Tensorflow学习笔记---人脸识别DEMO实现

```'''

（1190 / 20）× （942 / 20）= 57 × 47
（大约，以为每张图片之间存在间距）

10类样本，利用CNN训练可以分类10类数据的神经网络，与手写字符识别类似
'''

#coding=utf-8
import os
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import matplotlib.patches as patches
from PIL import Image

#获取dataset
img = Image.open(dataset_path)
# 定义一个20 × 20的训练样本，一共有40个人，每个人都10张样本照片
img_ndarray = np.asarray(img, dtype='float64') / 256
#img_ndarray = np.asarray(img, dtype='float32') / 32

# 记录脸数据矩阵，57 * 47为每张脸的像素矩阵
faces = np.empty((400, 57 * 47))

for row in range(20):
for column in range(20):
faces[20 * row + column] = np.ndarray.flatten(
img_ndarray[row * 57: (row + 1) * 57, column * 47 : (column + 1) * 47]
)

label = np.zeros((400, 40))
for i in range(40):
label[i * 10: (i + 1) * 10, i] = 1

# 将数据分成训练集，验证集，测试集
train_data = np.empty((320, 57 * 47))
train_label = np.zeros((320, 40))
vaild_data = np.empty((40, 57 * 47))
vaild_label = np.zeros((40, 40))
test_data = np.empty((40, 57 * 47))
test_label = np.zeros((40, 40))

for i in range(40):
train_data[i * 8: i * 8 + 8] = faces[i * 10: i * 10 + 8]
train_label[i * 8: i * 8 + 8] = label[i * 10: i * 10 + 8]

vaild_data[i] = faces[i * 10 + 8]
vaild_label[i] = label[i * 10 + 8]

test_data[i] = faces[i * 10 + 9]
test_label[i] = label[i * 10 + 9]

train_data = train_data.astype('float32')
vaild_data = vaild_data.astype('float32')
test_data = test_data.astype('float32')

return [
(train_data, train_label),
(vaild_data, vaild_label),
(test_data, test_label)
]

def convolutional_layer(data, kernel_size, bias_size, pooling_size):
kernel = tf.get_variable("conv", kernel_size, initializer=tf.random_normal_initializer())
bias = tf.get_variable('bias', bias_size, initializer=tf.random_normal_initializer())

conv = tf.nn.conv2d(data, kernel, strides=[1, 1, 1, 1], padding='SAME')
pooling = tf.nn.max_pool(linear_output, ksize=pooling_size, strides=pooling_size, padding="SAME")
return pooling

def linear_layer(data, weights_size, biases_size):
weights = tf.get_variable("weigths", weights_size, initializer=tf.random_normal_initializer())
biases = tf.get_variable("biases", biases_size, initializer=tf.random_normal_initializer())

def convolutional_neural_network(data):
# 根据类别个数定义最后输出层的神经元
n_ouput_layer = 40

kernel_shape1=[5, 5, 1, 32]
kernel_shape2=[5, 5, 32, 64]
full_conn_w_shape = [15 * 12 * 64, 1024]
out_w_shape = [1024, n_ouput_layer]

bias_shape1=[32]
bias_shape2=[64]
full_conn_b_shape = [1024]
out_b_shape = [n_ouput_layer]

data = tf.reshape(data, [-1, 57, 47, 1])

# 经过第一层卷积神经网络后，得到的张量shape为：[batch, 29, 24, 32]
with tf.variable_scope("conv_layer1") as layer1:
layer1_output = convolutional_layer(
data=data,
kernel_size=kernel_shape1,
bias_size=bias_shape1,
pooling_size=[1, 2, 2, 1]
)
# 经过第二层卷积神经网络后，得到的张量shape为：[batch, 15, 12, 64]
with tf.variable_scope("conv_layer2") as layer2:
layer2_output = convolutional_layer(
data=layer1_output,
kernel_size=kernel_shape2,
bias_size=bias_shape2,
pooling_size=[1, 2, 2, 1]
)
with tf.variable_scope("full_connection") as full_layer3:
# 讲卷积层张量数据拉成2-D张量只有有一列的列向量
layer2_output_flatten = tf.contrib.layers.flatten(layer2_output)
layer3_output = tf.nn.relu(
linear_layer(
data=layer2_output_flatten,
weights_size=full_conn_w_shape,
biases_size=full_conn_b_shape
)
)
# layer3_output = tf.nn.dropout(layer3_output, 0.8)
with tf.variable_scope("output") as output_layer4:
output = linear_layer(
data=layer3_output,
weights_size=out_w_shape,
biases_size=out_b_shape
)

return output;

def train_facedata(dataset, model_dir,model_path):
