133e5b6a84e126cbcfbc5c11eeb6286185dbec2f,beginner_source/torchtext_translation_tutorial.py,,,#,58

Before Change

import torch

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

BATCH_SIZE = 128

train_iterator, valid_iterator, test_iterator = BucketIterator.splits(
    (train_data, valid_data, test_data),
    batch_size = BATCH_SIZE,
    device = device)

////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
// These iterators can be called just like ``DataLoader``s; below, in
// the ``train`` and ``evaluate`` functions, they are called simply with:

After Change

url_base = "https://raw.githubusercontent.com/multi30k/dataset/master/data/task1/raw/"
train_urls = ("train.de.gz", "train.en.gz")
val_urls = ("val.de.gz", "val.en.gz")
test_urls = ("test_2016_flickr.de.gz", "test_2016_flickr.en.gz")

train_filepaths = [extract_archive(download_from_url(url_base + url))[0] for url in train_urls]
val_filepaths = [extract_archive(download_from_url(url_base + url))[0] for url in val_urls]
test_filepaths = [extract_archive(download_from_url(url_base + url))[0] for url in test_urls]

de_tokenizer = get_tokenizer("spacy", language="de")
en_tokenizer = get_tokenizer("spacy", language="en")

Instances