tensorflow1.1/构建卷积神经网络人脸识别

环境：tensorflow1.1,python3,matplotlin2.02

olivettifaces是纽约大学的一个比较小的人脸库，由40个人的400张图片构成，即每个人的人脸图片为10张。每张图片的灰度级为8位，每个像素的灰度大小位于0-255之间，每张图片大小为64×64。图片大小是1190*942，一共有20*20张人脸，故每张人脸大小是（1190/20）*（942/20）即57*47=2679本文所用的训练数据就是这张图片，400个样本，40个类别。

#coding:utf-8"""python 3tensorflow 1.1matplotlib 2.02"""import tensorflow as tfimport pickleimport numpy as npimport matplotlib.pyplot as plt#读取数据集with open('facedataset.pickle','rb') as f:    (train_data,train_labels),(test_data,test_labels) = pickle.load(f)tf.set_random_seed(100)np.random.seed(100)batch_size = 40learning_rate = 0.01#定义one_hotdef label_to_one_hot(labels_dense, num_classes=10):    num_labels = labels_dense.shape[0]    index_offset = np.arange(num_labels) * num_classes    labels_one_hot = np.zeros((num_labels, num_classes))    labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1    return labels_one_hottrain_data = train_data.astype(np.float32)test_data = test_data.astype(np.float32)train_labels = label_to_one_hot(train_labels,num_classes=40).astype(np.int32)test_labels = label_to_one_hot(test_labels,num_classes=40).astype(np.int32)#查看图片plt.imshow(train_data[0].reshape((57,47)))plt.title('the face picture',fontdict={'size':16,'color':'c'})plt.gray()plt.show()#定义输入形状xs = tf.placeholder(tf.float32,[None,57*47])ys = tf.placeholder(tf.int32,[None,40])#构建神经网络x = tf.reshape(xs,[-1,57,47,1])conv1 = tf.layers.conv2d(inputs=x,filters=5,kernel_size=3,strides=1,padding='same',activation=tf.nn.relu)pool1 = tf.layers.max_pooling2d(conv1,pool_size=2,strides=2)conv2 = tf.layers.conv2d(inputs=pool1,filters=10,kernel_size=3,strides=1,padding='same',activation=tf.nn.relu)pool2 = tf.layers.max_pooling2d(conv2,pool_size=2,strides=2)flat = tf.reshape(pool2,[-1,14*11*10])output = tf.layers.dense(flat,40)#计算lossloss = tf.losses.softmax_cross_entropy(onehot_labels=ys,logits=output)train = tf.train.AdamOptimizer(learning_rate).minimize(loss)_,accuracy = tf.metrics.accuracy(labels=tf.argmax(ys,axis=1),predictions=tf.argmax(output,axis=1))with tf.Session() as sess:    init = tf.group(tf.global_variables_initializer(),tf.local_variables_initializer())    sess.run(init)    for i in range(10):        _,c = sess.run([train,loss],feed_dict={xs:train_data,ys:train_labels})        print('= = = = = = > > > > > >loss: %.4f' %c)    acc = sess.run(accuracy,feed_dict={xs:test_data,ys:test_labels})    print('accuracy is :%.4f' %acc)

由于数据集很小，在训练的时候就没有考虑采用batch训练

结果：

训练注意事项

在神经网络训练的过程中，如果数据集没有被打乱，原始数据集是有序的，会对检测精度造成很大影响
上述实验中在训练集和label上设置相同的随机种子，打乱顺序后训练，检测精度显著提高。