Created
January 19, 2017 17:33
-
-
Save tu-lee/22a2712320d8da5dbf774b95a2b92a01 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import tensorflow as tf | |
import numpy as np | |
import random | |
import math | |
from mlxtend.preprocessing import one_hot | |
from tensorflow.python.ops import rnn, rnn_cell | |
from random import shuffle | |
""" | |
Hyperparameters | |
""" | |
hm_epochs = 100 | |
n_classes = 2 | |
batch_size = 10 | |
chunk_size = 1 | |
n_chunks = 1 | |
rnn_size = 5 | |
""" | |
Parameters for generating input multiple exponential signals for input | |
""" | |
lorange= 1 | |
resolution= 500 | |
hirange= 1000 | |
amplitude= np.random.uniform(-10,10) | |
t = 100 | |
no_tau = 100 | |
"""Input signals""" | |
count = 0 | |
class1 = [0] | |
class2 = [1] | |
train_input = [] | |
train_output = [] | |
while (count<no_tau): | |
tau =np.array(int(math.ceil(np.random.uniform(lorange, hirange)))) | |
count = count+1 | |
X = amplitude * np.exp(-t / tau) | |
X = np.reshape(X, [-1, 1,1]) | |
if tau < 500: | |
label = one_hot(class1, num_labels=2) | |
else: | |
label = one_hot(class2, num_labels=2) | |
train_input.append(X) | |
#train_input = np.reshape(train_input, [-1, 1,1]) | |
train_output.append(label) | |
print(train_input) | |
print(train_output) | |
"""testing data""" | |
ct = 0 | |
class1 = [0] | |
class2 = [1] | |
test_input = [] | |
test_output = [] | |
while (count<no_tau): | |
tau =np.array(int(math.ceil(np.random.uniform(1000, 2000)))) | |
count = count+1 | |
X1 = amplitude * np.exp(-t / tau) | |
X1 = np.reshape(X, [-1, 1,1]) | |
if tau < 500: | |
label = one_hot(class1, num_labels=2) | |
else: | |
label = one_hot(class2, num_labels=2) | |
test_input.append(X) | |
#train_input = np.reshape(train_input, [-1, 1,1]) | |
test_output.append(label) | |
""" Input placeholders for signal and label""" | |
x = tf.placeholder('float', [None,n_chunks, chunk_size]) | |
y = tf.placeholder('float') | |
"""Define RNN function""" | |
def recurrent_neural_network(x): | |
layer = {'weights':tf.Variable(tf.random_normal([rnn_size,n_classes])), | |
'biases':tf.Variable(tf.random_normal([n_classes]))} | |
x = tf.transpose(x, [1, 0, 2]) | |
x = tf.reshape(x, [-1, chunk_size]) | |
x = tf.split(0, n_chunks, x) | |
lstm_cell = rnn_cell.BasicLSTMCell(rnn_size,state_is_tuple=True) | |
outputs, states = rnn.rnn(lstm_cell, x, dtype=tf.float32) | |
output = (tf.add(tf.matmul(outputs[-1], layer['weights']), layer['biases'])) | |
return output | |
"""Training the network""" | |
def train_neural_network(x): | |
prediction = recurrent_neural_network(x) | |
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(prediction, y)) | |
optimizer = tf.train.GradientDescentOptimizer(0.1).minimize(cost) | |
with tf.Session() as sess: | |
sess.run(tf.global_variables_initializer()) | |
for epoch in range(hm_epochs): | |
epoch_loss = 0 | |
i = 0 | |
while i < no_tau: | |
start = i | |
end = i + batch_size | |
batch_x = np.array(train_input[start:end]) | |
batch_x = np.reshape(batch_x, [-1, 1, 1]) | |
batch_y = np.array(train_output[start:end]) | |
_, c = sess.run([optimizer, cost], feed_dict={x: batch_x, y: batch_y}) | |
epoch_loss += c | |
i += batch_size | |
print('Epoch', epoch + 1, 'completed out of', hm_epochs, 'loss:', epoch_loss) | |
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1)) | |
accuracy = -tf.reduce_mean(tf.cast(correct, 'float')) | |
print(accuracy) | |
#batch_y = np.reshape(batch_y, [10, 2]) | |
print('Accuracy:', accuracy.eval({x: batch_x, y: batch_y})) | |
train_neural_network(x) | |
""" | |
Output labels | |
to = [] | |
count = 0 | |
class1 = [0] | |
class2 = [1] | |
while (count < no_tau): | |
tau = np.array([int(math.ceil(np.random.uniform(lorange, hirange)))]) | |
if tau<500: | |
label = one_hot(class1, num_labels=2) | |
else: | |
label = one_hot(class2, num_labels=2) | |
count = count + 1 | |
label.append(to) | |
""" | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment