cnn_relation_extraction部分记录
import tensorflow as tf
import numpy as np
import os
import datetime
import time
from cnn_relation_extraction_master.text_cnn import TextCNN
from cnn_relation_extraction_master.data_helpers import *
from sklearn.metrics import f1_score
import warnings
import sklearn.exceptions
warnings.filterwarnings("ignore", category=sklearn.exceptions.UndefinedMetricWarning)
# Parameters
# ==================================================
# Data loading params 语料路径
tf.flags.DEFINE_string("train_dir", "SemEval2010_task8_all_data/SemEval2010_task8_training/TRAIN_FILE.TXT", "Path of train data")
tf.flags.DEFINE_float("dev_sample_percentage", .1, "Percentage of the training data to use for validation")
tf.flags.DEFINE_integer("max_sentence_length", 100, "Max sentence length in train(98)/test(70) data (Default: 100)")
# 第一个是参数名称，第二个是默认值，第三个是参数描述
# Model Hyperparameters 网络参数
tf.flags.DEFINE_string("word2vec", r"D:\file_download\BaiduNetdiskDownload\PyCharm_File\wiki_en_word2vec-master\wiki.en.text.vector", "Word2vec file with pre-trained embeddings")
tf.flags.DEFINE_integer("text_embedding_dim", 400, "Dimensionality of word embedding (Default: 300)")
tf.flags.DEFINE_integer("position_embedding_dim", 100, "Dimensionality of position embedding (Default: 100)")
tf.flags.DEFINE_string("filter_sizes", "2,3,4,5", "Comma-separated filter sizes (Default: 2,3,4,5)")
tf.flags.DEFINE_integer("num_filters", 128, "Number of filters per filter size (Default: 128)")
tf.flags.DEFINE_float("dropout_keep_prob", 0.5, "Dropout keep probability (Default: 0.5)")
tf.flags.DEFINE_float("l2_reg_lambda", 3.0, "L2 regularization lambda (Default: 3.0)")
# Training parameters
tf.flags.DEFINE_integer("batch_size", 64, "Batch Size (Default: 64)")
tf.flags.DEFINE_integer("num_epochs", 100, "Number of training epochs (Default: 100)")
tf.flags.DEFINE_integer("display_every", 10, "Number of iterations to display training info.")
tf.flags.DEFINE_integer("evaluate_every", 100, "Evaluate model on dev set after this many steps")
tf.flags.DEFINE_integer("checkpoint_every", 100, "Save model after this many steps")
tf.flags.DEFINE_integer("num_checkpoints", 5, "Number of checkpoints to store")
tf.flags.DEFINE_float("learning_rate", 1e-3, "Which learning rate to start with. (Default: 1e-3)")
# Misc Parameters
tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement")
tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices")
FLAGS = tf.flags.FLAGS # FLAGS保存命令行参数的数据
FLAGS._parse_flags() # 将其解析成字典存储到FLAGS.__flags中
print("\nParameters:")
for attr, value in sorted(FLAGS.__flags.items()):
print("{} = {}".format(attr.upper(), value))
print("")
def train():
with tf.device('/cpu:0'):
x_text, pos1, pos2, y = load_data_and_labels(FLAGS.train_dir) # 将语料进行处理并转为df,label转为one-hot
