基于bAbI数据集训练记忆网络
bAbi: 来自 FAIR（Facebook AI Research，脸书人工智能研究）的合成式阅读理解与问答数据集。
官网：https://research.fb.com/downloads/babi/
代码注释
'''Trains a memory network on the bAbI dataset.
基于bAbI数据集训练记忆网络
bAbi: 来自 FAIR（Facebook AI Research，脸书人工智能研究）的合成式阅读理解与问答数据集。
官网：https://research.fb.com/downloads/babi/
References:
参考
- Jason Weston, Antoine Bordes, Sumit Chopra, Tomas Mikolov, Alexander M. Rush,
"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks",
面向AI完成的问答：一组必备的玩具任务
http://arxiv.org/abs/1502.05698
- Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus,
"End-To-End Memory Networks",
端对端记忆网络
http://arxiv.org/abs/1503.08895
Reaches 98.6% accuracy on task 'single_supporting_fact_10k' after 120 epochs.
Time per epoch: 3s on CPU (core i7).
120个周期后，single_supporting_fact_10k任务达到98.6%精确度，
每个周期3s基于cpu（Central Processing Unit，中央处理器）（intel i7的架构）
'''
from __future__ import print_function
from keras.models import Sequential, Model
from keras.layers.embeddings import Embedding
from keras.layers import Input, Activation, Dense, Permute, Dropout, add, dot, concatenate
from keras.layers import LSTM
from keras.utils.data_utils import get_file
from keras.preprocessing.sequence import pad_sequences
from functools import reduce
import tarfile
import numpy as np
import re
def tokenize(sent):
'''Return the tokens of a sentence including punctuation.
返回包含标点符号的句子的词序列（句子分解后的各部分）
>>> tokenize('Bob dropped the apple. Where is the apple?')
['Bob', 'dropped', 'the', 'apple', '.', 'Where', 'is', 'the', 'apple', '?']
'''
return [x.strip() for x in re.split('(\W+)?', sent) if x.strip()]
def parse_stories(lines, only_supporting=False):
'''Parse stories provided in the bAbi tasks format
基于bAbi（数据集）任务模式，解析故事
If only_supporting is true, only the sentences
that support the answer are kept.
只要支持是真的，只有支持答案的句子被保留下来。
'''
data = []
story = []
for line in lines:
line = line.decode('utf-8').strip()
nid, line = line.split(' ', 1)
nid = int(nid)
if nid == 1:
story = []
if '\t' in line:
q, a, supporting = line.split('\t')
q = tokenize(q)
substory = None
if only_supporting:
# Only select the related substory
supporting = map(int, supporting.split())
substory = [story[i - 1] for i in supporting]
else:
# Provide all the substories
# 提供所有子故事
substory = [x for x in story if x]
data.append((substory, q, a))
story.append('')
else:
sent = tokenize(line)
story.append(sent)
return data
def get_stories(f, only_supporting=False, max_length=None):
'''Given a file name, read the file,
根据文件名，读文件
retrieve the stories,
检索故事
and then convert the sentences into a single story.
转换句子为一个故事
If max_length is supplied,
any stories longer than max_length tokens will be discarded.
如果最大长度已提供，
'''
data = parse_stories(f.readlines(), only_supporting=only_supporting)
flatten = lambda data: reduce(lambda x, y: x + y, data)
data = [(flatten(story), q, answer) for story, q, answer in data if not max_length or len(flatten(story)) < max_length]
return data
def vectorize_stories(data):
inputs, queries, answers = [], [], []
for story, query, answer in data:
inputs.append([word_idx[w] for w in story])
queries.append([word_idx[w] for w in query])
answers.append(word_idx[answer])
return (pad_sequences(inputs, maxlen=story_maxlen),
pad_sequences(queries, maxlen=query_maxlen),
np.array(answers))
try:
path = get_file('babi-tasks-v1-2.tar.gz', origin='https://s3.amazonaws.com/text-datasets/babi_tasks_1-20_v1-2.tar.gz')
except:
print('Error downloading dataset, please download it manually:\n'
'$ wget http://www.thespermwhale.com/jaseweston/babi/tasks_1-20_v1-2.tar.gz\n'
'$ mv tasks_1-20_v1-2.tar.gz ~/.keras/datasets/babi-tasks-v1-2.tar.gz')
raise
challenges = {
# QA1 with 10,000 samples
# 问答数据集1:包含 10,000个样本
'single_supporting_fact_10k': 'tasks_1-20_v1-2/en-10k/qa1_single-supporting-fact_{}.txt',
# QA2 with 10,000 samples
# 问答数据集2:包含 10,000个样本
'two_supporting_facts_10k': 'tasks_1-20_v1-2/en-10k/qa2_two-supporting-facts_{}.txt',
}
challenge_type = 'single_supporting_fact_10k'
challenge = challenges[challenge_type]
print('Extracting stories for the challenge:', challenge_type)
with tarfile.open(path) as tar:
train_stories = get_stories(tar.extractfile(challenge.format('train')))
test_stories = get_stories(tar.extractfile(challenge.format('test')))
vocab = set()
for story, q, answer in train_stories + test_stories:
vocab |= set(story + q + [answer])
vocab = sorted(vocab)
# Reserve 0 for masking via pad_sequences
# 通过ad_sequences掩膜的保留0
vocab_size = len(vocab) + 1
story_maxlen = max(map(len, (x for x, _, _ in train_stories + test_stories)))
query_maxlen = max(map(len, (x for _, x, _ in train_stories + test_stories)))
print('-')
print('Vocab size:', vocab_size, 'unique words')
print('Story max length:', story_maxlen, 'words')
print('Query max length:', query_maxlen, 'words')
print('Number of training stories:', len(train_stories))
print('Number of test stories:', len(test_stories))
print('-')
print('Here\'s what a "story" tuple looks like (input, query, answer):')
print(train_stories[0])
print('-')
print('Vectorizing the word sequences...')
