TensorFlow过程可视化--不同版本引起的错误

Tensorflow 运行过程的可视化：

## 可视化好帮手 ##

import tensorflow as tf
import numpy as np

def add_layer(inputs,in_size,out_size,n_layer,activation_function=None):
    layer_name = 'layer%s'%n_layer                                         ##给定一个层的命名
    with tf.name_scope('layer_name'):
        with tf.name_scope('weights'):
            Weights = tf.Variable(tf.random_normal([in_size,out_size]))
            tf.summary.histogram(layer_name+'/weights',Weights)                             ###以直方图形式画出-summary.histogram
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1,out_size]) + 0.1,name='b')
            tf.summary.histogram(layer_name+'/biases',biases)                               ###---------------
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = 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

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
with tf.name_scope('inputs'):
    xs = tf.placeholder(tf.float32,[None,1],name='x_data')
    ys = tf.placeholder(tf.float32,[None,1],name='y_data')

l1 = add_layer(xs,1,10,n_layer=1,activation_function=tf.nn.relu)
prediction = add_layer(l1, 10,1,n_layer=2,activation_function=None)

#tf.reduce_mean() --取平均数；tf.reduce_sum(  ,reduction_indices=[1]) --求和；
with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),
                                        reduction_indices=[1]))
    tf.summary.scalar('loss',loss)                       #以标量图给出EVENTS中展示，若换在HISTOGRAMS中展示就用tf.summary.histogram 格式。
with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

sess = tf.Session()
merged = summary_op = tf.summary.merge_all()
writer = tf.summary.FileWriter("F://logs",sess.graph)
sess.run(tf.initialize_all_variables())
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)

学习可视化时，由于Python 的版本不同代码运行时出了不少格式的错误：查找资料修改结果整理如下。

    

1. AttributeError: 'module' object has no attribute 'merge_all_summaries'

>> tf.merge_all_summaries() 改为：summary_op = tf.summary.merge_all()

2. AttributeError: 'module' object has no attribute 'SummaryWriter'

>> tf.train.SummaryWriter 改为：tf.summary.FileWriter

3. AttributeError: 'module' object has no attribute 'scalar_summary'

>> tf.scalar_summary 改为：tf.summary.scalar

4. AttributeError: 'module' object has no attribute 'histogram_summary'

>> histogram_summary 改为：tf.summary.histogram

TypeError: zeros_initializer() takes at least 1 argument (0 given)

>> 将 biases_initializer=tf.zeros_initializer() 改为：biases_initializer=tf.zeros_initializer
根据上一节中提到的方法进入tensorboard界面：查看结果对应图谱。