我想编写与https://docs.chainer.org/en/stable/tutorial/recurrentnet.html示例相同的 RNN/LSTM 迭代器,但添加与 MultiprocessIterator 功能相同的多进程获取能力。url 链接的示例如下:
from __future__ import division
class ParallelSequentialIterator(chainer.dataset.Iterator):
def __init__(self, dataset, batch_size, repeat=True):
self.dataset = dataset
self.batch_size = batch_size
self.epoch = 0
self.is_new_epoch = False
self.repeat = repeat
self.offsets = [i * len(dataset) // batch_size for i in range(batch_size)]
self.iteration = 0
def __next__(self):
length = len(self.dataset)
if not self.repeat and self.iteration * self.batch_size >= length:
raise StopIteration
cur_words = self.get_words()
self.iteration += 1
next_words = self.get_words()
epoch = self.iteration * self.batch_size // length
self.is_new_epoch = self.epoch < epoch
if self.is_new_epoch:
self.epoch = epoch
return list(zip(cur_words, next_words))
@property
def epoch_detail(self):
return self.iteration * self.batch_size / len(self.dataset)
def get_words(self):
return [self.dataset[(offset + self.iteration) % len(self.dataset)]
for offset in self.offsets]
def serialize(self, serializer):
self.iteration = serializer('iteration', self.iteration)
self.epoch = serializer('epoch', self.epoch)
train_iter = ParallelSequentialIterator(train, 20)
val_iter = ParallelSequentialIterator(val, 1, repeat=False)