I am trying to create a neural network in Tensorflow that approximates a sine function. I have found some examples of universal function approximators but I am not fully understanding the code and, since I am quite new with Tensorflow, I would like to code it myself to understand every step.
This is my code:
import tensorflow as tf
import numpy as np
import math, random
import matplotlib.pyplot as plt
# Create the arrays x and y that contains the inputs and the outputs of the function to approximate
x = np.arange(0, 2*np.pi, 2*np.pi/1000).reshape((1000,1))
y = np.sin(x)
# plt.plot(x,y)
# plt.show()
# Define the number of nodes
n_nodes_hl1 = 100
n_nodes_hl2 = 100
# Define the number of outputs and the learn rate
n_classes = 1
learn_rate = 0.1
# Define input / output placeholders
x_ph = tf.placeholder('float', [None, 1])
y_ph = tf.placeholder('float')
# Routine to compute the neural network (2 hidden layers)
def neural_network_model(data):
hidden_1_layer = {'weights': tf.Variable(tf.random_normal([1, n_nodes_hl1])),
'biases': tf.Variable(tf.random_normal([n_nodes_hl1]))}
hidden_2_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
'biases': tf.Variable(tf.random_normal([n_nodes_hl2]))}
output_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl2, n_classes])),
'biases': tf.Variable(tf.random_normal([n_classes]))}
# (input_data * weights) + biases
l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(l1, hidden_2_layer['weights']), hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)
output = tf.add(tf.matmul(l2, output_layer['weights']), output_layer['biases'])
return output
# Routine to train the neural network
def train_neural_network(x_ph):
prediction = neural_network_model(x_ph)
cost = tf.reduce_mean(tf.square(prediction - y_ph))
optimizer = tf.train.GradientDescentOptimizer(learn_rate).minimize(cost)
# cycles feed forward + backprop
hm_epochs = 10
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
# Train in each epoch with the whole data
for epoch in range(hm_epochs):
epoch_loss = 0
_, c = sess.run([optimizer, cost], feed_dict = {x_ph: x, y_ph: y})
epoch_loss += c
print('Epoch', epoch, 'completed out of', hm_epochs, 'loss:', epoch_loss)
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y_ph, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print('Accuracy;', accuracy.eval({x_ph: x, y_ph: x}))
# Train network
train_neural_network(x_ph)
If you run that program you will see how the loss diverges and I don't know why it behaves like that. Could anyone help me?
Thank you!