使用TensorBoard进行数据可视化

叁歲伎倆 2022-06-06 12:28 469阅读 0赞

# 使用TensorBoard进行数据可视化 #

--------------------

### 除了python的matplotlib这个数据图像化的包，我们还可以使用Tensorflow自带的TensorBoard来将数据进行可视化，实现的代码如下 ###

--------------------

import tensorflow as tf
    import numpy as np
    
    def add_layer(inputs, in_size, out_size, n_layer, activation_function=None):
        layer_name = 'layer%s' % n_layer
        with tf.name_scope("layer"): 
            with tf.name_scope("weight"):
                Weights = tf.Variable(tf.random_normal([in_size,out_size]),name="W")
                tf.summary.histogram(layer_name+'/Weights',Weights)
            with tf.name_scope("biases"):
                biases = tf.Variable(tf.zeros([1, out_size])+0.1,name="b")
                tf.summary.histogram(layer_name+'/biases',biases)
            with tf.name_scope("Wx_plus_b"):
                Wx_plus_b = tf.matmul(inputs, Weights)+biases
            if activation_function == None:
                outputs = Wx_plus_b
            else:
                outputs = activation_function(Wx_plus_b)
                tf.summary.histogram(layer_name+'/outputs',outputs)
            return outputs
    
    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
    
    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 = add_layer(xs, 1, 10, n_layer=1, activation_function=tf.nn.relu)
    prediction = add_layer(l1, 10, 1, n_layer=2, activation_function=None) 
    
    with tf.name_scope("loss"):
        loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]),name="loss")
        tf.summary.scalar('loss',loss)
    with tf.name_scope("train"):
        train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
    
    init = tf.global_variables_initializer()
    sess = tf.Session()
    merged = tf.summary.merge_all()
    writer = tf.summary.FileWriter("logs/",sess.graph)
    sess.run(init)
    
    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)

--------------------

### 代码进行保存以及运行之后，将会在指定文件夹中看到保存的文件，这是我们需要在终端中运行下面的命令，然后将网址复制到浏览器即可打开 ###

$ tensorboard --logdir='logs/' #'logs'是指保存的文件所在的文件夹

![这里写图片描述][SouthEast]

--------------------

## 注： ##

--------------------

### 1. ###

tf.name_scope("name")

### 该函数中的name是指GRAPHS中的 ###

![这里写图片描述][SouthEast 1]

### 以及每个神经网络的节点打开后里面的各种量的名字 ###

### 这是部分节点点开后的样子 ###

![这里写图片描述][SouthEast 2]

### 这是所有节点点开后的样子 ###

![这里写图片描述][SouthEast 3]

--------------------

### 2. ###

tf.summary.histogram(layer_name+'name',name)

### 该函数是用来绘制histogram中图可视化绘图 ###

![这里写图片描述][SouthEast 4]

--------------------

### 3. ###

tf.summary.scalar('name',name)

### 该函数主要适用于损失函数在scalar的可视化绘图 ###

![这里写图片描述][SouthEast 5]

--------------------

### 4. ###

tf.summary.FileWriter("logs/",sess.graph)

### 该函数是将TensorBoard文件保存到指定路径，例如”logs/”即是指路径，正常运行后将会在logs文件夹下产生一个文件 ###

![这里写图片描述][SouthEast 6]

--------------------

### 5. ###

tf.summary.merge_all()

### 该函数是将所有summary文件合并到同一个文件里并在下一步的tf.summary.FileWriter(“logs/”,sess.graph)进行保存 ###

--------------------

### 6. ###

add_summary(result,i)

### 该函数是将result这个数据加入到writer = tf.summary.FileWriter(“logs/”,sess.graph)这个函数的write中去，其中i是指步数，例如本函数中就是50布记录一个点 ###

--------------------

### 7.运行应该在ipython中运行，如果在jupyter中运行可能会产生报错 ###

[SouthEast]: /images/20220606/8c1e2362693b48ab9f70ce1a533ee34b.png
[SouthEast 1]: /images/20220606/88355b89ca0745b4bfed9b7c42e0dbcd.png
[SouthEast 2]: /images/20220606/95e32aa694324695a9bc96dbcf0ab1db.png
[SouthEast 3]: /images/20220606/03cdde62ec8a4f1d8975514fee2f2bc5.png
[SouthEast 4]: /images/20220606/df8dc977d8bd49b288450dd8dace01b8.png
[SouthEast 5]: /images/20220606/97ea75cc01d0447899c3c10ca46d4f87.png
[SouthEast 6]: /images/20220606/dbb371882e6448afa11b84da7b4afbe5.png