word_idx = dict((c, i + 1) for i, c in enumerate(vocab))
inputs_train, queries_train, answers_train = vectorize_stories(train_stories)
inputs_test, queries_test, answers_test = vectorize_stories(test_stories)
print('-')
print('inputs: integer tensor of shape (samples, max_length)')
print('inputs_train shape:', inputs_train.shape)
print('inputs_test shape:', inputs_test.shape)
print('-')
print('queries: integer tensor of shape (samples, max_length)')
print('queries_train shape:', queries_train.shape)
print('queries_test shape:', queries_test.shape)
print('-')
print('answers: binary (1 or 0) tensor of shape (samples, vocab_size)')
print('answers_train shape:', answers_train.shape)
print('answers_test shape:', answers_test.shape)
print('-')
print('Compiling...')
# placeholders
# 占位符
input_sequence = Input((story_maxlen,))
question = Input((query_maxlen,))
# encoders
# 编码器
# embed the input sequence into a sequence of vectors
# 输入序列嵌入到向量序列
input_encoder_m = Sequential()
input_encoder_m.add(Embedding(input_dim=vocab_size,
output_dim=64))
input_encoder_m.add(Dropout(0.3))
# output: (samples, story_maxlen, embedding_dim)
# 输出：（样本，故事最大长度，嵌入维度）
# embed the input into a sequence of vectors of size query_maxlen
# 输入序列嵌入到向量序列，该序列大小为query_maxlen
input_encoder_c = Sequential()
input_encoder_c.add(Embedding(input_dim=vocab_size,
output_dim=query_maxlen))
input_encoder_c.add(Dropout(0.3))
# output: (samples, story_maxlen, query_maxlen)
# 输出：（样本，故事最大长度，问题最大长度）
# embed the question into a sequence of vectors
# 输入序列嵌入到向量序列
question_encoder = Sequential()
question_encoder.add(Embedding(input_dim=vocab_size,
output_dim=64,
input_length=query_maxlen))
question_encoder.add(Dropout(0.3))
# output: (samples, query_maxlen, embedding_dim)
# 输出：(samples, query_maxlen, embedding_dim)
# encode input sequence and questions (which are indices)
# to sequences of dense vectors
# 编码输入序列和问题（索引）为全连接向量序列
input_encoded_m = input_encoder_m(input_sequence)
input_encoded_c = input_encoder_c(input_sequence)
question_encoded = question_encoder(question)
# compute a 'match' between the first input vector sequence
# and the question vector sequence
# 计算第一输入向量序列与问题向量序列之间的“匹配”
# shape: `(samples, story_maxlen, query_maxlen)`
# 形状：(samples, story_maxlen, query_maxlen)`
match = dot([input_encoded_m, question_encoded], axes=(2, 2))
match = Activation('softmax')(match)
# add the match matrix with the second input vector sequence
# 用第二输入向量序列加入匹配矩阵
response = add([match, input_encoded_c]) # (samples, story_maxlen, query_maxlen)
response = Permute((2, 1))(response) # (samples, query_maxlen, story_maxlen)
# concatenate the match matrix with the question vector sequence
# 用问题向量序列串接匹配矩阵
answer = concatenate([response, question_encoded])
# the original paper uses a matrix multiplication for this reduction step.
# 原论文使用矩阵相乘降低步骤
# we choose to use a RNN instead.
# 本文选择RNN（循环神经网络）替换
answer = LSTM(32)(answer) # (samples, 32)
# one regularization layer -- more would probably be needed.
# 一个正则化层--很需要。
answer = Dropout(0.3)(answer)
answer = Dense(vocab_size)(answer) # (samples, vocab_size)
# we output a probability distribution over the vocabulary
# 基于词汇表输出概率分布
answer = Activation('softmax')(answer)
# build the final model
# 建立模型
model = Model([input_sequence, question], answer)
model.compile(optimizer='rmsprop', loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
# train
# 训练
model.fit([inputs_train, queries_train], answers_train,
batch_size=32,
epochs=120,
validation_data=([inputs_test, queries_test], answers_test))
代码执行
Keras详细介绍
中文：http://keras-cn.readthedocs.io/en/latest/
实例下载
https://github.com/keras-team/keras
https://github.com/keras-team/keras/tree/master/examples
完整项目下载
方便没积分童鞋，请加企鹅452205574，共享文件夹。
包括：代码、数据集合（图片）、已生成model、安装库文件等。