# Build vocabulary
# Example: x_text[3] = "A misty <e1>ridge</e1> uprises from the <e2>surge</e2>."
# ['a misty ridge uprises from the surge <UNK> <UNK> ... <UNK>']
# =>
# [27 39 40 41 42 1 43 0 0 ... 0]
# dimension = FLAGS.max_sentence_length
text_vocab_processor = tf.contrib.learn.preprocessing.VocabularyProcessor(FLAGS.max_sentence_length)
text_vec = np.array(list(text_vocab_processor.fit_transform(x_text)))
print("Text Vocabulary Size: {:d}".format(len(text_vocab_processor.vocabulary_)))
# Example: pos1[3] = [-2 -1 0 1 2 3 4 999 999 999 ... 999]
# [95 96 97 98 99 100 101 999 999 999 ... 999]
# =>
# [11 12 13 14 15 16 21 17 17 17 ... 17]
# dimension = MAX_SENTENCE_LENGTH
pos_vocab_processor = tf.contrib.learn.preprocessing.VocabularyProcessor(FLAGS.max_sentence_length)
pos_vocab_processor.fit(pos1 + pos2)
pos1_vec = np.array(list(pos_vocab_processor.transform(pos1)))
pos2_vec = np.array(list(pos_vocab_processor.transform(pos2)))
print("Position Vocabulary Size: {:d}".format(len(pos_vocab_processor.vocabulary_)))
x = np.array([list(i) for i in zip(text_vec, pos1_vec, pos2_vec)])
print("x = {0}".format(x.shape))
print("y = {0}".format(y.shape))
print("")
# Randomly shuffle data
np.random.seed(10)
shuffle_indices = np.random.permutation(np.arange(len(y)))
x_shuffled = x[shuffle_indices]
y_shuffled = y[shuffle_indices]
# Split train/test set
# TODO: This is very crude, should use cross-validation
dev_sample_index = -1 * int(FLAGS.dev_sample_percentage * float(len(y)))
x_train, x_dev = x_shuffled[:dev_sample_index], x_shuffled[dev_sample_index:]
x_dev = np.array(x_dev).transpose((1, 0, 2))
y_train, y_dev = y_shuffled[:dev_sample_index], y_shuffled[dev_sample_index:]
print("Train/Dev split: {:d}/{:d}\n".format(len(y_train), len(y_dev)))
with tf.Graph().as_default():
session_conf = tf.ConfigProto(
allow_soft_placement=FLAGS.allow_soft_placement,
log_device_placement=FLAGS.log_device_placement)
sess = tf.Session(config=session_conf)
with sess.as_default():
cnn = TextCNN(
sequence_length=x_train.shape[2],
num_classes=y_train.shape[1],
text_vocab_size=len(text_vocab_processor.vocabulary_),
text_embedding_size=FLAGS.text_embedding_dim,
pos_vocab_size=len(pos_vocab_processor.vocabulary_),
pos_embedding_size=FLAGS.position_embedding_dim,
filter_sizes=list(map(int, FLAGS.filter_sizes.split(","))),
num_filters=FLAGS.num_filters,
l2_reg_lambda=FLAGS.l2_reg_lambda)
# Define Training procedure
global_step = tf.Variable(0, name="global_step", trainable=False)
train_op = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(cnn.loss, global_step=global_step)
# Output directory for models and summaries
timestamp = str(int(time.time()))
out_dir = os.path.abspath(os.path.join(os.path.curdir, "runs", timestamp))
print("Writing to {}\n".format(out_dir))
# Summaries for loss and accuracy
loss_summary = tf.summary.scalar("loss", cnn.loss)
acc_summary = tf.summary.scalar("accuracy", cnn.accuracy)
# Train Summaries
train_summary_op = tf.summary.merge([loss_summary, acc_summary])
train_summary_dir = os.path.join(out_dir, "summaries", "train")
train_summary_writer = tf.summary.FileWriter(train_summary_dir, sess.graph)
# Dev summaries
dev_summary_op = tf.summary.merge([loss_summary, acc_summary])
dev_summary_dir = os.path.join(out_dir, "summaries", "dev")
dev_summary_writer = tf.summary.FileWriter(dev_summary_dir, sess.graph)
# Checkpoint directory. Tensorflow assumes this directory already exists so we need to create it
checkpoint_dir = os.path.abspath(os.path.join(out_dir, "checkpoints"))
checkpoint_prefix = os.path.join(checkpoint_dir, "model")
if not os.path.exists(checkpoint_dir):
os.makedirs(checkpoint_dir)
saver = tf.train.Saver(tf.global_variables(), max_to_keep=FLAGS.num_checkpoints)
# Write vocabulary
text_vocab_processor.save(os.path.join(out_dir, "text_vocab"))
pos_vocab_processor.save(os.path.join(out_dir, "position_vocab"))
# Initialize all variables
sess.run(tf.global_variables_initializer())
# Pre-trained word2vec
if FLAGS.word2vec:
# initial matrix with random uniform
initW = np.random.uniform(-0.25, 0.25, (len(text_vocab_processor.vocabulary_), FLAGS.text_embedding_dim))
# load any vectors from the word2vec
print("Load word2vec file {0}".format(FLAGS.word2vec))
with open(FLAGS.word2vec, "rb") as f:
header = f.readline()
vocab_size, layer1_size = map(int, header.split())
binary_len = np.dtype('float32').itemsize * layer1_size
for line in range(vocab_size):
word = []
while True:
ch = f.read(1).decode('latin-1')
if ch == ' ':
word = ''.join(word)
break
if ch != '\n':
word.append(ch)
idx = text_vocab_processor.vocabulary_.get(word)
if idx != 0:
initW[idx] = np.fromstring(f.read(binary_len), dtype='float32')
else:
f.read(binary_len)
sess.run(cnn.W_text.assign(initW))
print("Success to load pre-trained word2vec model!\n")
# Generate batches
batches = batch_iter(
list(zip(x_train, y_train)), FLAGS.batch_size, FLAGS.num_epochs)
