通过python的matplotlib包将Tensorflow数据进行可视化

傷城~ 2022-06-06 12:26 120阅读 0赞

# 使用matplotlib中的一些函数将tensorflow中的数据可视化，更加便于分析 #

import tensorflow as tf
    import numpy as np
    import matplotlib.pyplot as plt
    
    def add_layer(inputs, in_size, out_size, activation_function=None):
        Weights = tf.Variable(tf.random_normal([in_size, out_size]))
        biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
        Wx_plus_b = tf.matmul(inputs, Weights) + biases
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b)
        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
    xs = tf.placeholder(tf.float32, [None, 1])
    ys = tf.placeholder(tf.float32, [None, 1])
    # add hidden layer
    l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
    # add output layer
    prediction = add_layer(l1, 10, 1, activation_function=None)
    
    # the error between prediction and real data
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction), reduction_indices=[1]))
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
    # important step
    
    #initialize_all_variables已被弃用,使用tf.global_variables_initializer代替。 
    init = tf.global_variables_initializer()
    sess = tf.Session()
    sess.run(init)
    
    # plot the real data
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    ax.scatter(x_data, y_data)
    plt.ion() #使plt不会在show之后停止而是继续运行
    plt.show()
    
    
    for i in range(1000):
        # training
        sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
        if i % 50 == 0:
            # to visualize the result and improvement
            try:
                ax.lines.remove(lines[0]) #在每一次绘图之前先讲上一次绘图删除，使得画面更加清晰
            except Exception:
                pass
            prediction_value = sess.run(prediction, feed_dict={xs: x_data})
            # plot the prediction
            lines = ax.plot(x_data, prediction_value, 'r-', lw=5) #'r-'指绘制一个红色的线
            plt.pause(1) #指等待一秒钟

运行结果如下：（实际效果应该是动态的，应当使用ipython运行，使用jupyter运行则图片不是动态的）  
![这里写图片描述][SouthEast]

注意：initialize\_all\_variables已被弃用,使用tf.global\_variables\_initializer代替。

[SouthEast]: /images/20220606/be98d3fac06c44df9caf06ae33213d81.png