Created
September 3, 2018 11:39
-
-
Save ysyun/16611aaafb8e5ac1811fb825a762ea11 to your computer and use it in GitHub Desktop.
Basic RNN - allofdeeplearning
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
# Lab 12 RNN | |
import tensorflow as tf | |
import numpy as np | |
tf.set_random_seed(777) # reproducibility | |
idx2char = ['h', 'i', 'e', 'l', 'o'] | |
# Teach hello: hihell -> ihello | |
x_data = [[0, 1, 0, 2, 3, 3]] # hihell | |
x_one_hot = [[[1, 0, 0, 0, 0], # h 0 | |
[0, 1, 0, 0, 0], # i 1 | |
[1, 0, 0, 0, 0], # h 0 | |
[0, 0, 1, 0, 0], # e 2 | |
[0, 0, 0, 1, 0], # l 3 | |
[0, 0, 0, 1, 0]]] # l 3 | |
y_data = [[1, 0, 2, 3, 3, 4]] # ihello | |
num_classes = 5 | |
input_dim = 5 # one-hot size | |
hidden_size = 5 # output from the LSTM. 5 to directly predict one-hot | |
batch_size = 1 # one sentence | |
sequence_length = 6 # |ihello| == 6 | |
learning_rate = 0.1 | |
X = tf.placeholder( | |
tf.float32, [None, sequence_length, input_dim]) # X one-hot | |
Y = tf.placeholder(tf.int32, [None, sequence_length]) # Y label | |
cell = tf.contrib.rnn.BasicLSTMCell(num_units=hidden_size, state_is_tuple=True) | |
initial_state = cell.zero_state(batch_size, tf.float32) | |
outputs, _states = tf.nn.dynamic_rnn( | |
cell, X, initial_state=initial_state, dtype=tf.float32) | |
# FC layer | |
X_for_fc = tf.reshape(outputs, [-1, hidden_size]) | |
# fc_w = tf.get_variable("fc_w", [hidden_size, num_classes]) | |
# fc_b = tf.get_variable("fc_b", [num_classes]) | |
# outputs = tf.matmul(X_for_fc, fc_w) + fc_b | |
outputs = tf.contrib.layers.fully_connected( | |
inputs=X_for_fc, num_outputs=num_classes, activation_fn=None) | |
# reshape out for sequence_loss | |
outputs = tf.reshape(outputs, [batch_size, sequence_length, num_classes]) | |
weights = tf.ones([batch_size, sequence_length]) | |
sequence_loss = tf.contrib.seq2seq.sequence_loss( | |
logits=outputs, targets=Y, weights=weights) | |
loss = tf.reduce_mean(sequence_loss) | |
train = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss) | |
prediction = tf.argmax(outputs, axis=2) | |
with tf.Session() as sess: | |
sess.run(tf.global_variables_initializer()) | |
for i in range(50): | |
l, _ = sess.run([loss, train], feed_dict={X: x_one_hot, Y: y_data}) | |
result = sess.run(prediction, feed_dict={X: x_one_hot}) | |
print(i, "loss:", l, "prediction: ", result, "true Y: ", y_data) | |
# print char using dic | |
result_str = [idx2char[c] for c in np.squeeze(result)] | |
print("\tPrediction str: ", ''.join(result_str)) | |
''' | |
0 loss: 1.71584 prediction: [[2 2 2 3 3 2]] true Y: [[1, 0, 2, 3, 3, 4]] | |
Prediction str: eeelle | |
1 loss: 1.56447 prediction: [[3 3 3 3 3 3]] true Y: [[1, 0, 2, 3, 3, 4]] | |
Prediction str: llllll | |
2 loss: 1.46284 prediction: [[3 3 3 3 3 3]] true Y: [[1, 0, 2, 3, 3, 4]] | |
Prediction str: llllll | |
3 loss: 1.38073 prediction: [[3 3 3 3 3 3]] true Y: [[1, 0, 2, 3, 3, 4]] | |
Prediction str: llllll | |
4 loss: 1.30603 prediction: [[3 3 3 3 3 3]] true Y: [[1, 0, 2, 3, 3, 4]] | |
Prediction str: llllll | |
5 loss: 1.21498 prediction: [[3 3 3 3 3 3]] true Y: [[1, 0, 2, 3, 3, 4]] | |
Prediction str: llllll | |
6 loss: 1.1029 prediction: [[3 0 3 3 3 4]] true Y: [[1, 0, 2, 3, 3, 4]] | |
Prediction str: lhlllo | |
7 loss: 0.982386 prediction: [[1 0 3 3 3 4]] true Y: [[1, 0, 2, 3, 3, 4]] | |
Prediction str: ihlllo | |
8 loss: 0.871259 prediction: [[1 0 3 3 3 4]] true Y: [[1, 0, 2, 3, 3, 4]] | |
Prediction str: ihlllo | |
9 loss: 0.774338 prediction: [[1 0 2 3 3 4]] true Y: [[1, 0, 2, 3, 3, 4]] | |
Prediction str: ihello | |
10 loss: 0.676005 prediction: [[1 0 2 3 3 4]] true Y: [[1, 0, 2, 3, 3, 4]] | |
Prediction str: ihello | |
... | |
''' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment