[TensorFlow]入门学习笔记(6)-Tensorboard简易教程和模型保存

模型保存

tf.train.Saver()

The Saver class adds ops to save and restore variables to and from checkpoints. It also provides convenience methods to run these ops.

两个重要的函数。
一个是saver.save() 将某个session中的模型和参数都保存在save-path,并且后面是迭代次数。

而对于restrore()函数，我认为理解恢复操作的最好方法是将它简单的看做是一种数据初始化操作，就是讲之前的session中的数据完整的init出来，在当前的session中。

# -*- coding: UTF-8 -*from tensorflow.examples.tutorials.mnist import input_dataimport tensorflow as tfmnist = input_data.read_data_sets("MNIST_data/",one_hot=True)learning_rate = 0.001batch_size = 100display_step = 1model_path = "../tmp/model.ckpt"n_hidden_1 = 256n_hidden_2 = 256n_input = 784n_classes = 10x = tf.placeholder(tf.float32,[None,n_input])y = tf.placeholder(tf.float32,[None,n_classes])weights = {    'h1':tf.Variable(tf.random_normal([n_input,n_hidden_1])),    'h2':tf.Variable(tf.random_normal([n_hidden_1,n_hidden_2])),    'out':tf.Variable(tf.random_normal([n_hidden_2,n_classes]))}biases = {    'b1':tf.Variable(tf.random_normal([n_hidden_1])),    'b2':tf.Variable(tf.random_normal([n_hidden_2])),    'out':tf.Variable(tf.random_normal([n_classes]))}#构建模型def multilayer_preceptron(x,weights,biases):    #hidden 1 with relu activation    layer_1 = tf.add(tf.matmul(x,weights['h1']),biases['b1'])    layer_1 = tf.nn.relu(layer_1)    #hidden 2 with relu activation    layer_2 = tf.add(tf.matmul(layer_1,weights['h2']),biases['b2'])    layer_2 = tf.nn.relu(layer_2)    #output layer with linear activation    out_layer = tf.matmul(layer_2,weights['out'])+biases['out']    return out_layerpred = multilayer_preceptron(x,weights,biases)cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred,labels=y))optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)init = tf.global_variables_initializer()saver = tf.train.Saver()print "Starting 1st session..."if __name__ == '__main__':    with tf.Session() as sess:        #init variables        sess.run(init)        for epoch in range(3):            avg_cost = 0            total_batch = int(mnist.train.num_examples/batch_size)            #loop            for i in range(total_batch):                batch_x,batch_y = mnist.train.next_batch(batch_size)                _,c = sess.run([optimizer,cost],feed_dict={                    x:batch_x,                    y:batch_y                })                avg_cost += c/total_batch            if epoch % display_step == 0:                print "Epoch:", '%04d' % (epoch + 1), "cost=", \                    "{:.9f}".format(avg_cost)        print "First Optimization Finished!"        # Test model        correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))        # Calculate accuracy        accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))        print "Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels})        # Save model weights to disk        save_path = saver.save(sess, model_path)        print "Model saved in file: %s" % save_path    #running a new session..    with tf.Session() as sess:        sess.run(init)        #理解恢复操作的最好方法是将它简单的看做是一种数据初始化操作        load_path = saver.restore(sess,model_path)        print "Model restored from file:%s"%save_path        for epoch in range(7):            avg_cost = 0            total_batch = int(mnist.train.num_examples/batch_size)            #loop            for i in range(total_batch):                batch_x,batch_y = mnist.train.next_batch(batch_size)                _,c = sess.run([optimizer,cost],feed_dict={                    x:batch_x,                    y:batch_y                })                avg_cost += c/total_batch            if epoch % display_step == 0:                print "Epoch:", '%04d' % (epoch + 1), "cost=", \                    "{:.9f}".format(avg_cost)        print "Second Optimization Finished!"        # Test model        correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))        # Calculate accuracy        accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))        print "Accuracy:", accuracy.eval(            {x: mnist.test.images, y: mnist.test.labels})

