Это не новый вопрос, ссылки, которые я нашел без какого-либо решения, работающего на меня первый и второй .Я новичок в PyTorch, сталкиваюсь с AttributeError: 'Field' object has no attribute 'vocab'
при создании пакетов текстовых данных в PyTorch
с использованием torchtext
.
В продолжение книги Deep Learning with PyTorch
Я написал такой же пример, как объяснено вbook.
Вот фрагмент:
from torchtext import data
from torchtext import datasets
from torchtext.vocab import GloVe
TEXT = data.Field(lower=True, batch_first=True, fix_length=20)
LABEL = data.Field(sequential=False)
train, test = datasets.IMDB.splits(TEXT, LABEL)
print("train.fields:", train.fields)
print()
print(vars(train[0])) # prints the object
TEXT.build_vocab(train, vectors=GloVe(name="6B", dim=300),
max_size=10000, min_freq=10)
# VOCABULARY
# print(TEXT.vocab.freqs) # freq
# print(TEXT.vocab.vectors) # vectors
# print(TEXT.vocab.stoi) # Index
train_iter, test_iter = data.BucketIterator.splits(
(train, test), batch_size=128, device=-1, shuffle=True, repeat=False) # -1 for cpu, None for gpu
# Not working (FROM BOOK)
# batch = next(iter(train_iter))
# print(batch.text)
# print()
# print(batch.label)
# This also not working (FROM Second solution)
for i in train_iter:
print (i.text)
print (i.label)
Вот трассировка стека:
AttributeError Traceback (most recent call last)
<ipython-input-33-433ec3a2ca3c> in <module>()
7
8
----> 9 for i in train_iter:
10 print (i.text)
11 print (i.label)
/anaconda3/lib/python3.6/site-packages/torchtext/data/iterator.py in __iter__(self)
155 else:
156 minibatch.sort(key=self.sort_key, reverse=True)
--> 157 yield Batch(minibatch, self.dataset, self.device)
158 if not self.repeat:
159 return
/anaconda3/lib/python3.6/site-packages/torchtext/data/batch.py in __init__(self, data, dataset, device)
32 if field is not None:
33 batch = [getattr(x, name) for x in data]
---> 34 setattr(self, name, field.process(batch, device=device))
35
36 @classmethod
/anaconda3/lib/python3.6/site-packages/torchtext/data/field.py in process(self, batch, device)
199 """
200 padded = self.pad(batch)
--> 201 tensor = self.numericalize(padded, device=device)
202 return tensor
203
/anaconda3/lib/python3.6/site-packages/torchtext/data/field.py in numericalize(self, arr, device)
300 arr = [[self.vocab.stoi[x] for x in ex] for ex in arr]
301 else:
--> 302 arr = [self.vocab.stoi[x] for x in arr]
303
304 if self.postprocessing is not None:
/anaconda3/lib/python3.6/site-packages/torchtext/data/field.py in <listcomp>(.0)
300 arr = [[self.vocab.stoi[x] for x in ex] for ex in arr]
301 else:
--> 302 arr = [self.vocab.stoi[x] for x in arr]
303
304 if self.postprocessing is not None:
AttributeError: 'Field' object has no attribute 'vocab'
Если вы не используете BucketIterator, что еще я могу использовать, чтобы получитьаналогичный вывод?