本文主要是介绍tensorflow使用DNN、CNN、RNN(lstm)分别实现识别mnist手写数字图片,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!
一、DNN结构实现mnist手写数字图片
import os
import struct
import numpy as np
import tensorflow as tf#数据加载函数
def load_mnist(path, kind='train'):"""load mnist dateArgs:path: date pathkind: train or testReturns:images and labels"""labels_path = os.path.join(path,'%s-labels.idx1-ubyte'% kind) #标签数据images_path = os.path.join(path,'%s-images.idx3-ubyte'% kind) #图像数据with open(labels_path, 'rb') as lbpath:magic, n = struct.unpack('>II',lbpath.read(8))labels = np.fromfile(lbpath,dtype=np.uint8)with open(images_path, 'rb') as imgpath:magic, num, rows, cols = struct.unpack('>IIII',imgpath.read(16))images = np.fromfile(imgpath,dtype=np.uint8).reshape(len(labels), 784)return images, labels#将label进行one-hot处理
def y_onehot(y):"""one-hot optionArgs:y: labelsReturns:one-hot labeleg:1->[0,1,0,0,0,0,0,0,0]"""n_class = 10y_labels = np.eye(n_class)[y]return y_labels#超参
Epoch=100
batch_size=256
learning_rate=0.05x=tf.placeholder(tf.float32, [None, 784])
y=tf.placeholder(tf.float32, [None, 10])
is_train = tf.placeholder(tf.bool) #BatchNorm 参数
keep_prob = tf.placeholder(tf.float32) #dropout参数W_fc1 = tf.Variable(tf.truncated_normal(shape=[784, 1024], stddev=0.1), name="W_fc1")
b_fc1 = tf.Variable(tf.constant(0.01, shape=[1024]), name="b_fc1")W_fc2 = tf.Variable(tf.truncated_normal(shape=[1024, 512], stddev=0.1), name="W_fc2")
b_fc2 = tf.Variable(tf.constant(0.01, shape=[512]), name="b_fc2")W_fc3 = tf.Variable(tf.truncated_normal(shape=[512, 10], stddev=0.1), name="W_fc3")
b_fc3 = tf.Variable(tf.constant(0.01, shape=[10]), name="b_fc3")def minist_dnn(x, is_train, keep_prob, W_fc1, b_fc1, W_fc2, b_fc2):layer1 = tf.add(tf.matmul(x, W_fc1), b_fc1)layer1_bn = tf.layers.batch_normalization(layer1, training=is_train) #BN层layer1_relu = tf.nn.relu(layer1_bn)#一般添加了BN层就不添加dropout,添加了dropout就不添加BN,这一层只使用dropoutlayer2 = tf.add(tf.matmul(layer1_relu, W_fc2), b_fc2)layer2_relu = tf.nn.relu(layer2)layer2_drop = tf.nn.dropout(layer2_relu, keep_prob) #dropout层layer3 = tf.add(tf.matmul(layer2_drop, W_fc3), b_fc3)pred = tf.nn.softmax(layer3)return predpred = minist_dnn(x, is_train, keep_prob, W_fc1, b_fc1, W_fc2, b_fc2)
loss = -tf.reduce_mean(y*tf.log(tf.clip_by_value(pred, 1e-8, 1)))
correct_prediction = tf.equal(tf.arg_max(y, 1), tf.arg_max(pred,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
train_op=optimizer.minimize(loss)init = tf.global_variables_initializer()
saver = tf.train.Saver(tf.global_variables())path = 'D:/data/mnist/'
X_train, y_train = load_mnist(path, kind='train') #训练集
y_train_labels = y_onehot(y_train)with tf.Session() as sess:sess.run(init)total_batch = int(len(X_train)/batch_size)for step in range(Epoch):for i in range(1,total_batch):batch_x = X_train[(i-1)*batch_size: i*batch_size]batch_y = y_train_labels[(i-1)*batch_size: i*batch_size]sess.run(train_op,feed_dict={x:batch_x, y:batch_y, is_train:True, keep_prob:0.5})entropy ,acc = sess.run([loss, accuracy], feed_dict={x:X_train[0:1000], y:y_train_labels[0:1000], is_train:False, keep_prob:1})print('step{} loss=============>:{:.4f}, auc===========> {:.4f}'.format(step, entropy, acc) )print ("Optimization Finished!")
