該代碼功能是實現一個閱讀理解的神經網絡，就是給一段材料，提一個問題，然后看是否能給出答案；

首先這個代碼有一個bug，在Python2下應該可以運行，但是在Python3下會報錯，

有人提交了pull request，https://github.com/keras-team/keras/pull/13519/commits/3fc48bcd9a9cc931c43cf4e9e63ae35b61af8910，

但是官方對這個工程已經不咋用心了，所以至今還未合并，

可以把第37行

return [x.strip() for x in re.split(r'(\W+)?', sent) if x.strip()]

中的問號去掉

?

數據集是 Facebook 的 babi 數據集，官方地址為?https://research.fb.com/downloads/babi/

我這人有一個毛病，就是看到一個名稱，總喜歡搞懂這個名稱本身是什么意思，不過搜了一下確實沒有搜到，只是看到一個非官方猜測?https://www.quora.com/What-does-bAbI-stand-for?， babi 這個名稱的含義：

babi，官方的叫法其實是?bAbI， 發音，和意思，都是baby，大致就是嬰兒學習的意思，而把baby，改為 bAbI，就是geek們把 AI 嵌入到了 baby 這個單詞中，因為 AI 這兩個字母刻意大寫，而其余字符刻意小寫

把數據集 https://s3.amazonaws.com/text-datasets/babi_tasks_1-20_v1-2.tar.gz?下載之后 ，解壓縮，打開?qa1_single-supporting-fact_train.txt 就可以大致明白是怎么回事了，

如第一個示例

1 Mary moved to the bathroom.
2 John went to the hallway.
3 Where is Mary? 	bathroom	1

1和2是材料，3是問題和答案

從這個數據集中，自己給每個單詞和標點符號搞了一個編碼：

{'.': 1, '?': 2, 'Daniel': 3, 'John': 4, 'Mary': 5, 'Sandra': 6, 'Where': 7, 'back': 8, 'bathroom': 9, 'bedroom': 10, 'garden': 11, 'hallway': 12, 'is': 13, 'journeyed': 14, 'kitchen': 15, 'moved': 16, 'office': 17, 'the': 18, 'to': 19, 'travelled': 20, 'went': 21}

可以看到總共是21個編碼，再加上補齊的pad，數值為0，那總共就是22個編碼

?

然后編碼每個材料，問題，和答案：

(['Mary', 'moved', 'to', 'the', 'bathroom', '.', 'John', 'went', 'to', 'the', 'hallway', '.'], ['Where', 'is', 'Mary', '?'], 'bathroom')
[ 0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  00  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  00  0  0  0  0  0  0  0  5 16 19 18  9  1  4 21 19 18 12  1]
[ 7 13  5  2]
9

0代碼啥也沒有，pad的字符

輸入的shape

inputs_train shape: (10000, 68)
queries_train shape: (10000, 4)
answers_train shape: (10000,)

神經網絡結構

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to
==================================================================================================
input_1 (InputLayer)            (None, 68)           0
__________________________________________________________________________________________________
input_2 (InputLayer)            (None, 4)            0
__________________________________________________________________________________________________
sequential_1 (Sequential)       multiple             1408        input_1[0][0]
__________________________________________________________________________________________________
sequential_3 (Sequential)       (None, 4, 64)        1408        input_2[0][0]
__________________________________________________________________________________________________
dot_1 (Dot)                     (None, 68, 4)        0           sequential_1[1][0]sequential_3[1][0]
__________________________________________________________________________________________________
activation_1 (Activation)       (None, 68, 4)        0           dot_1[0][0]
__________________________________________________________________________________________________
sequential_2 (Sequential)       multiple             88          input_1[0][0]
__________________________________________________________________________________________________
add_1 (Add)                     (None, 68, 4)        0           activation_1[0][0]sequential_2[1][0]
__________________________________________________________________________________________________
permute_1 (Permute)             (None, 4, 68)        0           add_1[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate)     (None, 4, 132)       0           permute_1[0][0]sequential_3[1][0]
__________________________________________________________________________________________________
lstm_1 (LSTM)                   (None, 32)           21120       concatenate_1[0][0]
__________________________________________________________________________________________________
dropout_4 (Dropout)             (None, 32)           0           lstm_1[0][0]
__________________________________________________________________________________________________
dense_1 (Dense)                 (None, 22)           726         dropout_4[0][0]
__________________________________________________________________________________________________
activation_2 (Activation)       (None, 22)           0           dense_1[0][0]
==================================================================================================
Total params: 24,750
Trainable params: 24,750
Non-trainable params: 0
__________________________________________________________________________________________________

——————————————————————

總目錄

keras的example文件解析

總結

以上是生活随笔為你收集整理的keras 的 example 文件 babi_memnn.py 解析的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。