012-lab-003. rnn for long sentence
<![CDATA[
import tensorflow as tf
import numpy as np
tf.set_random_seed(777)
sample = " if you want you"
# set(sample) extracts unique characters
idx2char = list(set(sample))
char2idx = {c: i for i, c in enumerate(idx2char)}
# size of input data(one hot size)
dic_size = len(char2idx)
hidden_size = len(char2idx) # RNN output size
num_classes = len(char2idx) # final output size (RNN or softmax, etc.)
batch_size = 1 # one sample data, one batch
sequence_length = len(sample) - 1 # number of lstm rollings (unit #)
learning_rate = 0.1
# character to index
sample_idx = [char2idx[c] for c in sample]
# if you want yo
x_data = [sample_idx[:-1]]
# f you want you
y_data = [sample_idx[1:]]
X = tf.placeholder(tf.int32, [None, sequence_length])
Y = tf.placeholder(tf.int32, [None, sequence_length])
# num_classes = size of idx2char(number of unique characters)
# Be careful on shape when you use one_hot()
x_one_hot = tf.one_hot(X, num_classes)
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_one_hot, initial_state=initial_state, dtype=tf.float32)
# FC layer
X_for_fc = tf.reshape(outputs, [-1, hidden_size])
outputs = tf.contrib.layers.fully_connected(X_for_fc, 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_data, Y: y_data})
result = sess.run(prediction, feed_dict={X: x_data})
# print char using dic
result_str = [idx2char[c] for c in np.squeeze(result)]
print(i, "loss:", l, "Prediction:", ''.join(result_str))
'''
0 loss: 2.35377 Prediction: uuuuuuuuuuuuuuu
1 loss: 2.21383 Prediction: yy you y you
2 loss: 2.04317 Prediction: yy yoo ou
3 loss: 1.85869 Prediction: yy ou uou
4 loss: 1.65096 Prediction: yy you a you
5 loss: 1.40243 Prediction: yy you yan you
6 loss: 1.12986 Prediction: yy you wann you
7 loss: 0.907699 Prediction: yy you want you
8 loss: 0.687401 Prediction: yf you want you
9 loss: 0.508868 Prediction: yf you want you
10 loss: 0.379423 Prediction: yf you want you
11 loss: 0.282956 Prediction: if you want you
12 loss: 0.208561 Prediction: if you want you
...
'''
from __future__ import print_function
import tensorflow as tf
import numpy as np
from tensorflow.contrib import rnn
tf.set_random_seed(777)
sentence = ("if you want to build a ship, don't drum up people together to "
"collect wood and don't assign them tasks and work, but rather "
"teach them to long for the endless immensity of the sea.")
# Extract unique characters and then make it as list
char_set = list(set(sentence))
char_dic = {w: i for i, w in enumerate(char_set)}
data_dim = len(char_set)
hidden_size = len(char_set)
num_classes = len(char_set)
# You can define whatever you want
# This is length part of sentence you learning
# For example, x is 'if you wan' and y is 'f you want'
sequence_length = 10
learning_rate = 0.1
dataX = []
dataY = []
# This is process of generating train dataset
for i in range(0, len(sentence) - sequence_length):
x_str = sentence[i:i + sequence_length]
y_str = sentence[i + 1: i + sequence_length + 1]
print(i, x_str, '->', y_str)
x = [char_dic[c] for c in x_str]
y = [char_dic[c] for c in y_str]
dataX.append(x)
dataY.append(y)
# We have many instances in entire train dataset
# So, we need to use batch size
batch_size = len(dataX)
X = tf.placeholder(tf.int32, [None, sequence_length])
Y = tf.placeholder(tf.int32, [None, sequence_length])
# One-hot encoding
X_one_hot = tf.one_hot(X, num_classes)
print(X_one_hot) # check out the shape
# Make a lstm cell with hidden_size (each unit output vector size)
def lstm_cell():
cell = rnn.BasicLSTMCell(hidden_size, state_is_tuple=True)
return cell
multi_cells = rnn.MultiRNNCell([lstm_cell() for _ in range(2)], state_is_tuple=True)
# outputs: unfolding size x hidden size, state = hidden size
outputs, _states = tf.nn.dynamic_rnn(multi_cells, X_one_hot, dtype=tf.float32)
# FC layer
X_for_fc = tf.reshape(outputs, [-1, hidden_size])
outputs = tf.contrib.layers.fully_connected(X_for_fc, num_classes, activation_fn=None)
# reshape out for sequence_loss
outputs = tf.reshape(outputs, [batch_size, sequence_length, num_classes])
# All weights are 1 (equal weights)
weights = tf.ones([batch_size, sequence_length])
sequence_loss = tf.contrib.seq2seq.sequence_loss(
logits=outputs, targets=Y, weights=weights)
mean_loss = tf.reduce_mean(sequence_loss)
train_op = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(mean_loss)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for i in range(500):
_, l, results = sess.run(
[train_op, mean_loss, outputs], feed_dict={X: dataX, Y: dataY})
for j, result in enumerate(results):
index = np.argmax(result, axis=1)
print(i, j, ''.join([char_set[t] for t in index]), l)
# Let's print the last char of each result to check it works
results = sess.run(outputs, feed_dict={X: dataX})
for j, result in enumerate(results):
index = np.argmax(result, axis=1)
if j is 0: # print all for the first result to make a sentence
print(''.join([char_set[t] for t in index]), end='')
else:
print(char_set[index[-1]], end='')
'''
0 167 tttttttttt 3.23111
0 168 tttttttttt 3.23111
0 169 tttttttttt 3.23111
…
499 167 of the se 0.229616
499 168 tf the sea 0.229616
499 169 the sea. 0.229616
g you want to build a ship, don't drum up people together to collect wood and don't assign them tasks and work, but rather teach them to long for the endless immensity of the sea.
'''
]]>