二、CNN结构实现mnist手写数字图片
import os
import struct
import numpy as np
import tensorflow as tftf.reset_default_graph() #清空计算图#数据加载函数
def load_mnist(path, kind='train'):"""load mnist dateArgs:path: date pathkind: train or testReturns:images and labels"""labels_path = os.path.join(path,'%s-labels.idx1-ubyte'% kind) #标签数据images_path = os.path.join(path,'%s-images.idx3-ubyte'% kind) #图像数据with open(labels_path, 'rb') as lbpath:magic, n = struct.unpack('>II',lbpath.read(8))labels = np.fromfile(lbpath,dtype=np.uint8)with open(images_path, 'rb') as imgpath:magic, num, rows, cols = struct.unpack('>IIII',imgpath.read(16))images = np.fromfile(imgpath,dtype=np.uint8).reshape(len(labels), 784)return images, labels#将label进行one-hot处理
def y_onehot(y):"""one-hot optionArgs:y: labelsReturns:one-hot labeleg:1->[0,1,0,0,0,0,0,0,0]"""n_class = 10y_labels = np.eye(n_class)[y]return y_labels#超参
Epoch=100
batch_size=256
learning_rate=0.001x= tf.placeholder(tf.float32, [None, 784]) #x
y=tf.placeholder(tf.float32, [None, 10]) #y
keep_prob = tf.placeholder(tf.float32) #用于空值dropout概率def mnist_cnn(x, keep_prob):x_image=tf.reshape(x, [-1,28,28,1]) #将数据变为28*28形状#第一层卷积with tf.variable_scope("conv_pool1"):W_conv1 = tf.get_variable("weights",[5,5,1,32], initializer = tf.truncated_normal_initializer(stddev=0.1)) #第一层卷积参数,fileter尺寸为5*5,输入通道为1,输出通道为32b_conv1 = tf.get_variable("bias",[32], initializer = tf.constant_initializer(0.01)) #第一层偏置项,输出的每一个通道通会加一个bias,总共加32个h_conv1=tf.nn.conv2d(x_image, filter= W_conv1, strides=[1,1,1,1], padding="SAME") #第一层卷积,stride为移动步长h_conv1_relu = tf.nn.relu(h_conv1+b_conv1) #激活函数,注意tf.nn.conv2d不带激活函数,tf.layers.conv2d参数可以指定激活函数h_pooling1 = tf.nn.max_pool(h_conv1_relu, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') #ksize为pooling核大小,pooling后变为(?, 14, 14, 32)#第二层卷积with tf.variable_scope("conv_pool2"):W_conv2 = tf.get_variable("weights",[5,5,32,64], initializer = tf.truncated_normal_initializer(stddev=0.1)) #第一层卷积参数,fileter尺寸为5*5,输入通道为1,输出通道为32b_conv2 = tf.get_variable("bias",[64], initializer = tf.constant_initializer(0.01)) #第一层偏置项,输出的每一个通道通会加一个bias,总共加32个h_conv2=tf.nn.conv2d(h_pooling1, filter= W_conv2, strides=[1,1,1,1], padding="SAME") #第一层卷积,stride为移动步长h_conv2_relu = tf.nn.relu(h_conv2+b_conv2) #激活函数,注意tf.nn.conv2d不带激活函数,tf.layers.conv2d参数可以指定激活函数h_pooling2 = tf.nn.max_pool(h_conv2_relu, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') #ksize为pooling核大小,pooling后变为(?, 14, 14, 32)pool_shape = h_pooling2.get_shape().as_list() #获得h_pooling2的维度,为[batch_size, wide, height, channel]h_pooling2_flat = tf.reshape(h_pooling2, [-1, pool_shape[1]*pool_shape[2]*pool_shape[3]]) #对pooling2一维展开#全连接with tf.variable_scope("fc1"):W_fc1 = tf.get_variable("weights",[pool_shape[1]*pool_shape[2]*pool_shape[3], 1024], initializer = tf.truncated_normal_initializer(stddev=0.1)) #全连接层权重,因为经过两层pooling,图片由28*28变为14*14,再变为7*7, 所以输入神经元为7*7*64b_fc1 = tf.get_variable("bias",[1024], initializer = tf.constant_initializer(0.01)) #h_pooling2 = tf.layers.flatten(h_pooling2) #对pooling2一维展开fc1 = tf.add(tf.matmul(h_pooling2_flat, W_fc1), b_fc1) #第一层全连接fc1_relu = tf.nn.relu(fc1)fc1_drop = tf.nn.dropout(fc1_relu, keep_prob) #dropout层#输出层with tf.variable_scope("output"):W_fc2 = tf.get_variable("weights",[1024, 10], initializer = tf.truncated_normal_initializer(stddev=0.1)) #全连接层权重,因为最终判断为10维,所以最终神经元为10个b_fc2 = tf.get_variable("bias",[10], initializer = tf.constant_initializer(0.01)) output = tf.add(tf.matmul(fc1_drop, W_fc2), b_fc2) #第二层全连接pred = tf.nn.softmax(output)return predpred = mnist_cnn(x, keep_prob) #带入函数
loss = -tf.reduce_mean(y*tf.log(tf.clip_by_value(pred,1e-11,1.0)))
correct_prediction = tf.equal(tf.argmax(pred,1), tf.argmax(y,1)) #判断预测准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) #准确率#可以加正则化损失
#loss = loss+ 0.001*tf.nn.l2_loss(W_fc1)
#optimizer = tf.compat.v1.train.AdamOptimizer(learning_rate)
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate) #用梯度下降求解
train_op=optimizer.minimize(loss)init = tf.global_variables_initializer()
saver = tf.train.Saver(tf.global_variables())
#saver = tf.compat.v1.train.Saver(tf.compat.v1.global_variables())#with tf.Session() as sess:
# print(accuracy)path = 'D:/data/mnist/'
X_train, y_train = load_mnist(path, kind='train') #训练集
y_train_labels = y_onehot(y_train)with tf.Session() as sess:sess.run(init)total_batch = int(len(X_train)/batch_size)for step in range(Epoch):for i in range(1,total_batch):batch_x = X_train[(i-1)*batch_size: i*batch_size]batch_y = y_train_labels[(i-1)*batch_size: i*batch_size]sess.run(train_op,feed_dict={x:batch_x, y:batch_y, keep_prob:0.5})#saver.save(sess, 'D:/data/mnist/cnn_mnist.module', global_step=step) #保存模型entropy ,acc = sess.run([loss, accuracy], feed_dict={x:X_train[0:1000], y:y_train_labels[0:1000], keep_prob:1})print('step{} loss=============>:{:.4f}, auc===========> {:.4f}'.format(step, entropy, acc) )print ("Optimization Finished!")
三、LSTM结构实现mnist手写数字图片
import os
import struct
import numpy as np
import tensorflow as tftf.reset_default_graph() #清空计算图#数据加载函数
def load_mnist(path, kind='train'):"""load mnist dateArgs:path: date pathkind: train or testReturns:images and labels"""labels_path = os.path.join(path,'%s-labels.idx1-ubyte'% kind) #标签数据images_path = os.path.join(path,'%s-images.idx3-ubyte'% kind) #图像数据with open(labels_path, 'rb') as lbpath:magic, n = struct.unpack('>II',lbpath.read(8))labels = np.fromfile(lbpath,dtype=np.uint8)with open(images_path, 'rb') as imgpath:magic, num, rows, cols = struct.unpack('>IIII',imgpath.read(16))images = np.fromfile(imgpath,dtype=np.uint8).reshape(len(labels), 784)return images, labels#将label进行one-hot处理
def y_onehot(y):"""one-hot optionArgs:y: labelsReturns:one-hot labeleg:1->[0,1,0,0,0,0,0,0,0]"""n_class = 10y_labels = np.eye(n_class)[y]return y_labels#超参
Epoch=100
learning_rate=0.05
timestep=28 #特征序列长度,对应隐藏层ht个数
num_input=28 #特征维度,共28维。图像每一行可以看做一个维度特征,共28维
lstm_hidden_size=64 #lstm隐藏层神经元个数
