TensorFlow activatefunction 及可视化

import tensorflow as  tf
import numpy as np
import matplotlib.pyplot as plt

plt.ion()


def add_layer(inputs, in_size, out_size, activation_function=None):
    Weight = tf.Variable(tf.random_normal([in_size, out_size]))  # 随机变量会比全部都是0好很多
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.matmul(inputs, Weight) + biases
    if activation_function is None:
        out_put = Wx_plus_b

    else:
        out_put = activation_function(Wx_plus_b)
    return out_put


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
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
ax.scatter(x_data, y_data)
plt.show()
xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])

l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
prediction = add_layer(l1, 10, 1, activation_function=None)

loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)


for i in range(1000):
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
    if i % 50 == 0:
        try:
            ax.lines.remove(lines[0])
        except:
            pass
        print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))
        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)

效果：