TensorBoard

tf.summary.scalar() 将记录要显示的变量，在tensorboard中显示，所有的summary也相当于op,定义完scalar后，将他们merge所有的op为一个组合。

在session函数迭代里面，run()出函数。

summary_writer = tf.summary.FileWriter(logs_path,graph=tf.get_default_graph())
写函数将所有的参数保存在log中，便于我们调用。

然后在迭代里面讲当前的summary op ，add进写文件。

最后，在终端里面，tensorboard –logdit=”“

打开http://127.0.0.0:6006/ into your web browser

basic model

# -*- coding: UTF-8 -*import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("MNIST_data/",one_hot=True)learning_rate = 0.01training_epochs = 25batch_size = 100display_step = 1logs_path = '../tmp/tensorflow_logs/example'x = tf.placeholder(tf.float32,[None,784],name='InputData')y = tf.placeholder(tf.float32,[None,10],name='LabelData')w = tf.Variable(tf.zeros([784,10]),name='Weights')b = tf.Variable(tf.zeros([10]),name='Bias')with tf.name_scope('Model'):    pred = tf.nn.softmax(tf.matmul(x,w)+b)with tf.name_scope('Loss'):    cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred), reduction_indices=1))with tf.name_scope('SGD'):    optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)with tf.name_scope('Accuracy'):    acc = tf.equal(tf.argmax(pred,1),tf.argmax(y,1))    acc = tf.reduce_mean(tf.cast(acc,tf.float32))init = tf.global_variables_initializer()tf.summary.scalar("loss",cost)tf.summary.scalar("accuracy",acc)merged_summary_op = tf.summary.merge_all()with tf.Session() as sess:    sess.run(init)    summary_writer = tf.summary.FileWriter(logs_path,graph=tf.get_default_graph())    for epoch in range(training_epochs):        avg_cost = 0        total_batch = int(mnist.train.num_examples/batch_size)        #loop        for i in range(total_batch):            batch_xs,batch_ys = mnist.train.next_batch(batch_size)            _,c,summary = sess.run([optimizer,cost,merged_summary_op],                                   feed_dict={x:batch_xs,y:batch_ys})            summary_writer.add_summary(summary,(epoch)*total_batch+i)            avg_cost+=c/total_batch        if (epoch + 1) % display_step == 0:            print "Epoch:", '%04d' % (epoch + 1), "cost=", "{:.9f}".format(avg_cost)    print "Optimization Finished!"    # Test model    # Calculate accuracy    print "Accuracy:", acc.eval({x: mnist.test.images, y: mnist.test.labels})    print "Run the command line:\n" \          "--> tensorboard --logdir=/tmp/tensorflow_logs " \          "\nThen open http://127.0.0.0:6006/ into your web browser"

