Tensorboard 視覺化模板例子

#!/usr/bin/env python
# -*- coding: utf-8 -*-


import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#載入資料
mnist = input_data.read_data_sets('../data/mnist' , one_hot= True)

#每個批次大小
batch_size = 100

n_batch = mnist.train.num_examples // batch_size

#參考概要
 

def variable_summaries(var , name = 'summaries'):
    with tf.name_scope(name):
        mean = tf.reduce_mean(var)
        tf.summary.scalar('mean', mean) #平均值
        with tf.name_scope('stddev'):
            stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
        tf.summary.scalar('stddev'
 
 , stddev) #標準差
        tf.summary.scalar('max' , tf.reduce_max(var)) #最大值
        tf.summary.scalar('min' , tf.reduce_min(var))   #最小值
        tf.summary.histogram('histogram' , var) #直方圖

#初始化權值
def weight_variable(shape):
    with tf.name_scope('weight'):
        initial = tf.truncated_normal(shape,stddev=0.1
 
) #生成一個截斷的正態分佈
        W =  tf.Variable(initial , name='W')
        return W

#初始化偏置
def bias_variable(shape):
    with tf.name_scope('biases'):
        initial = tf.truncated_normal(shape=shape , stddev=0.1)
        b = tf.Variable(initial , name='b')
        return b


#卷積層
def conv2d(x , W):
    with tf.name_scope('conv2d'):
        return tf.nn.conv2d(x , W , strides=[1,1,1,1] ,padding='SAME')

def max_pool_2x2(x):
    with tf.name_scope('max_pool_2x2'):
        return tf.nn.max_pool(x ,ksize=[1,2,2,1] , strides=[1,2,2,1] , padding='SAME')


#定義placeholder

with tf.name_scope('input'):
    x = tf.placeholder(tf.float32 , [None , 784] ,name = 'x_input') #28*28
    y = tf.placeholder(tf.float32, [None , 10] , name='y_input')

    #改變x的格式轉為4D的向量[batch , in_height , in_width , in_channels]
    x_image = tf.reshape(x , [-1,28,28,1] , name='x_image')
    tf.summary.image('input_image', x_image,12)


with tf.name_scope('conv1'):
    #初始化第一個卷積層的權值和偏置
    W_conv1 = weight_variable([5,5,1,32]) #5*5取樣視窗，32個卷積核從一個平面抽取特徵
    b_conv1 = bias_variable([32]) #每一個卷積核一個偏置
    variable_summaries(W_conv1 , 'W_conv1')
    variable_summaries(b_conv1, 'b_conv1')
    #把x_image和權值向量進行卷積，加上偏置，然後應用relu啟用函式,maxpooling
    h_conv1 = tf.nn.relu(conv2d(x_image , W_conv1) + b_conv1 , name= 'relu')
    h_pool1 = max_pool_2x2(h_conv1)

with tf.name_scope('conv2'):
    #初始化第二個卷積成的權值和偏置
    W_conv2 = weight_variable([5,5,32,64]) #5*5取樣視窗，64個卷積核從32個平面抽取特徵
    b_conv2 = bias_variable([64]) #每一個卷積核一個偏置
    variable_summaries(W_conv2 , 'W_conv2')
    variable_summaries(b_conv2, 'b_conv2')
    #把h_pool1和權值向量進行卷積，加上偏置，然後應用relu啟用函式,maxpooling
    h_conv2 = tf.nn.relu(conv2d(h_pool1 , W_conv2) + b_conv2 , name='relu')
    h_pool2 = max_pool_2x2(h_conv2)

    #28*28的圖片第一次卷積後28*28，pool後14*14
    #第二次卷積14*14，pool後7*7
    #經過上述之後得到64張7*7的平面

with tf.name_scope('fc1'):
    #初始化第一個全連線的權值
    W_fc1 = weight_variable([7*7*64 , 1024]) #上一層有7*7*64個神經元，全連線層有1024個神經元
    b_fc1 = bias_variable([1024])

    #將池化層2的輸出轉換成1維

    h_pool2_flat = tf.reshape(h_pool2 , [-1,7*7*64])
    #求第一個全連線的輸出
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+ b_fc1)

