import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data',one_hot=True) #每个批次的大小 batch_size = 100 #计算一共有多少个批次 n_batch = mnist.train.num_examples // batch_size #初始化权值 def weight_variable(shape): initial = tf.truncated_normal(shape,stddev=0.1)#生成一个截断的正态分布 return tf.Variable(initial) #初始化偏置 def bias_variable(shape): initial = tf.constant(0.1,shape=shape) return tf.Variable(initial) #卷积层 def conv2d(x,W): #x input tensor of shape `[batch, in_height, in_width, in_channels]` #W filter / kernel tensor of shape [filter_height, filter_width, in_channels, out_channels] #`strides[0] = strides[3] = 1`. strides[1]代表x方向的步长,strides[2]代表y方向的步长 #padding: A `string` from: `"SAME", "VALID"` #W为卷积和 return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME') #池化层 def max_pool_2x2(x): #ksize [1,x,y,1],窗口大小,第一值和第4个值必需设为1,中间两个值表示一次池化的窗口大小 return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME') #定义两个placeholder x = tf.placeholder(tf.float32,[None,784])#28*28 y = tf.placeholder(tf.float32,[None,10]) #改变x的格式转为4D的向量[batch, in_height, in_width, in_channels]` #in_channels表示通道数,1表示黑白,3表示彩色图片 x_image = tf.reshape(x,[-1,28,28,1]) #初始化第一个卷积层的权值和偏置 #[5,5,1,32]第三个参数1也是通道数,同上面的in_channels W_conv1 = weight_variable([5,5,1,32])#5*5的采样窗口,32个卷积核从1个平面抽取特征 b_conv1 = bias_variable([32])#每一个卷积核一个偏置值 #把x_image和权值向量进行卷积,再加上偏置值,然后应用于relu激活函数 h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1) + b_conv1) h_pool1 = max_pool_2x2(h_conv1)#进行max-pooling #初始化第二个卷积层的权值和偏置 W_conv2 = weight_variable([5,5,32,64])#5*5的采样窗口,64个卷积核从32个平面抽取特征 b_conv2 = bias_variable([64])#每一个卷积核一个偏置值 #把h_pool1和权值向量进行卷积,再加上偏置值,然后应用于relu激活函数 h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2) h_pool2 = max_pool_2x2(h_conv2)#进行max-pooling #28*28的图片第一次卷积后还是28*28,第一次池化后变为14*14 #第二次卷积后为14*14,第二次池化后变为了7*7 #进过上面操作后得到64张7*7的平面 #初始化第一个全连接层的权值 W_fc1 = weight_variable([7*7*64,1024])#上一层有7*7*64个神经元,全连接层有1024个神经元 b_fc1 = bias_variable([1024])#1024个节点 #把池化层2的输出扁平化为1维 h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64]) #求第一个全连接层的输出 h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1) + b_fc1) #keep_prob用来表示神经元的输出概率 keep_prob = tf.placeholder(tf.float32) h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob) #初始化第二个全连接层 W_fc2 = weight_variable([1024,10]) b_fc2 = bias_variable([10]) #计算输出 prediction = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2) + b_fc2) #交叉熵代价函数 cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction)) #使用AdamOptimizer进行优化 train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) #结果存放在一个布尔列表中 correct_prediction = tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))#argmax返回一维张量中最大的值所在的位置 #求准确率 accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32)) with tf.Session() as sess: sess.run(tf.global_variables_initializer()) for epoch in range(21): for batch in range(n_batch): batch_xs,batch_ys = mnist.train.next_batch(batch_size) sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:0.7}) acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0}) print ("Iter " + str(epoch) + ", Testing Accuracy= " + str(acc))
LSTM常应用于语音识别和自然语言处理,也可以用于图像识别;
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data #载入数据集 mnist = input_data.read_data_sets("MNIST_data/",one_hot=True) # 输入图片是28*28,每一张图片都会往LSTM网络里传28次,每次传一行,即28个数据 n_inputs = 28 #输入一行,一行有28个数据 max_time = 28 #一共28行,一个完整的数字需要输入28次 lstm_size = 100 #隐层单元,block的数量 n_classes = 10 # 10个分类 batch_size = 50 #每批次50个样本 n_batch = mnist.train.num_examples // batch_size #计算一共有多少个批次 #这里的none表示第一个维度可以是任意的长度 x = tf.placeholder(tf.float32,[None,784]) #正确的标签 y = tf.placeholder(tf.float32,[None,10]) #初始化权值 weights = tf.Variable(tf.truncated_normal([lstm_size, n_classes], stddev=0.1)) #初始化偏置值 biases = tf.Variable(tf.constant(0.1, shape=[n_classes])) #定义RNN网络 def RNN(X,weights,biases): # inputs=[batch_size, max_time, n_inputs] inputs = tf.reshape(X,[-1,max_time,n_inputs]) #定义LSTM基本CELL lstm_cell = tf.contrib.rnn.BasicLSTMCell(lstm_size) # final_state[state, batch_size, cell.state_size] # final_state[0]是cell state,表示cell的输出信号 # final_state[1]是hidden_state,表示迭代完成后,最终的输出 # outputs: The RNN output `Tensor`.outputs表示每次迭代的输出 # If time_major == False (default), this will be a `Tensor` shaped: # `[batch_size, max_time, cell.output_size]`.max_time这个参数可以控制输出迭代中间的结果,如第3次迭代后的输出 # If time_major == True, this will be a `Tensor` shaped: # `[max_time, batch_size, cell.output_size]`. outputs,final_state = tf.nn.dynamic_rnn(lstm_cell,inputs,dtype=tf.float32)#执行计算 results = tf.nn.softmax(tf.matmul(final_state[1],weights) + biases) return results #计算RNN的返回结果 prediction= RNN(x, weights, biases) #损失函数 cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y)) #使用AdamOptimizer进行优化 train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) #结果存放在一个布尔型列表中 correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#argmax返回一维张量中最大的值所在的位置 #求准确率 accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))#把correct_prediction变为float32类型 #初始化 init = tf.global_variables_initializer() with tf.Session() as sess: sess.run(init) for epoch in range(6): for batch in range(n_batch): batch_xs,batch_ys = mnist.train.next_batch(batch_size) sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys}) acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels}) print ("Iter " + str(epoch) + ", Testing Accuracy= " + str(acc))