forked from jadore801120/attention-is-all-you-need-pytorch
-
Notifications
You must be signed in to change notification settings - Fork 0
/
translate.py
67 lines (58 loc) · 2.56 KB
/
translate.py
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
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
''' Translate input text with trained model. '''
import torch
import argparse
from tqdm import tqdm
from transformer.Translator import Translator
from DataLoader import DataLoader
from preprocess import read_instances_from_file, convert_instance_to_idx_seq
def main():
'''Main Function'''
parser = argparse.ArgumentParser(description='translate.py')
parser.add_argument('-model', required=True,
help='Path to model .pt file')
parser.add_argument('-src', required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-vocab', required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-output', default='pred.txt',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5,
help='Beam size')
parser.add_argument('-batch_size', type=int, default=30,
help='Batch size')
parser.add_argument('-n_best', type=int, default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_true')
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
test_src_word_insts = read_instances_from_file(
opt.src,
preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
test_data = DataLoader(
preprocess_data['dict']['src'],
preprocess_data['dict']['tgt'],
src_insts=test_src_insts,
cuda=opt.cuda,
shuffle=False,
batch_size=opt.batch_size)
translator = Translator(opt)
translator.model.eval()
with open(opt.output, 'wb') as f:
for batch in tqdm(test_data, mininterval=2, desc=' - (Test)', leave=False):
all_hyp, all_scores = translator.translate_batch(batch)
for idx_seqs in all_hyp:
for idx_seq in idx_seqs:
pred_line = ' '.join([test_data.tgt_idx2word[idx] for idx in idx_seq]) + '\n'
pred_line = pred_line.encode('utf-8')
f.write(pred_line)
print('[Info] Finished.')
if __name__ == "__main__":
main()