olivettifaces數據集實現人臉識別代碼

數據集：

# -*- coding: utf-8 -*-
"""
Created on Wed Apr 24 18:21:21 2019

@author: 92958
"""

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
import numpy
from PIL import Image

dataset_path='./olivettifaces.gifa'
#獲取dataset
def load_data(dataset_path):
    img = Image.open(dataset_path)
    # 定義一個20 × 20的訓練樣本，一共有40我的，每一個人都10張樣本照片
    img_ndarray = np.asarray(img, dtype='float64') / 256
    #img_ndarray = np.asarray(img, dtype='float32') / 32

    # 記錄臉數據矩陣，57 * 47爲每張臉的像素矩陣
    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

    # 將數據分紅訓練集，驗證集，測試集
    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')
    linear_output = tf.nn.relu(tf.add(conv, bias))
    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())
    return tf.add(tf.matmul(data, weights), biases)

def convolutional_neural_network(data):
    # 根據類別個數定義最後輸出層的神經元
    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])

    # 通過第一層卷積神經網絡後，獲得的張量shape爲：[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]
        )
    # 通過第二層卷積神經網絡後，獲得的張量shape爲：[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:
        # 講卷積層張量數據拉成2-D張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")  # 輸入數據
    # Y = tf.placeholder(tf.float32, shape=(None, None), name='y-input')  # 輸入標籤

    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))
    optimizer = tf.train.AdamOptimizer(1e-2).minimize(cost_func)

    # 用於保存訓練的最佳模型
    saver = tf.train.Saver()
    #model_dir = './model'
    #model_path = model_dir + '/best.ckpt'
    with tf.Session() as session:
        # 若不存在模型數據，須要訓練模型參數
        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)

        # 恢復數據並校驗和測試
        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")


#畫出在測試集中錯誤的數據
def plot_errordata(error_index, dataset_path):
    img = mpimg.imread(dataset_path)
    plt.imshow(img)
    currentAxis = plt.gca()
    for index in error_index:
        row = index // 2
        column = index % 2
        currentAxis.add_patch(
            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"
    data = load_data(dataset_path)
    model_dir = './model'
    model_path = model_dir + '/best.ckpt'
    train_facedata(data, model_dir, model_path)

if __name__ == "__main__" :
    main()

控制檯信息：
runfile('F:/python/TensorFlow/人臉識別/olive1.py', wdir='F:/python/TensorFlow/人臉識別')
WARNING:tensorflow:From C:\Users\92958\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.

WARNING: The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:

• https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
• https://github.com/tensorflow/addons
  If you depend on functionality not listed there, please file an issue.

WARNING:tensorflow:From C:\Users\92958\Anaconda3\lib\site-packages\tensorflow\contrib\layers\python\layers\layers.py:1624: flatten (from tensorflow.python.layers.core) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.flatten instead.
WARNING:tensorflow:From F:/python/TensorFlow/人臉識別/olive1.py:158: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version.
Instructions for updating:

Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.

See tf.nn.softmax_cross_entropy_with_logits_v2.

0 : 2671140.984375
create the directory: ./model
Model saved in file: ./model/best.ckpt
1 : 610905.9375
Model saved in file: ./model/best.ckpt
2 : 181258.35693359375
Model saved in file: ./model/best.ckpt
3 : 54391.228271484375
Model saved in file: ./model/best.ckpt
4 : 24234.38525390625
Model saved in file: ./model/best.ckpt
5 : 9868.018524169922
Model saved in file: ./model/best.ckpt
6 : 3433.5851974487305
Model saved in file: ./model/best.ckpt
7 : 826.4495697021484
Model saved in file: ./model/best.ckpt
8 : 200.12329292297363
Model saved in file: ./model/best.ckpt
9 : 194.84842109680176
Model saved in file: ./model/best.ckpt
10 : 63.74338483810425
Model saved in file: ./model/best.ckpt
11 : 10.006996154785156
Model saved in file: ./model/best.ckpt
12 : 7.118054211139679
Model saved in file: ./model/best.ckpt
13 : 0.0
Model saved in file: ./model/best.ckpt
14 : 0.0
15 : 0.0
16 : 0.0
17 : 0.0
18 : 0.0
19 : 0.0
WARNING:tensorflow:From C:\Users\92958\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py:1266: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
INFO:tensorflow:Restoring parameters from ./model/best.ckpt
valid set accuracy: 0.8
picture person is 4, but mis-predicted as person 8
picture person is 18, but mis-predicted as person 14
picture person is 21, but mis-predicted as person 27
picture person is 35, but mis-predicted as person 17

原文：https://blog.csdn.net/hanghangaidoudou/article/details/79347080