Tensorboard

Tensorboard

import tensorflow as tf
import numpy as np


def addlayer(inputs, insize, outsize, activation_function=None):
    #add one more layer and return the output of this layer
    with tf.name_scope('layer'):
        with tf.name_scope('weights'):
            Weights = tf.Variable(tf.random_normal([insize, outsize]),name='W')  # 定义权值矩阵，一般初始值为随机数比赋全0要好
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros(outsize) + 0.1)  # 在机器学习中，biases的推荐值不为0，所以我们这里是在0向量的基础上又加了0.1
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = tf.matmul(inputs, Weights) + biases  # 此处矩阵乘的顺序一定要注意！！！
        if activation_function is None:  # 注意此处使用is
            output = Wx_plus_b
        else:
            output = activation_function(Wx_plus_b)
        return output

x_data = np.linspace(-1, 1, 300, dtype=np.float32)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape).astype(np.float32)
y_data = np.square(x_data) - 0.5 + noise

#define placeholder for inputs to network
with tf.name_scope('inputs'):
    xs = tf.placeholder(tf.float32, [None, 1], name='x_input')  # 输入只有一个特征
    ys = tf.placeholder(tf.float32, [None, 1], name='y_input')

#add hidden layer
l1 = addlayer(xs, 1, 10, activation_function=tf.nn.relu)  # 隐层的输入为1（特征数），输出定义为10个神经元
#add output layer
prediction = addlayer(l1, 10, 1, None)  # 输出层为1，不需要激活函数

with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(prediction-ys), reduction_indices=[1]),name = 'loss')
# tf.reduce_sum()这一步相当于降维了（原来的二维数组变为了一维数组），最后可以求一维数组的平均值
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

init = tf.initialize_all_variables()
sess = tf.Session()
merged =tf.summary.merge_all()
writer =  tf.summary.FileWriter("D:\myjupyter\logs", sess.graph) #tf.summary.FileWriter()

sess.run(init)

实现tensorboard可视化，相较于之前代码增加内容：

 with tf.name_scope('layer'): #大框架的名字
        with tf.name_scope('weights'): #大框架下小零件的名字

merged =tf.summary.merge_all()
writer =  tf.summary.FileWriter("D:\myjupyter\logs", sess.graph) #tf.summary.FileWriter()
#将上面保存的图添加到一个目录中（这里建立一个logs目录），graph的作用是将前面定义的东西收集起来生成文件，保存在log中！

运行
tensorboard --logdir logs
复制链接到网页…结果发现并不能打开！
一通百度之后！这样就好啦！tensorboard --logdir logs --host=127.0.0.1

C:\Users\study>activate tensorflow

(tensorflow) C:\Users\study>D:

(tensorflow) D:\>cd D:\myjupyter

(tensorflow) D:\myjupyter>tensorboard --logdir logs --host=127.0.0.1

打开网页发现：不知道为啥有两个框架（先不管它
inputs
layer
gradients
第二部分的代码参考！
https://blog.csdn.net/kudou1994/article/details/81119401?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522161424187016780261951987%2522%252C%2522scm%2522%253A%252220140713.130102334.pc%255Fall.%2522%257D&request_id=161424187016780261951987&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2_allfirst_rank_v2~rank_v29-2-81119401.first_rank_v2_pc_rank_v29&utm_term=tensorboard+%E8%8E%AB%E7%83%A6