 输入通道(3)， 输出通道(32)
输入一张图片，会被分解成含有图片信息得32张小图片
pool1 = maxPool(conv1)
输入图片大小为6464，每池化一次降低一般，池化一次变为3232，一共池化了三次，所以最后图片大小为88，又因为输出为64，所以一共有88*64个神经点。
Wf = weightVariable([8 * 8 * 64, 512])
512是我们随意设的输出，输入为8864个神经点，输出为512个神经点。
def cnnTrain():
out = cnnLayer()
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=out, labels=y_))
# 梯度下降函数，优化器就会按照循环的次数一次次沿着loss最小值的方向优化参数了。
# train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
train_step = tf.train.AdamOptimizer(0.01).minimize(cross_entropy)
# 比较标签是否相等，再求的所有数的平均值，tf.cast(强制转换类型)
accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(out, 1), tf.argmax(y_, 1)), tf.float32))
# 将loss与accuracy保存以供tensorboard使用
tf.summary.scalar('loss', cross_entropy)
tf.summary.scalar('accuracy', accuracy)
merged_summary_op = tf.summary.merge_all()
# 数据保存器的初始化
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for n in range(10):
# 每次取12(batch_size)张图片
for i in range(num_batch):
#[i * batch_size: (i + 1) * batch_size] 假设i=1即为12：24，所以一次12个图片
batch_x = train_x[i * batch_size: (i + 1) * batch_size]
batch_y = train_y[i * batch_size: (i + 1) * batch_size]
# 开始训练数据，同时训练三个变量，返回三个数据
_, loss, summary = sess.run([train_step, cross_entropy, merged_summary_op],
feed_dict={x: batch_x, y_: batch_y, keep_prob_5: 0.5, keep_prob_75: 0.75})
# 打印损失
'''
with tf.Session() as sess:
print(accuracy.eval({x:mnist.test.images,y_: mnist.test.labels}))
with tf.Session() as sess:
print(sess.run(accuracy, {x:mnist.test.images,y_: mnist.test.labels}))
'''
acc = accuracy.eval({x: test_x, y_: test_y, keep_prob_5: 1.0, keep_prob_75: 1.0})
print(n * num_batch + i, loss, acc)
if (n * num_batch + i) % 100 == 0:
# 获取测试数据的准确率 这里得意思是把text_x得值赋值给x，后边得一样得道理
acc = accuracy.eval({x: test_x, y_: test_y, keep_prob_5: 1.0, keep_prob_75: 1.0})
print(n * num_batch + i, acc)
# 准确率大于0.98时保存并退出
if acc > 0.98 and n > 2:
sys.exit(0)
print('accuracy less 0.98, exited!')
# 保存为训练模型
saver.save(sess, '模型')
最后一部分主要是完成对数据得训练，把训练结果转化成准确率。