# train_set_x = data[0][0]
# train_set_y = data[0][1]
# valid_set_x = data[1][0]
# valid_set_y = data[1][1]
# test_set_x = data[2][0]
# test_set_y = data[2][1]
# X = tf.placeholder(tf.float32, shape=(None, None), name="x-input")  # 输入数据
# Y = tf.placeholder(tf.float32, shape=(None, None), name='y-input')  # 输入标签

batch_size = 40

# train_set_x, train_set_y = dataset[0]
# valid_set_x, valid_set_y = dataset[1]
# test_set_x, test_set_y = dataset[2]
train_set_x = dataset[0][0]
train_set_y = dataset[0][1]
valid_set_x = dataset[1][0]
valid_set_y = dataset[1][1]
test_set_x = dataset[2][0]
test_set_y = dataset[2][1]

X = tf.placeholder(tf.float32, [batch_size, 57 * 47])
Y = tf.placeholder(tf.float32, [batch_size, 40])

predict = convolutional_neural_network(X)
cost_func = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=predict, labels=Y))

# 用于保存训练的最佳模型
saver = tf.train.Saver()
#model_dir = './model'
#model_path = model_dir + '/best.ckpt'
with tf.Session() as session:
# 若不存在模型数据，需要训练模型参数
if not os.path.exists(model_path + ".index"):
session.run(tf.global_variables_initializer())
best_loss = float('Inf')
for epoch in range(20):
epoch_loss = 0
for i in range((int)(np.shape(train_set_x)[0] / batch_size)):
x = train_set_x[i * batch_size: (i + 1) * batch_size]
y = train_set_y[i * batch_size: (i + 1) * batch_size]
_, cost = session.run([optimizer, cost_func], feed_dict={X: x, Y: y})
epoch_loss += cost

print(epoch, ' : ', epoch_loss)
if best_loss > epoch_loss:
best_loss = epoch_loss
if not os.path.exists(model_dir):
os.mkdir(model_dir)
print("create the directory: %s" % model_dir)
save_path = saver.save(session, model_path)
print("Model saved in file: %s" % save_path)

# 恢复数据并校验和测试
saver.restore(session, model_path)
correct = tf.equal(tf.argmax(predict,1), tf.argmax(Y,1))
valid_accuracy = tf.reduce_mean(tf.cast(correct,'float'))
print('valid set accuracy: ', valid_accuracy.eval({X: valid_set_x, Y: valid_set_y}))

test_pred = tf.argmax(predict, 1).eval({X: test_set_x})
test_true = np.argmax(test_set_y, 1)
test_correct = correct.eval({X: test_set_x, Y: test_set_y})
incorrect_index = [i for i in range(np.shape(test_correct)[0]) if not test_correct[i]]
for i in incorrect_index:
print('picture person is %i, but mis-predicted as person %i'
%(test_true[i], test_pred[i]))
plot_errordata(incorrect_index, "olivettifaces.gif")

#画出在测试集中错误的数据
def plot_errordata(error_index, dataset_path):
plt.imshow(img)
currentAxis = plt.gca()
for index in error_index:
row = index // 2
column = index % 2
patches.Rectangle(
xy=(
47 * 9 if column == 0 else 47 * 19,
row * 57
),
width=47,
height=57,
linewidth=1,
edgecolor='r',
facecolor='none'
)
)
plt.savefig("result.png")
plt.show()

def main():
dataset_path = "olivettifaces.gif"
model_dir = './model'
model_path = model_dir + '/best.ckpt'
train_facedata(data, model_dir, model_path)

if __name__ == "__main__" :
main()```

0 条评论

• Python基础 PyQt5（一）

pyqt5是一套Python绑定Digia QT5应用的框架。它可用于Python 3。（小编所有的教程都是基于python3的，如果有需要了解python2的...

• python爬取考研网的信息

https://yz.chsi.com.cn/zsml/queryAction.do

• AutoKeras---自动机器学习

Auto-Keras是用于自动机器学习的开源软件库。目的是让仅拥有一定数据科学知识或机器学习背景的行业专家可以轻松地应用深度学习模型。

• 对于数据库操作的敬畏小案例

之前一直在说对于线上运维操作的敬畏之心，但是话说了，有时候没有案例的说明其实是苍白的。刚好借着最近同事碰到的一个案例来做下说明。

• VBA实现自己的ArrayPtr取数组地址函数

在VBA数据类型Array中，我们提到了取数组的函数，是使用1个API函数VarPtrArray ，要声明这么一个不大常用的API总觉得不大方便，我就在想能不能...

• 学术杂谈|一篇所有研究生都该读的好文：阳光温热 科研静好！

你感觉上课就像打酱油时，当你对读研感到很迷茫时，当你坐在电脑前孜孜不倦时，请看下面的文章，很受用，至少我心里现在没有以前浮躁。好的文章有时能改变一个人的精神状态...

• WordPress 免插件生成最安全的纯静态站点地图（sitemap.xml）

之前酷猫一直使用的是插件生成站点地图的方法，但是用来用去还是各种的不舒服，想了想还是免插件生成最好了，安全还高效！

• Angular 使用 Resolve 预先获取组件数据

这几天碰到一个需求，登录后要根据用户信息的不同跳转到不同的页面。 比如默认登录要求跳转到A页面，如果A的页面中表格数据是空则要求登录后要直接跳转到B页面。 ...

SQL Tuing Advisor(STA) 是Automatic Tuning Optimizer(自动优化调整器)的一部分。在前面的文章使用SQ...