如何为一种热编码实现生成器功能

Question

我实现了一个生成器函数来生成一个热编码向量，但生成器实际上会抛出错误

我使用生成器函数来生成一个热编码向量，因为后者将用作深度学习 lstm 模型的输入。我这样做是为了避免在尝试对非常大的数据集创建一个热编码时出现过度负载和内存故障。但是，我没有收到生成器函数的错误。我需要帮助找出我哪里出错了。

之前的代码：

X = np.zeros((len(sequences), seq_length, vocab_size), dtype=np.bool)
y = np.zeros((len(sequences), vocab_size), dtype=np.bool)
for i, sentence in enumerate(sequences):
    for t, word in enumerate(sentence):
        X[i, t, vocab[word]] = 1
    y[i, vocab[next_words[i]]] = 1

这里，

sequences = sentences generated from data set
seq_length = length of each sentence(this is constant)
vocab_size = number of unique words in dictionary

My program when run on the large data set produces,

sequences = 44073315
seq_length = 30
vocab_size = 124958

因此，当上面的代码直接用于后面的输入时，会给出beloe错误。

Traceback (most recent call last):
  File "1.py", line 206, in <module>
    X = np.zeros((len(sequences), seq_length, vocab_size), dtype=np.bool)
MemoryError
(my_env) [rjagannath1@login ~]$

所以，我尝试创建一个生成器函数（用于测试），如下所示 -

def gen(batch_size, no_of_sequences, seq_length, vocab_size):
    bs = batch_size
    ns = no_of_sequences
    X = np.zeros((batch_size, seq_length, vocab_size), dtype=np.bool)
    y = np.zeros((batch_size, vocab_size), dtype=np.bool)
    while(ns > bs):
        for i, sentence in enumerate(sequences):
            for t, word in enumerate(sentence):
                X[i, t, vocab[word]] = 1
            y[i, vocab[next_words[i]]] = 1
        print(X.shape())
        print(y.shape())
        yield(X, y)
        ns = ns - bs 

for item in gen(1000, 44073315, 30, 124958):
    print(item)

但我收到以下错误 -

File "path_of_file", line 247, in gen
    X[i, t, vocab[word]] = 1

IndexError: index 1000 is out of bounds for axis 0 with size 1000

我在生成器函数中犯了什么错误？

Answer 1

在你的生成器中修改如下：

batch_i = 0
while(ns > bs):
    s = batch_i*batch_size
    e = (batch_i+1)*batch_size
    for i, sentence in enumerate(sequences[s:e]):

基本上，您想要运行超过 batch_size 大小的 windows，因此您正在运行ning 切入 sequences，这看起来是你的整个数据集。

你还必须递增 batch_i，将其放在 yield 之后，所以添加 batch_i+=1

如何为一种热编码实现生成器功能

How to implement generator function for one hot encoding

python

generator

deep-learning

one-hot-encoding