matplotlib实现TensorFlow训练过程的可视化

本篇博客介绍使用matplotlib实现TensorFlow训练过程的可视化，下面是代码：

# encoding:utf-8
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


# 添加层
def add_layer(inputs, in_size, out_size, activation_function=None):
    W = tf.Variable(tf.random_normal([in_size, out_size]))
    b = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.matmul(inputs, W) + b
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

# 生成输入数据、噪点和输出数据
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


xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])

# 隐藏层和输出层
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
prediction = add_layer(l1, 10, 1, activation_function=None)

# 损失值
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),
                     reduction_indices=[1]))

# 用梯度下降更新loss
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

# 初始化所有参数
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

figure = plt.figure()
ax = figure.add_subplot(1, 1, 1)
ax.scatter(x_data, y_data)
plt.ion()
plt.show()
# 训练1000次
for i in range(1000):
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
    if i % 50 == 0:
        # print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))
        try:
            ax.lines.remove(lines[0])
        except Exception:
            pass
        prediction_value = sess.run(prediction, feed_dict={xs: x_data, ys: y_data})
        lines = ax.plot(x_data, prediction_value, 'r-', lw=5)

        plt.pause(0.1)

结果：

可以看到一条红线不断地去拟合数据点。