词向量嵌入的实例详解(2)-木庄网络博客

当前第2页返回上一页

import tensorflow as tf
import numpy as np
from helpers import lazy_property
class EmbeddingModel:
def __init__(self, data, target, params):
self.data = data
self.target = target
self.params = params
self.embeddings
self.cost
self.optimize
@lazy_property
def embeddings(self):
initial = tf.random_uniform(
[self.params.vocabulary_size, self.params.embedding_size],
-1.0, 1.0)
return tf.Variable(initial)
@lazy_property
def optimize(self):
optimizer = tf.train.MomentumOptimizer(
self.params.learning_rate, self.params.momentum)
return optimizer.minimize(self.cost)
@lazy_property
def cost(self):
embedded = tf.nn.embedding_lookup(self.embeddings, self.data)
weight = tf.Variable(tf.truncated_normal(
[self.params.vocabulary_size, self.params.embedding_size],
stddev=1.0 / self.params.embedding_size ** 0.5))
bias = tf.Variable(tf.zeros([self.params.vocabulary_size]))
target = tf.expand_dims(self.target, 1)
return tf.reduce_mean(tf.nn.nce_loss(
weight, bias, embedded, target,
self.params.contrastive_examples,
self.params.vocabulary_size))

import collections
import tensorflow as tf
import numpy as np
from batched import batched
from EmbeddingModel import EmbeddingModel
from skipgrams import skipgrams
from Wikipedia import Wikipedia
from helpers import AttrDict
WIKI_DOWNLOAD_DIR = './wikipedia'
params = AttrDict(
vocabulary_size=10000,
max_context=10,
embedding_size=200,
contrastive_examples=100,
learning_rate=0.5,
momentum=0.5,
batch_size=1000,
)
data = tf.placeholder(tf.int32, [None])
target = tf.placeholder(tf.int32, [None])
model = EmbeddingModel(data, target, params)
corpus = Wikipedia(
'https://dumps.wikimedia.org/enwiki/20160501/'
'enwiki-20160501-pages-meta-current1.xml-p000000010p000030303.bz2',
WIKI_DOWNLOAD_DIR,
params.vocabulary_size)
examples = skipgrams(corpus, params.max_context)
batches = batched(examples, params.batch_size)
sess = tf.Session()
sess.run(tf.initialize_all_variables())
average = collections.deque(maxlen=100)
for index, batch in enumerate(batches):
feed_dict = {data: batch[0], target: batch[1]}
cost, _ = sess.run([model.cost, model.optimize], feed_dict)
average.append(cost)
print('{}: {:5.1f}'.format(index + 1, sum(average) / len(average)))
if index > 100000:
break
embeddings = sess.run(model.embeddings)
np.save(WIKI_DOWNLOAD_DIR + '/embeddings.npy', embeddings)