词向量嵌入的实例详解


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)

以上就是词向量嵌入的实例详解的详细内容,更多文章请关注木庄网络博客!!

返回前面的内容

相关阅读 >>

Python 2.7在linux下安装或升级的操作方法

Python中异常有哪些?Python中异常的详细介绍

Python中hashlib加密模块的分析(代码实例)

pip是啥

Python中的切片是什么?(实例解析)

Python中open函数的用法详解

Python中导入哪个库可以进行大数据分析

Python3怎么运行

Python随机密码的生成教程

Python实现堆栈与队列功能(基于list的append与pop方法)的示例

更多相关阅读请进入《Python》频道 >>




打赏

取消

感谢您的支持,我会继续努力的!

扫码支持
扫码打赏,您说多少就多少

打开支付宝扫一扫,即可进行扫码打赏哦

分享从这里开始,精彩与您同在

评论

管理员已关闭评论功能...