tensorflow(四)：简单神经网络数据可视化，用tensorboard

一、准备神经网络程序

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)
# 每个批次的大小
batch_size = 100
# 计算一共有多少批次
n_batch = mnist.train.num_examples // batch_size
# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
# 创建一个简单的神经网络
W_1 = tf.Variable(tf.truncated_normal([784, 2000], stddev=0.1))
b_1 = tf.Variable(tf.zeros([2000]) + 0.1)
L_1 = tf.nn.relu(tf.matmul(x, W_1) + b_1)
L1_drop=tf.nn.dropout(L_1, keep_prob)

W2=tf.Variable(tf.truncated_normal([2000,1000],stddev=0.1))
b2=tf.Variable(tf.zeros([1000]) + 0.1)
L2=tf.nn.tanh(tf.matmul(L1_drop, W2)+b2)
L2_drop=tf.nn.dropout(L2, keep_prob)

W_3 = tf.Variable(tf.truncated_normal([1000,10],stddev=0.1))
b_3 = tf.Variable(tf.zeros([10]) + 0.1)
prediction = tf.nn.softmax(tf.matmul(L2_drop,W_3) + b_3)

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
train_step = tf.train.MomentumOptimizer(0.2,0.9).minimize(loss)

# 初始化变量
init = tf.global_variables_initializer()

# 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))

gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.333)
with tf.Session() as sess:
    sess.run(init)
    for epoch in range(50):
        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:0.5})
        test_acc=sess.run(accuracy,feed_dict={x:mnist.test.images, y:mnist.test.labels,keep_prob:0.1})
        train_acc=sess.run(accuracy,feed_dict={x:mnist.train.images, y:mnist.train.labels,keep_prob:1.0})
        print("Iter"+str(epoch)+",Testing Accuracy "+str(test_acc)+"Training Accuracy "+str(train_acc))

二、添加命名空间

          添加类似 with tf.name_scope("input")的代码，定义命名空间。如下，添加了4行with

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)
# 每个批次的大小
batch_size = 100
# 计算一共有多少批次
n_batch = mnist.train.num_examples // batch_size
# 定义两个placeholder
with tf.name_scope("input"):
    x = tf.placeholder(tf.float32, [None, 784])
    y = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
# 创建一个简单的神经网络
with tf.name_scope("layer1"):
    W_1 = tf.Variable(tf.truncated_normal([784, 2000], stddev=0.1))
    b_1 = tf.Variable(tf.zeros([2000]) + 0.1)
    L_1 = tf.nn.relu(tf.matmul(x, W_1) + b_1)
    L1_drop=tf.nn.dropout(L_1, keep_prob)
with tf.name_scope("layer2"):
    W2=tf.Variable(tf.truncated_normal([2000,1000],stddev=0.1))
    b2=tf.Variable(tf.zeros([1000]) + 0.1)
    L2=tf.nn.tanh(tf.matmul(L1_drop, W2)+b2)
    L2_drop=tf.nn.dropout(L2, keep_prob)
with tf.name_scope("output"):
    W_3 = tf.Variable(tf.truncated_normal([1000,10],stddev=0.1))
    b_3 = tf.Variable(tf.zeros([10]) + 0.1)
prediction = tf.nn.softmax(tf.matmul(L2_drop,W_3) + b_3)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
train_step = tf.train.MomentumOptimizer(0.2,0.9).minimize(loss)
# 初始化变量
init = tf.global_variables_initializer()
# 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))
gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.333)
with tf.Session() as sess:
    sess.run(init)
    for epoch in range(50):
        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:0.5})
        test_acc=sess.run(accuracy,feed_dict={x:mnist.test.images, y:mnist.test.labels,keep_prob:0.1})
        train_acc=sess.run(accuracy,feed_dict={x:mnist.train.images, y:mnist.train.labels,keep_prob:1.0})
        print("Iter"+str(epoch)+",Testing Accuracy "+str(test_acc)+"Training Accuracy "+str(train_acc))

 三、添加summary

     添加各种summary

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

def varibale_summary(var):
    with tf.name_scope("summary"):
        mean = tf.reduce_mean(var)
        tf.summary.scalar("mean", mean)
        stddev = tf.sqrt(tf.reduce_mean(tf.square(var-mean)))
        tf.summary.scalar("stddev", stddev)
        tf.summary.scalar("max", tf.reduce_max(var))
        tf.summary.scalar("min", tf.reduce_min(var))
        tf.summary.histogram("histogram", var)
# 载入数据集
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
# 每个批次的大小
batch_size = 100
# 计算一共有多少批次
n_batch = mnist.train.num_examples // batch_size
# 定义两个placeholder
with tf.name_scope("input"):
    x = tf.placeholder(tf.float32, [None, 784])
    y = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
# 创建一个简单的神经网络
with tf.name_scope("layer1"):
    W_1 = tf.Variable(tf.truncated_normal([784, 2000], stddev=0.1))
    b_1 = tf.Variable(tf.zeros([2000]) + 0.1)
    L_1 = tf.nn.relu(tf.matmul(x, W_1) + b_1)
    L1_drop=tf.nn.dropout(L_1, keep_prob)
    varibale_summary(W_1)
    varibale_summary(b_1)
with tf.name_scope("layer2"):
    W2=tf.Variable(tf.truncated_normal([2000,1000],stddev=0.1))
    b2=tf.Variable(tf.zeros([1000]) + 0.1)
    L2=tf.nn.tanh(tf.matmul(L1_drop, W2)+b2)
    L2_drop=tf.nn.dropout(L2, keep_prob)
    varibale_summary(W2)
    varibale_summary(b2)
with tf.name_scope("output"):
    W_3 = tf.Variable(tf.truncated_normal([1000,10],stddev=0.1))
    b_3 = tf.Variable(tf.zeros([10]) + 0.1)
    varibale_summary(W_3)
    varibale_summary(b_3)
    prediction = tf.nn.softmax(tf.matmul(L2_drop,W_3) + b_3)
with tf.name_scope("loss"):
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
    tf.summary.scalar("loss", loss)
with tf.name_scope("train"):
    train_step = tf.train.MomentumOptimizer(0.2,0.9).minimize(loss)
# 初始化变量
init = tf.global_variables_initializer()
with tf.name_scope("accurary"):
    # 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))
    tf.summary.scalar("accurary", accuracy)
merged = tf.summary.merge_all()
with tf.Session() as sess:
    sess.run(init)
    writer = tf.summary.FileWriter("logs/", sess.graph)
    for epoch in range(5):
        for batch in range(n_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            _summary, _ = sess.run([merged, train_step], feed_dict={x: batch_xs, y: batch_ys, keep_prob:0.5})
        writer.add_summary(_summary, epoch)
        test_acc=sess.run(accuracy,feed_dict={x:mnist.test.images, y:mnist.test.labels,keep_prob:0.1})
        train_acc=sess.run(accuracy,feed_dict={x:mnist.train.images, y:mnist.train.labels,keep_prob:1.0})
        print("Iter"+str(epoch)+",Testing Accuracy "+str(test_acc)+"Training Accuracy "+str(train_acc))

四、CMD终端启动 

tensorboard --logdir=F:\code\MINST_test\logs

输入命令行以后，控制台会输出网址，浏览器打开即可。