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

?

?

目錄

輸出結果

代碼設計

---

?

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 layerlayer_name = 'layer%s' % n_layerwith 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_belse: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)

?

?

?

相關文章
TF：TF之Tensorboard實踐：將神經網絡Tensorboard形式得到events.out.tfevents文件+dos內運行該文件本地服務器輸出到網頁可視化

?

?

總結

以上是生活随笔為你收集整理的TF之DNN：对DNN神经网络进行Tensorboard可视化(得到events.out.tfevents本地服务器输出到网页可视化）的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。