blob: bc292cf7ef89333d2df7e03656221646039a7252 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
|
import torch
import torch.nn as nn
import torch.optim as optim
from torchtext.legacy.datasets import Multi30k
from torchtext.legacy.data import Field, BucketIterator
import spacy
import numpy as np
import random
import math
import time
SEED = 1234
random.seed(SEED)
np.random.seed(SEED)
torch.manual_seed(SEED)
torch.cuda.manual_seed(SEED)
torch.backends.cudnn.deterministic = True
spacy_de = spacy.load('de_core_news_sm')
spacy_en = spacy.load('en_core_web_sm')
def tokenize_de(text):
"""
Tokenizes German text from a string into a list of strings (tokens) and reverses it
"""
return [tok.text for tok in spacy_de.tokenizer(text)][::-1]
def tokenize_en(text):
"""
Tokenizes English text from a string into a list of strings (tokens)
"""
return [tok.text for tok in spacy_en.tokenizer(text)]
SRC = Field(tokenize = tokenize_de,
init_token = '<sos>',
eos_token = '<eos>',
lower = True)
TRG = Field(tokenize = tokenize_en,
init_token = '<sos>',
eos_token = '<eos>',
lower = True)
train_data, valid_data, test_data = Multi30k.splits(exts = ('.de', '.en'),
fields = (SRC, TRG))
|
