Tutorials on training the Skip-thoughts vectors for features extraction of sentence.
Tutorials on training the Skip-thoughts vectors for features extraction of sentence.
1. Send emails and download the training dataset.
the dataset used in skip_thoughts vectors is from [BookCorpus]: http://yknzhu.wixsite.com/mbweb
first, you should send a email to the auther of this paper and ask for the link of this dataset. Then you will download the following files:
unzip these files in the current folders.
2. Open and download the tensorflow version code.
Do as the following links: https://github.com/tensorflow/models/tree/master/research/skip_thoughts
Then, you will see the processing as follows:
[Attention] when you install the bazel, you need to install this software, but do not update it. Or, it may shown you some errors in the following operations.
3. Install the packages needed.
- Bazel (instructions)
- TensorFlow (instructions)
- NumPy (instructions)
- scikit-learn (instructions)
- Natural Language Toolkit (NLTK)
- First install NLTK (instructions)
- Then install the NLTK data (instructions)
- gensim (instructions)
- Only required if you will be expanding your vocabulary with the word2vec model.
4. Encoding Sentences :
run the following py files.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import os.path
import scipy.spatial.distance as sd
from skip_thoughts import configuration
from skip_thoughts import encoder_manager
import pdb print("==>> Skip-Thought Vector ") # Set paths to the model.
VOCAB_FILE = "./skip_thoughts/pretrained/skip_thoughts_bi_2017_02_16/vocab.txt"
EMBEDDING_MATRIX_FILE = "./skip_thoughts/pretrained/skip_thoughts_bi_2017_02_16/embeddings.npy"
CHECKPOINT_PATH = "./skip_thoughts/model/train/model.ckpt-78581"
# The following directory should contain files rt-polarity.neg and rt-polarity.pos. # Set up the encoder. Here we are using a single unidirectional model.
# To use a bidirectional model as well, call load_model() again with
# configuration.model_config(bidirectional_encoder=True) and paths to the
# bidirectional model's files. The encoder will use the concatenation of
# all loaded models. print("==>> loading the pre-trained models ... ") encoder = encoder_manager.EncoderManager()
encoder.load_model(configuration.model_config(),
vocabulary_file=VOCAB_FILE,
embedding_matrix_file=EMBEDDING_MATRIX_FILE,
checkpoint_path=CHECKPOINT_PATH) print("==>> Done !") # Load the movie review dataset.
data = [' This is my second attempt to the tensorflow version skip_thought_vectors ... '] print("==>> the given sentence is: ", data) # Generate Skip-Thought Vectors for each sentence in the dataset.
encodings = encoder.encode(data) print("==>> the sentence feature is: ", encodings) ## the output feature is 2400 dimension.
wangxiao@AHU:/media/wangxiao/49cd8079-e619-4e4b-89b1-15c86afb5102/skip_thought_vector_onlineModels$ python run_sentence_feature_extraction.py
RuntimeError: module compiled against API version 0xc but this version of numpy is 0xb
RuntimeError: module compiled against API version 0xc but this version of numpy is 0xb
==>> Skip-Thought Vector
==>> loading the pre-trained models ...
WARNING:tensorflow:From ./skip_thoughts/skip_thoughts_model.py:360: create_global_step (from tensorflow.contrib.framework.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.create_global_step
2018-05-13 21:36:27.670186: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
==>> Done !
==>> the given sentence is: [' This is my second attempt to the tensorflow version skip_thought_vectors ... ']
==>> the sentence feature is: [[-0.00676637 0.01928637 -0.01759908 ..., 0.00851333 0.00875245 -0.0040213 ]]
> ./run_sentence_feature_extraction.py(48)<module>()
-> print("==>> the encodings[0] is: ", encodings[0])
(Pdb) x = encodings[0]
(Pdb) x.size
2400
(Pdb)
as we can see from above terminal, the output feature vector is 2400-D.
...
Tutorials on training the Skip-thoughts vectors for features extraction of sentence.的更多相关文章
- Training Deep Neural Networks
http://handong1587.github.io/deep_learning/2015/10/09/training-dnn.html //转载于 Training Deep Neural ...
- Computer Vision Tutorials from Conferences (2) -- ECCV
ECCV 2012 (http://eccv2012.unifi.it/program/tutorials/) Vision Applications on Mobile using OpenCVGa ...
- awesome-nlp
awesome-nlp A curated list of resources dedicated to Natural Language Processing Maintainers - Keon ...
- [C3] Andrew Ng - Neural Networks and Deep Learning
About this Course If you want to break into cutting-edge AI, this course will help you do so. Deep l ...
- [C2P2] Andrew Ng - Machine Learning
##Linear Regression with One Variable Linear regression predicts a real-valued output based on an in ...
- pytorch做seq2seq注意力模型的翻译
以下是对pytorch 1.0版本 的seq2seq+注意力模型做法语--英语翻译的理解(这个代码在pytorch0.4上也可以正常跑): # -*- coding: utf-8 -*- " ...
- [C2P3] Andrew Ng - Machine Learning
##Advice for Applying Machine Learning Applying machine learning in practice is not always straightf ...
- 论文翻译——Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Abstract Semantic word spaces have been very useful but cannot express the meaning of longer phrases ...
- 第五章第四周习题: Transformers Architecture with TensorFlow
目录 Transformer Network Packages 1 - Positional Encoding 1.1 - Sine and Cosine Angles Exercise 1 - ge ...
随机推荐
- Spring boot 入门配置
1,maven 的pom 文件里面引入 <!-- spring boot 父节点依赖,引入这个之后相关的引入就不需要添加version配置,spring boot会自动选择最合适的版本进行添加. ...
- 【封装函数】当前元素距离html文档顶部距离
function getPositionTop(node) { var top = node.offsetTop; var parent = node.offsetParent; while(pare ...
- python相关工具
1.matlab与python之间的数据传递 import scipy.io as sio import numpy as np ###下面是讲解python怎么读取.mat文件以及怎么处理得到的 ...
- python GIL 全局锁,多核cpu下的多线程性能究竟如何?
python GIL 全局锁,多核cpu下的多线程性能究竟如何?GIL全称Global Interpreter Lock GIL是什么? 首先需要明确的一点是GIL并不是Python的特性,它是在实现 ...
- 102.自己实现ArrayList
package collection; import java.util.ArrayList; import java.util.List; /** * 自己实现一个ArrayList,帮助理解底层结 ...
- [转载]PowerDesigner生成的ORACLE 建表脚本中去掉对象的双引号,设置大、小写
若要将 CDM 中将 Entity的标识符都设为指定的大小写,则可以这么设定: 打开cdm的情况下,进入Tools-Model Options-Naming Convention,把Name和Code ...
- 基于jquery 的dateRangePicker 和 My97DatePicker
引入相应的date插件 <script type="text/javascript" src="../plugins/daterangepicker/moment. ...
- 在Eclipse中创建Dynamic Web Project具有和MyEclipse中Web Project一样的目录结构
1.在Eclipse中新建Dynamic Web Project 1.1.修改default output folder build\classes修改为:WebRoot\WEB-INF\classe ...
- ltp-ddt的makefile结构
顶层makefile COMMON_TARGETS := pan utils COMMON_TARGETS += tools testcases/ddt COMMON_TARGET ...
- Spring Boot(十八):使用Spring Boot集成FastDFS
Spring Boot(十八):使用Spring Boot集成FastDFS 环境:Spring Boot最新版本1.5.9.jdk使用1.8.tomcat8.0 功能:使用Spring Boot将文 ...