今天是最后一节对Attention is all you need pytorch实现的解析,这一节非常的简单,我将会一笔带过。
上一讲连接在此:
Attention is all you need pytorch实现 源码解析01 - 数据预处理、词表的构建 - https://blog.csdn.net/weixin_42744102/article/details/87006081
Attention is all you need pytorch实现 源码解析02 - 模型的训练(1)- 模型的训练代码 - https://blog.csdn.net/weixin_42744102/article/details/87076089
Attention is all you need pytorch实现 源码解析03 - 模型的训练(2)- transformer模型的代码实现以及结构 - https://blog.csdn.net/weixin_42744102/article/details/87088748
先上github源码:https://github.com/Eathoublu/attention-is-all-you-need-pytorch
''' Translate input text with trained model. '''
import torch
import torch.utils.data
import argparse
from tqdm import tqdm
from dataset import collate_fn, TranslationDataset
from transformer.Translator import Translator
from preprocess import read_instances_from_file, convert_instance_to_idx_seq
# 1 - main函数开始,传入参数,其中,-model -src -vocab是必须传入的,这几个参数分别是:模型的路径,data的路径以及vocab(词表)的路径。
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_loader = torch.utils.data.DataLoader(
TranslationDataset(
src_word2idx=preprocess_data['dict']['src'],
tgt_word2idx=preprocess_data['dict']['tgt'],
src_insts=test_src_insts),
num_workers=2,
batch_size=opt.batch_size,
collate_fn=collate_fn)
# 2 - 以上为载入数据,现在实例化一个translator对象
translator = Translator(opt)
# 3 - 打开输出文件,开始进行translate
with open(opt.output, 'w') as f:
for batch in tqdm(test_loader, mininterval=2, desc=' - (Test)', leave=False):
# 4 - 将data中的数据按batch送入translate中,并得到结果,输出到文件中。
all_hyp, all_scores = translator.translate_batch(*batch)
for idx_seqs in all_hyp:
for idx_seq in idx_seqs:
pred_line = ' '.join([test_loader.dataset.tgt_idx2word[idx] for idx in idx_seq])
f.write(pred_line + '\n')
print('[Info] Finished.')
if __name__ == "__main__":
main()