-
Notifications
You must be signed in to change notification settings - Fork 3
/
highway_layer_cnn.py
115 lines (92 loc) · 5 KB
/
highway_layer_cnn.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
import tensorflow as tf
import numpy as np
class hightway_CNN(object):
"""
Uses an embedding layer,highway layer, followed by a convolutional, max-pooling and softmax layer.
"""
def __init__(
self, sequence_length, num_classes, vocab_size,
embedding_size, filter_sizes, num_filters, l2_reg_lambda,learning_rate):
# Placeholders for input, output and dropout
self.input_x = tf.placeholder(tf.int32, [None, sequence_length], name="input_x")
self.input_y = tf.placeholder(tf.float32, [None, num_classes], name="input_y")
self.dropout_keep_prob = tf.placeholder(tf.float32, name="dropout_keep_prob")
# Keeping track of l2 regularization loss (optional)
l2_loss = tf.constant(0.0)
# Embedding layer
with tf.device('/cpu:0'), tf.name_scope("embedding"):
self.W = tf.Variable(
tf.random_uniform([vocab_size, embedding_size], -0.25, 0.25),trainable=False,
name="W")
self.embedded_chars = tf.nn.embedding_lookup(self.W, self.input_x)
#self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)
with tf.name_scope("highway"):
W = tf.Variable(tf.truncated_normal([embedding_size,embedding_size],stddev = 0.1),name = "weight")
W_T = tf.Variable(tf.truncated_normal([embedding_size, embedding_size], stddev=0.1), name="weight_t")
b = tf.Variable(tf.constant(0.1,shape=[embedding_size]),name = "bias")
b_T = tf.Variable(tf.constant(0.1, shape=[embedding_size]), name="bias_T")
T = tf.nn.relu(tf.map_fn(lambda x:tf.nn.xw_plus_b(x, W, b, name="non-linear-activation"),self.embedded_chars))
t = tf.sigmoid(
tf.map_fn(lambda x: tf.nn.xw_plus_b(x, W_T, b_T, name="transform_gate"), self.embedded_chars))
c = tf.subtract(1.0, t, name="carry_gate")
output = tf.add(tf.multiply(T,t),tf.multiply(self.embedded_chars,c))
print ("output")
print (output.shape)
self.embedded_chars_expanded = tf.expand_dims(output, -1)
# Create a convolution + maxpool layer for each filter size
pooled_outputs = []
for i, filter_size in enumerate(filter_sizes):
with tf.name_scope("conv-maxpool-%s" % filter_size):
# Convolution Layer
filter_shape = [filter_size, embedding_size, 1, num_filters]
W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b")
conv = tf.nn.conv2d(
self.embedded_chars_expanded,
W,
strides=[1, 1, 1, 1],
padding="VALID",
name="conv")
# Apply nonlinearity
h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")
# Maxpooling over the outputs
pooled = tf.nn.max_pool(
#pooled = tf.nn.avg_pool(
h,
ksize=[1, sequence_length - filter_size + 1, 1, 1],
strides=[1, 1, 1, 1],
padding='VALID',
name="pool")
pooled_outputs.append(pooled)
# Combine all the pooled features
num_filters_total = num_filters * len(filter_sizes)
self.h_pool = tf.concat(pooled_outputs, 3)
self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total])
# Add dropout
with tf.name_scope("dropout"):
self.h_drop = tf.nn.dropout(self.h_pool_flat, self.dropout_keep_prob)
# Final (unnormalized) scores and predictions
with tf.name_scope("output"):
W = tf.get_variable(
"W",
shape=[num_filters_total, num_classes],
initializer=tf.contrib.layers.xavier_initializer())
b = tf.Variable(tf.constant(0.1, shape=[num_classes]), name="b")
l2_loss += tf.nn.l2_loss(W)
l2_loss += tf.nn.l2_loss(b)
self.scores = tf.nn.xw_plus_b(self.h_drop, W, b, name="scores")
self.predictions = tf.argmax(self.scores, 1, name="predictions")
#Highway layer
print (self.h_drop.shape)
# CalculateMean cross-entropy loss
with tf.name_scope("loss"):
losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.scores, labels=self.input_y)
self.loss = tf.reduce_mean(losses) + l2_reg_lambda * l2_loss
# optimizer = tf.train.AdamOptimizer(learning_rate)
# grads_and_vars = optimizer.compute_gradients(self.loss)
# self.train_op = optimizer.apply_gradients(grads_and_vars)
# Accuracy
with tf.name_scope("accuracy"):
correct_predictions = tf.equal(self.predictions, tf.argmax(self.input_y, 1))
self.accuracy = tf.reduce_mean(tf.cast(correct_predictions, "float"), name="accuracy")
self.y = tf.argmax(self.input_y, 1)