    #dropout
    with tf.name_scope('dropout'):
        keep_pro = tf.placeholder(tf.float32)
        h_fc1_drop = tf.nn.dropout(h_fc1 , keep_pro)

with tf.name_scope('fc2'):
    #初始化第二個全連線
    W_fc2 = weight_variable([1024,10])
    b_fc2 = bias_variable([10])

#計算輸出
    with tf.name_scope('softmax'):
        prediction = tf.nn.softmax(tf.matmul(h_fc1_drop , W_fc2) + b_fc2)


with tf.name_scope('cr_ep_loss'):
    #交叉熵代價函式
    cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
    tf.summary.scalar('cr_ep_loss' , cross_entropy)

with tf.name_scope('train'):

    #使用AdamOptimizer優化
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
with tf.name_scope('accuracy'):
    #將結果放進布林列表
    correct_prediction = tf.equal(tf.argmax(prediction , 1) , tf.argmax(y ,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction , tf.float32) , name='accuracy')
    tf.summary.scalar('accuracy',accuracy)


merged = tf.summary.merge_all()



with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    train_writer = tf.summary.FileWriter('logs/train' , sess.graph)
    test_writer = tf.summary.FileWriter('logs/test' , sess.graph)

    for i in range(1001):
        batch_xs , batch_ys = mnist.train.next_batch(batch_size)
        sess.run([merged , train_step], feed_dict={x:batch_xs , y:batch_ys , keep_pro:0.7})

        train_summary = sess.run(merged , feed_dict={x:batch_xs , y:batch_ys , keep_pro:1})
        train_writer.add_summary(train_summary , i)

        batch_xs, batch_ys = mnist.test.next_batch(batch_size)
        test_summary,acc = sess.run([merged , accuracy] , feed_dict={x:batch_xs , y:batch_ys , keep_pro:1})
        test_writer.add_summary(test_summary, i)

        if i%100 == 0:
            test_acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels, keep_pro: 1.0})
            train_acc, loss = sess.run([accuracy,cross_entropy] , feed_dict={x:mnist.train.images[:10000] ,
                                                                             y:mnist.train.labels[0:10000],
                                                                             keep_pro :1.0})
        print('Iter :%s; loss%s; Train Accuracy:%s; Test Accuracy:%s'%(
            str(i) , str(loss),str(train_acc),str(test_acc)))

tensorboard 顯示的Graphs

使用with tf.name_scope()定義名稱空間
train_writer = tf.summary.FileWriter(‘logs/train’ , sess.graph) 語句寫入logs檔案

顯示loss和accuracy

記錄loss

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
tf.summary.scalar('cr_ep_loss' , cross_entropy)

記錄accuracy

batch_xs , batch_ys = mnist.train.next_batch(batch_size)
sess.run([merged , train_step], feed_dict={x:batch_xs , y:batch_ys , keep_pro:0.7})

train_summary = sess.run(merged , feed_dict={x:batch_xs , y:batch_ys , keep_pro:1})
train_writer.add_summary(train_summary , i)

batch_xs, batch_ys = mnist.test.next_batch(batch_size)
test_summary,acc = sess.run([merged , accuracy] , feed_dict={x:batch_xs , y:batch_ys , keep_pro:1})
test_writer.add_summary(test_summary, i)

顯示權值偏置的統計資訊

定義統計函式：

def variable_summaries(var , name = 'summaries'):
    with tf.name_scope(name):
        mean = tf.reduce_mean(var)
        tf.summary.scalar('mean', mean) #平均值
        with tf.name_scope('stddev'):
            stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
        tf.summary.scalar('stddev' , stddev) #標準差
        tf.summary.scalar('max' , tf.reduce_max(var)) #最大值
        tf.summary.scalar('min' , tf.reduce_min(var))   #最小值
        tf.summary.histogram('histogram' , var) #直方圖

使用：
傳入需統計的變數和名稱空間

 W_conv1 = weight_variable([5,5,1,32]) #5*5取樣視窗，32個卷積核從一個平面抽取特徵
 b_conv1 = bias_variable([32]) #每一個卷積核一個偏置
 variable_summaries(W_conv1 , 'W_conv1')
 variable_summaries(b_conv1, 'b_conv1')

直方圖資訊：

顯示輸入圖片

記錄顯示圖片

x_image = tf.reshape(x , [-1,28,28,1] , name='x_image')
tf.summary.image('input_image', x_image,12) #12表示在tensorboard中顯示12張圖片