我正在使用Babi数据集上的keras进行以下内存网络代码 -
'''Trains a memory network on the bAbI dataset.
References:
- Jason Weston, Antoine Bordes, Sumit Chopra, Tomas Mikolov, Alexander M. Rush,
"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks",
http://arxiv.org/abs/1502.05698
- Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus,
"End-To-End Memory Networks",
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).
'''
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.
>>> 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
If only_supporting is true, only the sentences
that support the answer are kept.
'''
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
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,
retrieve the stories,
and then convert the sentences into a single story.
If max_length is supplied,
any stories longer than max_length tokens will be discarded.
'''
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, word_idx, story_maxlen, query_maxlen):
X = []
Xq = []
Y = []
for story, query, answer in data:
x = [word_idx[w] for w in story]
xq = [word_idx[w] for w in query]
# let's not forget that index 0 is reserved
y = np.zeros(len(word_idx) + 1)
y[word_idx[answer]] = 1
X.append(x)
Xq.append(xq)
Y.append(y)
return (pad_sequences(X, maxlen=story_maxlen),
pad_sequences(Xq, maxlen=query_maxlen), np.array(Y))
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
tar = tarfile.open(path)
challenges = {
# QA1 with 10,000 samples
'single_supporting_fact_10k': 'tasks_1-20_v1-2/en-10k/qa1_single-supporting-fact_{}.txt',
# QA2 with 10,000 samples
'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)
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
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,
word_idx,
story_maxlen,
query_maxlen)
inputs_test, queries_test, answers_test = vectorize_stories(test_stories,
word_idx,
story_maxlen,
query_maxlen)
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
input_sequence = Input((story_maxlen,))
question = Input((query_maxlen,))
# encoders
# embed the input sequence into a sequence of vectors
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)
# embed the input into a sequence of vectors of size 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)
# embed the question into a sequence of vectors
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)
# encode input sequence and questions (which are indices)
# to sequences of dense vectors
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
# shape: `(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
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
answer = concatenate([response, question_encoded])
# the original paper uses a matrix multiplication for this reduction step.
# we choose to use a RNN instead.
answer = LSTM(32)(answer) # (samples, 32)
# one regularization layer -- more would probably be needed.
answer = Dropout(0.3)(answer)
answer = Dense(vocab_size)(answer) # (samples, vocab_size)
# we output a probability distribution over the vocabulary
answer = Activation('softmax')(answer)
# build the final model
model = Model([input_sequence, question], answer)
model.compile(optimizer='rmsprop', loss='categorical_crossentropy',
metrics=['accuracy'])
# train
model.fit([inputs_train, queries_train], answers_train,
batch_size=32,
epochs=120,
validation_data=([inputs_test, queries_test], answers_test))
这就是我对模型创建部分的理解 -
使用以下代码创建故事和问题部分的密集向量 -
input_encoded_m = input_encoder_m(input_sequence)
input_encoded_c = input_encoder_c(input_sequence)
question_encoded = question_encoder(question)
输出将具有以下形状
input_encoded_m将具有形状 - samples，story_maxlen，query_maxlen input_encoded_c将具有形状 - samples，story_maxlen，query_maxlen question_encoded将具有形状 - samples，query_maxlen，embedding_dim
input_encoded_m和input_encoded_c具有嵌入在不同维度中的相同输入，即（68和4）。而且question_encoded会有问题嵌入。
现在下面的部分匹配故事和问题中的单词，并在输出上应用softmax激活，这意味着匹配单词被识别 -
match = dot([input_encoded_m, question_encoded], axes=(2, 2))
match = Activation('softmax')(match)
我不清楚为什么将不同的嵌入式相同输入向量从上一步添加到匹配矩阵中。评论说＆＃34;第二输入向量＆＃34;但是我们还没有处理第二个输入..没能理解这个，任何帮助??? ＃将匹配矩阵与第二个输入矢量序列相加 response = add（[match，input_encoded_c]）＃（samples，story_maxlen，query_maxlen）
此外，在上下文中输出上述步骤的输出 - response = Permute（（2,1））（response）＃（samples，query_maxlen，story_maxlen）
这只是将上述部分的故事与LSTM层的问题联系起来？如果我的理解错误，请更正 -
# concatenate the match matrix with the question vector sequence
answer = concatenate([response, question_encoded])
我没有找到任何直观的解释，所以在这里张贴。
非常感谢任何帮助！
感谢。
答案 0 :(得分：0)
首先，match变量不仅识别匹配的单词，而是在输入上给出概率分布。这些可以看作每个输入句子的权重。
使用两个不同的矩阵嵌入输入序列，其结果在代码中为input_encoded_c和input_encoded_m。使用第一次嵌入，我们找到匹配权重。然后将权重应用于第二个嵌入向量，我们找到答案。将权重应用于我们计算它们的相同向量是不合逻辑的。
然后来Permute。要生成答案，
我们将查询添加到response，以获得相同的维度，我们会对响应的维度进行置换。
在论文End-to-End Memory Network中，如果您阅读第2.1节，它将帮助您理解。