Tensorflow 构建简单神经网络

Tensorflow 构建简单神经网络

• 莫凡Tensorflow教程笔记
  https://morvanzhou.github.io/tutorials/machine-learning/tensorflow/3-2-create-NN/

import tensorflow as tf
import numpy as np

def add_layer(inputs, in_size, out_size, activation_function=None):
        Weights = tf.Variable(tf.random_normal([in_size,out_size])) # Weight matrix 
        biases = tf.Variable(tf.zeros([1, out_size])+0.1) #Biases is not suggested to be zero, so set +0.1 here
        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

# Input Observed 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

# Store Observed Data  with placeholder 
xs = tf.placeholder(tf.float32, [None,1])
ys = tf.placeholder(tf.float32, [None,1])

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

# define loss function,
loss = tf.reduce_mean(tf.square(ys-prediction))

# use Gradient Descent Optimizer to minimize loss
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)


# initiation
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})  # learn 1000 times
        if i%50:
                print(sess.run(loss, feed_dict={xs:x_data, ys:y_data})) # print loss