基于CNN的人脸识别程序

import os import tensorflow as tf import numpy as np import cv2 import matplotlib.pyplot as plt os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' Class_Nums = 5 # 共有 5 个种类 Sample_Nums = 90 # 每类取 10 个样本,共 50 个样本 def load_images(): img_list = [] for i in range(Class_Nums): path = 'F:\Python WorkSpace\FaceRecognize\\train\%d\\' % (i+1) for j in range(Sample_Nums): file_name = '%03d.jpg' % (j+1) file = path + file_name image = cv2.imread(file, cv2.IMREAD_GRAYSCALE) img_list.append(image) return img_list def get_accuracy(logits, targets): batch_prediction = np.argmax(logits, axis=1) num_correct = np.sum(np.equal(batch_prediction, targets)) return 100.* num_correct / batch_prediction.shape[0] # 以下代码用于实现卷积网络 def weight_init(shape, name): return tf.get_variable(name, shape, initializer=tf.random_normal_initializer(mean=0.0, stddev=0.1)) def bias_init(shape, name): return tf.get_variable(name, shape, initializer=tf.constant_initializer(0.0)) def conv2d(input_data, conv_w): return tf.nn.conv2d(input_data, conv_w, strides=[1, 1, 1, 1], padding='SAME') def max_pool(input_data, size): return tf.nn.max_pool(input_data, ksize=[1, size, size, 1], strides=[1, size, size, 1], padding='SAME') def conv_net(input_data, name): with tf.name_scope('conv1'): w_conv1 = weight_init([3, 3, 1, 8], 'conv1_w') # 卷积核大小是 3*3 输入是 1 通道,输出为 8 通道,即提取8特征 b_conv1 = bias_init([8], 'conv1_b') h_conv1 = tf.nn.relu(tf.nn.bias_add(conv2d(input_data, w_conv1), b_conv1)) bn1 = tf.contrib.layers.batch_norm(h_conv1) h_pool1 = max_pool(bn1, 2) with tf.name_scope('conv2'): w_conv2 = weight_init([5, 5, 8, 8], 'conv2_w') # 卷积核大小是 5*5 输入是64,输出为 32 b_conv2 = bias_init([8], 'conv2_b') h_conv2 = tf.nn.relu(conv2d(h_pool1, w_conv2) + b_conv2) bn2 = tf.contrib.layers.batch_norm(h_conv2) h_pool2 = max_pool(bn2, 2) with tf.name_scope('conv3'): w_conv3 = weight_init([5, 5, 8, 8], 'conv3_w') # 卷积核大小是 5*5 输入是8,输出为 8 b_conv3 = bias_init([8], 'conv3_b') h_conv3 = tf.nn.relu(conv2d(h_pool2, w_conv3) + b_conv3) bn3 = tf.contrib.layers.batch_norm(h_conv3) h_pool3 = max_pool(bn3, 2) with tf.name_scope('fc1'): w_fc1 = weight_init([23 * 23 * 8, 120], 'fc1_w') # 三层卷积后得到的图像大小为 22 * 22,共 50 个样本 b_fc1 = bias_init([120], 'fc1_b') h_fc1 = tf.nn.relu(tf.matmul(tf.reshape(h_pool3, [-1, 23 * 23 * 8]), w_fc1) + b_fc1) with tf.name_scope('fc2'): w_fc2 = weight_init([120, Class_Nums], 'fc2_w') # 将 130 个特征映射到 26 个类别上 b_fc2 = bias_init([Class_Nums], 'fc2_b') h_fc2 = tf.nn.softmax(tf.matmul(h_fc1, w_fc2) + b_fc2) return h_fc2 # 生成 tfrecord 文件 def gen_tfrecord(path): tf_writer = tf.python_io.TFRecordWriter(path) for i in range(Class_Nums): path = 'F:\Python WorkSpace\FaceRecognize\\train\%d\\' % (i + 1) label_data = i for j in range(Sample_Nums): file_name = '%03d.jpg' % (j + 1) file = path + file_name image = cv2.imread(file, cv2.IMREAD_GRAYSCALE) image_bytes= image.tostring() height = image.shape[0] width = image.shape[1] channels = 1 example = tf.train.Example() feature = example.features.feature feature['height'].int64_list.value.append(height) feature['width'].int64_list.value.append(width) feature['channels'].int64_list.value.append(channels) feature['image_data'].bytes_list.value.append(image_bytes) feature['label'].int64_list.value.append(label_data) tf_writer.write(example.SerializeToString()) tf_writer.close() def