使用Tensorboard进行可视化

上一篇博客中记录了使用Tensorflow和JupyterNotebook简单搭建一个神经网络，这篇博客在上一篇的基础上进行了修改，使用Tensorboard进行可视化。

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt

def addlayer(inputs, insize, outsize, activefunction=None):
    with tf.name_scope('layer'):
        with tf.name_scope('weights'):
            Weight = tf.Variable(tf.random_normal([insize, outsize]), name = 'w')
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1, outsize]) + 0.1)
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = tf.matmul(inputs,Weight) + biases
        if activefunction is None:
            outputs = Wx_plus_b
        else:
            outputs = activefunction(Wx_plus_b)
        return outputs

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

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

l1 = addlayer(xs, 1, 10, activefunction=tf.nn.relu)
prediction = addlayer(l1,10,1,activefunction=None)

with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),reduction_indices=[1]))
with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

init = tf.initialize_all_variables()

sess = tf.Session()
writer = tf.summary.FileWriter('logs/',sess.graph)
sess.run(init)

运行完成后，打开Anaconda终端输入：tensorboard --logdir=logs/

图片中马赛克掉的是我的名字，无关紧要。

根据终端提供的网址，我使用的是Chrome，能够顺利打开。效果大致是如下图所示