【TensorFlow】使用Tensorboard绘制网络结构

import tensorflow as tf
# 加载数据
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('/tmp/data',one_hot=True)
           

Extracting /tmp/data/train-images-idx3-ubyte.gz
Extracting /tmp/data/train-labels-idx1-ubyte.gz
Extracting /tmp/data/t10k-images-idx3-ubyte.gz
Extracting /tmp/data/t10k-labels-idx1-ubyte.gz
           

一、定义和训练模型

1.参数

batch_size = 100 # 每个batch的大小
n_batch = mnist.train.num_examples//batch_size # 训练集共包含多少个batch
           

2.定义计算图

定义name_scope和name属性后，对应的名字会在TensorBoard中显示；而且定义合适的name_scope可以使TensorBoard的图更加简洁清晰

# 定义命名空间
with tf.name_scope('input'):
    x = tf.placeholder(tf.float32,[None,784],name='x-input')
    y = tf.placeholder(tf.float32,[None,10],name='y-input')
    keep_prob = tf.placeholder(tf.float32) # dropout时，每个元素被保留的概率

with tf.name_scope('layer1'):
    with tf.name_scope('weights'):
        W1 = tf.Variable(tf.truncated_normal([784,2000],stddev=0.1),name='W1')
    with tf.name_scope('biases'):
        b1 = tf.Variable(tf.zeros([2000])+0.1,name='b1')
    L1 = tf.nn.tanh(tf.matmul(x,W1)+b1)
    L1_drop = tf.nn.dropout(L1,keep_prob)

with tf.name_scope('layer2'):
    W2 = tf.Variable(tf.truncated_normal([2000,1000],stddev=0.1),name='W2')
    b2 = tf.Variable(tf.zeros([1000])+0.1,name='b2')
    L2 = tf.nn.tanh(tf.matmul(L1_drop,W2)+b2)
    L2_drop = tf.nn.dropout(L2,keep_prob)
    
with tf.name_scope('layer3'):
    W3 = tf.Variable(tf.truncated_normal([1000,10],stddev=0.1),name='W3')
    b3 = tf.Variable(tf.zeros([10])+0.1,name='b3')

# 预测值
prediction = tf.nn.softmax(tf.matmul(L2_drop,W3)+b3)
# loss
# loss = tf.reduce_mean(tf.square(y-prediction)) # MSE
# cross entropy
with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
# SGD
with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
# 初始化
init = tf.global_variables_initializer()

with tf.name_scope('accuracy'):
    # 分类结果
    # tf.argmax(y,1):在axis=1，y中最大值的下标
    correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))
    # 准确率
    # tf.cast：将bool类型的correct_prediction转换为tf.float32类型
    accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
           

3.训练

with tf.Session() as sess:
    sess.run(init)
    # 将sess.graph写到文件夹logs下
    writer = tf.summary.FileWriter('logs/',sess.graph)
    for epoch in range(2):
        for batch in range(n_batch):
            batch_xs,batch_ys = mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:0.5})
            
        test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
        train_acc = sess.run(accuracy,feed_dict={x:mnist.train.images,y:mnist.train.labels,keep_prob:1.0})
        print("Iter "+str(epoch)+",Testing accuracy "+str(test_acc)+",Training accuracy "+str(train_acc))
           

Iter 0,Testing accuracy 0.9049,Training accuracy 0.89774543
Iter 1,Testing accuracy 0.9204,Training accuracy 0.915
           

二、使用TensorBoard

在上面训练的过程中我们已经将有关于图信息的文件保存到了目录’logs/’，那么之后只要打开TensorBoard服务读取这个文件。然后再浏览器中就能看到我们的网络结构了。

1.进入命令行，输入下面的命令，其中logs可以替换为保存图信息文件的相对路径或者决定路径

2.进入浏览器，输入"tensorboard服务器的IP地址:6006"，将会看到如下图