TF之DNN：對DNN神經網絡進行Tensorboard可視化(得到events.out.tfevents本地伺服器輸出到網頁可視化）

輸出結果

代碼設計

import tensorflow as tf

import numpy as np    

def add_layer(inputs, in_size, out_size, n_layer, activation_function=None):

   # add one more layer and return the output of this layer

   layer_name = 'layer%s' % n_layer

   with tf.name_scope(layer_name):

       with tf.name_scope('Jason_niu_weights'):

           Weights = tf.Variable(tf.random_normal([in_size, out_size]), name='W')

           tf.summary.histogram(layer_name + '/weights', Weights)

       with tf.name_scope('Jason_niu_biases'):

           biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, name='b')

           tf.summary.histogram(layer_name + '/biases', biases)

       with tf.name_scope('Jason_niu_Wx_plus_b'):

           Wx_plus_b = tf.add(tf.matmul(inputs, Weights), biases)

       if activation_function is None:

           outputs = Wx_plus_b

       else:

           outputs = activation_function(Wx_plus_b, )

       tf.summary.histogram(layer_name + '/outputs', outputs)

       return outputs

# Make up some real data

x_data = np.linspace(-1, 1, 300)[:, np.newaxis]

noise = np.random.normal(0, 0.05, x_data.shape)

y_data = np.square(x_data) - 0.5 + noise

# define placeholder for inputs to network

with tf.name_scope('Jason_niu_inputs'):

   xs = tf.placeholder(tf.float32, [None, 1], name='x_input')

   ys = tf.placeholder(tf.float32, [None, 1], name='y_input')

# add hidden layer

l1 = add_layer(xs, 1, 10, n_layer=1, activation_function=tf.nn.relu)

# add output layer

prediction = add_layer(l1, 10, 1, n_layer=2, activation_function=None)

# the error between prediciton and real data

with tf.name_scope('Jason_niu_loss'):

   loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),

                                       reduction_indices=[1]))

   tf.summary.scalar('Jason_niu_loss', loss)  

with tf.name_scope('Jason_niu_train'):

   train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

sess = tf.Session()

merged =  tf.summary.merge_all()  

writer = tf.summary.FileWriter("logs3/", sess.graph)

# important step

sess.run(tf.global_variables_initializer())

for i in range(1000):  

   sess.run(train_step, feed_dict={xs: x_data, ys: y_data})

   if i % 50 == 0:                                          

       result = sess.run(merged,feed_dict={xs: x_data, ys: y_data})

       writer.add_summary(result, i)