torch下载IMDB数据集的代码

以下是使用torch下载IMDB数据集的代码：

import torch
from torchtext.datasets import IMDB

# set up fields
TEXT = torchtext.data.Field(tokenize='spacy', lower=True)
LABEL = torchtext.data.LabelField(dtype=torch.float)

# make splits for data
train_data, test_data = IMDB.splits(TEXT, LABEL)

# build the vocabulary
MAX_VOCAB_SIZE = 25_000
TEXT.build_vocab(train_data, 
                 max_size=MAX_VOCAB_SIZE, 
                 vectors='glove.6B.100d', 
                 unk_init=torch.Tensor.normal_)
LABEL.build_vocab(train_data)

# create the iterators
BATCH_SIZE = 64
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
train_iterator, test_iterator = torchtext.data.BucketIterator.splits(
    (train_data, test_data), 
    batch_size=BATCH_SIZE, 
    device=device)

# print information about the data
print(f'Number of training examples: {len(train_data)}')
print(f'Number of testing examples: {len(test_data)}')
print(f'Unique tokens in TEXT vocabulary: {len(TEXT.vocab)}')
print(f'Unique tokens in LABEL vocabulary: {len(LABEL.vocab)}')
print(f'Number of batches in the train iterator: {len(train_iterator)}')
print(f'Number of batches in the test iterator: {len(test_iterator)}')

这段代码使用了torchtext库中的IMDB数据集，并通过构建词汇表和设置迭代器，将数据集准备好用于模型训练。注意，这里使用了预训练的GloVe词向量，需要提前下载并放置到指定路径中。