轉載自 csdn

import tensorflow as tf import numpy as npdef add_layer(inputs, in_size, out_size, n_layer, activation_function=None): # activation_function=None線性函數layer_name = "layer%s" % n_layerwith tf.name_scope(layer_name):with tf.name_scope('weights'):Weights = tf.Variable(tf.random_normal([in_size, out_size])) # Weight中都是隨機變量tf.summary.histogram(layer_name + "/weights", Weights) # 可視化觀看變量with tf.name_scope('biases'):biases = tf.Variable(tf.zeros([1, out_size]) + 0.1) # biases推薦初始值不為0tf.summary.histogram(layer_name + "/biases", biases) # 可視化觀看變量with tf.name_scope('Wx_plus_b'):Wx_plus_b = tf.matmul(inputs, Weights) + biases # inputs*Weight+biasestf.summary.histogram(layer_name + "/Wx_plus_b", Wx_plus_b) # 可視化觀看變量if activation_function is None:outputs = Wx_plus_belse:outputs = activation_function(Wx_plus_b)tf.summary.histogram(layer_name + "/outputs", outputs) # 可視化觀看變量return outputs# 創建數據x_data，y_datax_data = np.linspace(-1, 1, 300)[:, np.newaxis] # [-1,1]區間，300個單位，np.newaxis增加維度(后面多一個1) noise = np.random.normal(0, 0.05, x_data.shape) # 噪點 y_data = np.square(x_data) - 0.5 + noisewith tf.name_scope('inputs'): # 結構化xs = tf.placeholder(tf.float32, [None, 1], name='x_input')ys = tf.placeholder(tf.float32, [None, 1], name='y_input')# 三層神經，輸入層（1個神經元），隱藏層（10神經元），輸出層（1個神經元） l1 = add_layer(xs, 1, 10, n_layer=1, activation_function=tf.nn.relu) # 隱藏層 prediction = add_layer(l1, 10, 1, n_layer=2, activation_function=None) # 輸出層# predition值與y_data差別 with tf.name_scope('loss'):loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1])) # square()平方,sum()求和,mean()平均值tf.summary.scalar('loss', loss) # 可視化觀看常量 with tf.name_scope('train'):train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss) # 0.1學習效率,minimize(loss)減小loss誤差init = tf.initialize_all_variables() sess = tf.Session() # 合并到Summary中 merged = tf.summary.merge_all() # 選定可視化存儲目錄 writer = tf.summary.FileWriter("Desktop/", sess.graph) sess.run(init) # 先執行init# 訓練1k次 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}) # merged也是需要run的writer.add_summary(result, i) # result是summary類型的，需要放入writer中，i步數（x軸）

然后在terminal中：

tensorboard --logdir=/path/to/log-directory

轉載于:https://www.cnblogs.com/theodoric008/p/7992852.html

總結

以上是生活随笔為你收集整理的tensorboard 使用教程的全部內容，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。