read_and_decode(filename_queue): reader = tf.TFRecordReader() _, serialized_example = reader.read(filename_queue) features = tf.parse_single_example( serialized_example, features={ 'height': tf.FixedLenFeature([], tf.int64), 'width': tf.FixedLenFeature([], tf.int64), 'channels': tf.FixedLenFeature([], tf.int64), 'image_data':tf.FixedLenFeature([], tf.string), 'label': tf.FixedLenFeature([], tf.int64) } ) image = tf.decode_raw(features['image_data'], tf.uint8) image = tf.reshape(image, [180, 180, 1]) image = tf.cast(image, tf.float32) label = tf.cast(features['label'], tf.int32) return image, label # 该函数用于统计 TFRecord 文件中的样本数量(总数) def total_sample(file_name): sample_nums = 0 for record in tf.python_io.tf_record_iterator(file_name): sample_nums += 1 return sample_nums def train_data(): batch_size = 10 batch_num = total_sample('Faces.tfrecord') / batch_size filename_queue = tf.train.string_input_producer(['Faces.tfrecord'], shuffle=False) image, label = read_and_decode(filename_queue) image_train, label_train = tf.train.batch([image, label], batch_size=batch_size, num_threads=1, capacity=32) #image_train, label_train = tf.train.shuffle_batch([image, label], batch_size, num_threads=1, capacity=5+batch_size*3, min_after_dequeue=5) train_labels_one_hot = tf.one_hot(label_train, 5, on_value=1.0, off_value=0.0) x_data = tf.placeholder(tf.float32, shape=[None, 180, 180, 1], name='x_data') y_target = tf.placeholder(tf.float32, shape=[None, Class_Nums], name='label') global_step = tf.get_variable('global_step', [], initializer=tf.constant_initializer(0), trainable=False, dtype=tf.int32) model_output = conv_net(x_data, name = "model_output") loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y_target, logits=model_output)) optimizer = tf.train.AdamOptimizer(10e-5).minimize(loss, global_step=global_step) train_correct_prediction = tf.equal(tf.argmax(model_output, 1), tf.argmax(y_target, 1)) train_accuracy = tf.reduce_mean(tf.cast(train_correct_prediction, tf.float32)) tf.summary.scalar('loss', loss) tf.summary.scalar('acc', train_accuracy) merge = tf.summary.merge_all() init = tf.global_variables_initializer() config = tf.ConfigProto(allow_soft_placement = True) # 如果指定设备不存在,允许TF自动分配设备 config.gpu_options.per_process_gpu_memory_fraction = 0.4 # 占用GPU40%的显存 session = tf.Session(config=config) writer = tf.summary.FileWriter("./log", session.graph) saver = tf.train.Saver(max_to_keep=4) # 保存训练的参数模型 tf.add_to_collection("predict", model_output) session.run(init) coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=session, coord=coord) loss_list = [] acc_list = [] try: for i in range(1000): cost_avg = 0 acc_avg = 0 for j in range(int(batch_num)): image_batch, label_batch = session.run([image_train, train_labels_one_hot]) _,step, acc, cost, rs = session.run([optimizer, global_step, train_accuracy, loss, merge], feed_dict={x_data: image_batch, y_target:label_batch}) acc_avg += (acc/batch_num) cost_avg += (cost/batch_num) writer.add_summary(rs, step) print("step %d, training accuracy %0.10f loss %0.10f" % (i, acc_avg, cost_avg)) loss_list.append(cost_avg) acc_list.append(acc_avg) if step % 60 == 0: