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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
|
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Example of Estimator for CNN-based text classification with DBpedia data."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import sys
import numpy as np
import pandas
import tensorflow as tf
FLAGS = None
MAX_DOCUMENT_LENGTH = 100
EMBEDDING_SIZE = 20
N_FILTERS = 10
WINDOW_SIZE = 20
FILTER_SHAPE1 = [WINDOW_SIZE, EMBEDDING_SIZE]
FILTER_SHAPE2 = [WINDOW_SIZE, N_FILTERS]
POOLING_WINDOW = 4
POOLING_STRIDE = 2
n_words = 0
MAX_LABEL = 15
WORDS_FEATURE = 'words' # Name of the input words feature.
def cnn_model(features, labels, mode):
"""2 layer ConvNet to predict from sequence of words to a class."""
# Convert indexes of words into embeddings.
# This creates embeddings matrix of [n_words, EMBEDDING_SIZE] and then
# maps word indexes of the sequence into [batch_size, sequence_length,
# EMBEDDING_SIZE].
word_vectors = tf.contrib.layers.embed_sequence(
features[WORDS_FEATURE], vocab_size=n_words, embed_dim=EMBEDDING_SIZE)
word_vectors = tf.expand_dims(word_vectors, 3)
with tf.variable_scope('CNN_Layer1'):
# Apply Convolution filtering on input sequence.
conv1 = tf.layers.conv2d(
word_vectors,
filters=N_FILTERS,
kernel_size=FILTER_SHAPE1,
padding='VALID',
# Add a ReLU for non linearity.
activation=tf.nn.relu)
# Max pooling across output of Convolution+Relu.
pool1 = tf.layers.max_pooling2d(
conv1,
pool_size=POOLING_WINDOW,
strides=POOLING_STRIDE,
padding='SAME')
# Transpose matrix so that n_filters from convolution becomes width.
pool1 = tf.transpose(pool1, [0, 1, 3, 2])
with tf.variable_scope('CNN_Layer2'):
# Second level of convolution filtering.
conv2 = tf.layers.conv2d(
pool1,
filters=N_FILTERS,
kernel_size=FILTER_SHAPE2,
padding='VALID')
# Max across each filter to get useful features for classification.
pool2 = tf.squeeze(tf.reduce_max(conv2, 1), axis=[1])
# Apply regular WX + B and classification.
logits = tf.layers.dense(pool2, MAX_LABEL, activation=None)
predicted_classes = tf.argmax(logits, 1)
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(
mode=mode,
predictions={
'class': predicted_classes,
'prob': tf.nn.softmax(logits)
})
loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
if mode == tf.estimator.ModeKeys.TRAIN:
optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
train_op = optimizer.minimize(loss, global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)
eval_metric_ops = {
'accuracy': tf.metrics.accuracy(
labels=labels, predictions=predicted_classes)
}
return tf.estimator.EstimatorSpec(
mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
def main(unused_argv):
global n_words
# Prepare training and testing data
dbpedia = tf.contrib.learn.datasets.load_dataset(
'dbpedia', test_with_fake_data=FLAGS.test_with_fake_data)
x_train = pandas.DataFrame(dbpedia.train.data)[1]
y_train = pandas.Series(dbpedia.train.target)
x_test = pandas.DataFrame(dbpedia.test.data)[1]
y_test = pandas.Series(dbpedia.test.target)
# Process vocabulary
vocab_processor = tf.contrib.learn.preprocessing.VocabularyProcessor(
MAX_DOCUMENT_LENGTH)
x_train = np.array(list(vocab_processor.fit_transform(x_train)))
x_test = np.array(list(vocab_processor.transform(x_test)))
n_words = len(vocab_processor.vocabulary_)
print('Total words: %d' % n_words)
# Build model
classifier = tf.estimator.Estimator(model_fn=cnn_model)
# Train.
train_input_fn = tf.estimator.inputs.numpy_input_fn(
x={WORDS_FEATURE: x_train},
y=y_train,
batch_size=len(x_train),
num_epochs=None,
shuffle=True)
classifier.train(input_fn=train_input_fn, steps=100)
# Evaluate.
test_input_fn = tf.estimator.inputs.numpy_input_fn(
x={WORDS_FEATURE: x_test},
y=y_test,
num_epochs=1,
shuffle=False)
scores = classifier.evaluate(input_fn=test_input_fn)
print('Accuracy: {0:f}'.format(scores['accuracy']))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument(
'--test_with_fake_data',
default=False,
help='Test the example code with fake data.',
action='store_true')
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
|