升级版的Tensorboard

# -*- coding: UTF-8 -*import tensorflow as tf# Import MNIST datafrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("MNIST_data/", one_hot=True)# Parameterslearning_rate = 0.01training_epochs = 10batch_size = 100display_step = 1logs_path = '../tmp/tensorflow_logs/example2'# Network Parametersn_hidden_1 = 20 # 1st layer number of featuresn_hidden_2 = 40 # 2nd layer number of featuresn_input = 784 # MNIST data input (img shape: 28*28)n_classes = 10 # MNIST total classes (0-9 digits)# tf Graph Input# mnist data image of shape 28*28=784x = tf.placeholder(tf.float32, [None, 784], name='InputData')# 0-9 digits recognition => 10 classesy = tf.placeholder(tf.float32, [None, 10], name='LabelData')#使用tf.summary.scalar记录标量# 使用tf.summary.histogram记录数据的直方图# 使用tf.summary.distribution记录数据的分布图# 使用tf.summary.image记录图像数据# Create modeldef multilayer_perceptron(x, weights, biases):    # Hidden layer with RELU activation    layer_1 = tf.add(tf.matmul(x, weights['w1']), biases['b1'])    layer_1 = tf.nn.relu(layer_1)    # Create a summary to visualize the first layer ReLU activation    tf.summary.histogram("relu1", layer_1)    # Hidden layer with RELU activation    layer_2 = tf.add(tf.matmul(layer_1, weights['w2']), biases['b2'])    layer_2 = tf.nn.relu(layer_2)    # Create another summary to visualize the second layer ReLU activation    tf.summary.histogram("relu2", layer_2)    # Output layer    out_layer = tf.add(tf.matmul(layer_2, weights['w3']), biases['b3'])    return out_layer# Store layers weight & biasweights = {    'w1': tf.Variable(tf.random_normal([n_input, n_hidden_1]), name='W1'),    'w2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2]), name='W2'),    'w3': tf.Variable(tf.random_normal([n_hidden_2, n_classes]), name='W3')}biases = {    'b1': tf.Variable(tf.random_normal([n_hidden_1]), name='b1'),    'b2': tf.Variable(tf.random_normal([n_hidden_2]), name='b2'),    'b3': tf.Variable(tf.random_normal([n_classes]), name='b3')}# Encapsulating all ops into scopes, making Tensorboard's Graph# Visualization more convenientwith tf.name_scope('Model'):    # Build model    pred = multilayer_perceptron(x, weights, biases)with tf.name_scope('Loss'):    # Softmax Cross entropy (cost function)    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))with tf.name_scope('SGD'):    # Gradient Descent    optimizer = tf.train.GradientDescentOptimizer(learning_rate)    # Op to calculate every variable gradient    grads = tf.gradients(loss, tf.trainable_variables())    grads = list(zip(grads, tf.trainable_variables()))    # Op to update all variables according to their gradient    apply_grads = optimizer.apply_gradients(grads_and_vars=grads)with tf.name_scope('Accuracy'):    # Accuracy    acc = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))    acc = tf.reduce_mean(tf.cast(acc, tf.float32))# Initializing the variablesinit = tf.global_variables_initializer()# Create a summary to monitor cost tensortf.summary.scalar("loss", loss)# Create a summary to monitor accuracy tensortf.summary.scalar("accuracy", acc)# Create summaries to visualize weightsfor var in tf.trainable_variables():    tf.summary.histogram(var.name, var)# Summarize all gradientsfor grad, var in grads:    tf.summary.histogram(var.name + '/gradient', grad)# Merge all summaries into a single opmerged_summary_op = tf.summary.merge_all()# Launch the graphwith tf.Session() as sess:    sess.run(init)    # op to write logs to Tensorboard    summary_writer = tf.summary.FileWriter(logs_path,                                            graph=tf.get_default_graph())    # Training cycle    for epoch in range(training_epochs):        avg_cost = 0.        total_batch = int(mnist.train.num_examples/batch_size)        # Loop over all batches        for i in range(total_batch):            batch_xs, batch_ys = mnist.train.next_batch(batch_size)            # Run optimization op (backprop), cost op (to get loss value)            # and summary nodes            _, c, summary = sess.run([apply_grads, loss, merged_summary_op],                                     feed_dict={x: batch_xs, y: batch_ys})            # Write logs at every iteration            summary_writer.add_summary(summary, epoch * total_batch + i)            # Compute average loss            avg_cost += c / total_batch        # Display logs per epoch step        if (epoch+1) % display_step == 0:            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))    print("Optimization Finished!")    # Test model    # Calculate accuracy    print("Accuracy:", acc.eval({x: mnist.test.images, y: mnist.test.labels}))    print("Run the command line:\n" \          "--> tensorboard --logdir=/tmp/tensorflow_logs " \          "\nThen open http://0.0.0.0:6006/ into your web browser")