# Training loop. For each batch...
for batch in batches:
x_batch, y_batch = zip(*batch)
x_batch = np.array(x_batch).transpose((1, 0, 2))
# Train
feed_dict = {
cnn.input_text: x_batch[0],
cnn.input_pos1: x_batch[1],
cnn.input_pos2: x_batch[2],
cnn.input_y: y_batch,
cnn.dropout_keep_prob: FLAGS.dropout_keep_prob
}
_, step, summaries, loss, accuracy = sess.run(
[train_op, global_step, train_summary_op, cnn.loss, cnn.accuracy], feed_dict)
train_summary_writer.add_summary(summaries, step)
# Training log display
if step % FLAGS.display_every == 0:
time_str = datetime.datetime.now().isoformat()
print("{}: step {}, loss {:g}, acc {:g}".format(time_str, step, loss, accuracy))
# Evaluation
if step % FLAGS.evaluate_every == 0:
print("\nEvaluation:")
feed_dict = {
cnn.input_text: x_dev[0],
cnn.input_pos1: x_dev[1],
cnn.input_pos2: x_dev[2],
cnn.input_y: y_dev,
cnn.dropout_keep_prob: 1.0
}
summaries, loss, accuracy, predictions = sess.run(
[dev_summary_op, cnn.loss, cnn.accuracy, cnn.predictions], feed_dict)
dev_summary_writer.add_summary(summaries, step)
time_str = datetime.datetime.now().isoformat()
print("{}: step {}, loss {:g}, acc {:g}".format(time_str, step, loss, accuracy))
print("(2*9+1)-Way Macro-Average F1 Score (excluding Other): {:g}\n".format(
f1_score(np.argmax(y_dev, axis=1), predictions, labels=np.array(range(1, 19)), average="macro")))
# Model checkpoint
if step % FLAGS.checkpoint_every == 0:
path = saver.save(sess, checkpoint_prefix, global_step=step)
print("Saved model checkpoint to {}\n".format(path))
def main(_):
train()
if __name__ == "__main__":
tf.app.run()import tensorflow as tf
class TextCNN:
def __init__(self, sequence_length, num_classes,
text_vocab_size, text_embedding_size, pos_vocab_size, pos_embedding_size,
filter_sizes, num_filters, l2_reg_lambda=0.0):
# Placeholders for input, output and dropout
self.input_text = tf.placeholder(tf.int32, shape=[None, sequence_length], name='input_text')
self.input_pos1 = tf.placeholder(tf.int32, shape=[None, sequence_length], name='input_pos1')
self.input_pos2 = tf.placeholder(tf.int32, shape=[None, sequence_length], name='input_pos2')
self.input_y = tf.placeholder(tf.float32, shape=[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("text-embedding"):
self.W_text = tf.Variable(tf.random_uniform([text_vocab_size, text_embedding_size], -1.0, 1.0), name="W_text")
self.text_embedded_chars = tf.nn.embedding_lookup(self.W_text, self.input_text)
self.text_embedded_chars_expanded = tf.expand_dims(self.text_embedded_chars, -1)
with tf.device('/cpu:0'), tf.name_scope("position-embedding"):
self.W_position = tf.Variable(tf.random_uniform([pos_vocab_size, pos_embedding_size], -1.0, 1.0), name="W_position")
self.pos1_embedded_chars = tf.nn.embedding_lookup(self.W_position, self.input_pos1)
self.pos1_embedded_chars_expanded = tf.expand_dims(self.pos1_embedded_chars, -1)
self.pos2_embedded_chars = tf.nn.embedding_lookup(self.W_position, self.input_pos2)
self.pos2_embedded_chars_expanded = tf.expand_dims(self.pos2_embedded_chars, -1)
self.embedded_chars_expanded = tf.concat([self.text_embedded_chars_expanded,
self.pos1_embedded_chars_expanded,
self.pos2_embedded_chars_expanded], 2)
embedding_size = text_embedding_size + 2*pos_embedding_size
# 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(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 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.logits = tf.nn.xw_plus_b(self.h_drop, W, b, name="logits")
self.predictions = tf.argmax(self.logits, 1, name="predictions")
# Calculate mean cross-entropy loss
with tf.name_scope("loss"):
losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.logits, labels=self.input_y)
self.loss = tf.reduce_mean(losses) + l2_reg_lambda * l2_loss
# 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, tf.float32), name="accuracy")
-----------------------------------------------------------------------------手动分割线 ----------------------------------------------------------------------------
- tf.flags.DEFINE_xxx()
用于接受命令行的可选参数。就是说利用该函数我们可以实现在命令行中选择需要设定的参数来运行程序， 可以不用反复修改源代码中的参数，直接在命令行中进行参数的设定。
- FLAGS = tf.flags.FLAGS # FLAGS保存命令行参数的数据
- FLAGS._parse_flags() # 将其解析成字典存储到FLAGS.__flags中
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