num_of_layers = 2 #lstm的层数x= tf.placeholder(tf.float32, [None, 784]) #x
y=tf.placeholder(tf.float32, [None, 10]) #y
lstm_keep_prob = tf.placeholder(tf.float32)
keep_prob = tf.placeholder(tf.float32) #用于空值dropout概率
batch_size = tf.placeholder(tf.int32, []) #一个批次数据,训练集是使用256,预测时使用1000,[]表示是一个Scalardef mnist_lstm(x, lstm_keep_prob, keep_prob, batch_size):x_image = tf.reshape(x, [-1,timestep, num_input]) #将数据序列长度*特征维度with tf.variable_scope("lstmlayer"):#创建lstm结构,ht神经元个数为64,,可推测出,一个门的参数个数为64*(64+28)+64, (64+28)表示ht-1与xt拼接的维度#为lstm创建dropout,有两个参数,训练时,input_keep_prob,一般设置为1,out_keep_prob一般设置为0.5#创建num_of_layers层lstm,不能用[lstm]*N,否则每层lstm参数会共享#注意lstm,dropout和多层MultiRNNCell必须放在一起调用,否则会出现维度错误stacked_lstm = tf.nn.rnn_cell.MultiRNNCell([tf.nn.rnn_cell.DropoutWrapper(tf.nn.rnn_cell.BasicLSTMCell(lstm_hidden_size), input_keep_prob=1, output_keep_prob =lstm_keep_prob ) for _ in range(num_of_layers)]) init_state = stacked_lstm.zero_state(batch_size, dtype=tf.float32)#计算前项lstm层的输出, 两个输出,一个记录ht,一个记录ctlstm_outputs, _ = tf.nn.dynamic_rnn(stacked_lstm, x_image, initial_state=init_state, dtype=tf.float32)#我们支取最后一个输出状态ht进行下一步的预测lstm_output = lstm_outputs[:,-1,:]with tf.variable_scope("fc1"):W_fc1 = tf.get_variable('weight', shape=[lstm_hidden_size, 10], initializer = tf.truncated_normal_initializer(stddev=0.1), dtype=tf.float32)b_fc1 = tf.get_variable('bias', shape=[10], initializer = tf.constant_initializer(0.1), dtype=tf.float32)output = tf.add(tf.matmul(lstm_output, W_fc1), b_fc1) #第一层全连接pred = tf.nn.softmax(output)return predpred = mnist_lstm(x, lstm_keep_prob, keep_prob, batch_size) #带入函数
loss = -tf.reduce_mean(y*tf.log(tf.clip_by_value(pred,1e-11,1.0)))
correct_prediction = tf.equal(tf.argmax(pred,1), tf.argmax(y,1)) #判断预测准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) #准确率#可以加正则化损失
#loss = loss+ 0.001*tf.nn.l2_loss(W_fc1)
#optimizer = tf.compat.v1.train.AdamOptimizer(learning_rate)
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate) #用梯度下降求解
train_op=optimizer.minimize(loss)init = tf.global_variables_initializer()
#saver = tf.train.Saver(tf.global_variables())path = 'D:/data/mnist/'
X_train, y_train = load_mnist(path, kind='train') #训练集
y_train_labels = y_onehot(y_train)with tf.Session() as sess:sess.run(init)total_batch = int(len(X_train)/256)for step in range(Epoch):for i in range(1,total_batch):batch_x = X_train[(i-1)*256: i*256]batch_y = y_train_labels[(i-1)*256: i*256]sess.run(train_op,feed_dict={x:batch_x, y:batch_y, lstm_keep_prob:0.5, keep_prob:0.5, batch_size:256})#saver.save(sess, 'D:/data/mnist/cnn_mnist.module', global_step=step) #保存模型entropy ,acc = sess.run([loss, accuracy], feed_dict={x:X_train[0:1000], y:y_train_labels[0:1000], lstm_keep_prob:1, keep_prob:1, batch_size:1000})print('step{} loss=============>:{:.4f}, auc===========> {:.4f}'.format(step, entropy, acc) )print ("Optimization Finished!")
这篇关于tensorflow使用DNN、CNN、RNN(lstm)分别实现识别mnist手写数字图片的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!