代码实现
num_examples = 50000
source, target = [], []
for i, line in enumerate(text.split(’\n’)):
if i > num_examples:
break
parts = line.split(’\t’)
if len(parts) >= 2:
source.append(parts[0].split(’ ‘))
target.append(parts[1].split(’ '))
source[0:3], target[0:3]
([[‘go’, ‘.’], [‘hi’, ‘.’], [‘hi’, ‘.’]],
[[‘va’, ‘!’], [‘salut’, ‘!’], [‘salut’, ‘.’]])
d2l.set_figsize()
d2l.plt.hist([[len(l) for l in source], [len(l) for l in target]],label=[‘source’, ‘target’])
d2l.plt.legend(loc=‘upper right’);
建立词典
单词组成的列表—单词id组成的列表
def build_vocab(tokens):
tokens = [token for line in tokens for token in line]
return d2l.data.base.Vocab(tokens, min_freq=3, use_special_tokens=True)
src_vocab = build_vocab(source)
len(src_vocab)
3789
Image Name
载入数据集
def pad(line, max_len, padding_token):
if len(line) > max_len:
return line[:max_len]
return line + [padding_token] * (max_len - len(line))
pad(src_vocab[source[0]], 10, src_vocab.pad)
[38, 4, 0, 0, 0, 0, 0, 0, 0, 0]
def build_array(lines, vocab, max_len, is_source):
lines = [vocab[line] for line in lines]
if not is_source:
lines = [[vocab.bos] + line + [vocab.eos] for line in lines]
array = torch.tensor([pad(line, max_len, vocab.pad) for line in lines])
valid_len = (array != vocab.pad).sum(1) #第一个维度
return array, valid_len
def load_data_nmt(batch_size, max_len): # This function is saved in d2l.
src_vocab, tgt_vocab = build_vocab(source), build_vocab(target)
src_array, src_valid_len = build_array(source, src_vocab, max_len, True)
tgt_array, tgt_valid_len = build_array(target, tgt_vocab, max_len, False)
train_data = data.TensorDataset(src_array, src_valid_len, tgt_array, tgt_valid_len)
train_iter = data.DataLoader(train_data, batch_size, shuffle=True)
return src_vocab, tgt_vocab, train_iter
src_vocab, tgt_vocab, train_iter = load_data_nmt(batch_size=2, max_len=8)
for X, X_valid_len, Y, Y_valid_len, in train_iter:
print(‘X =’, X.type(torch.int32), ‘\nValid lengths for X =’, X_valid_len,
‘\nY =’, Y.type(torch.int32), ‘\nValid lengths for Y =’, Y_valid_len)
break
X = tensor([[ 5, 24, 3, 4, 0, 0, 0, 0],
[ 12, 1388, 7, 3, 4, 0, 0, 0]], dtype=torch.int32)
Valid lengths for X = tensor([4, 5])
Y = tensor([[ 1, 23, 46, 3, 3, 4, 2, 0],
[ 1, 15, 137, 27, 4736, 4, 2, 0]], dtype=torch.int32)
Valid lengths for Y = tensor([7, 7])
Encoder-Decoder
encoder：输入到隐藏状态
decoder：隐藏状态到输出
class Encoder(nn.Module):
def init(self, **kwargs):
super(Encoder, self).init(**kwargs)
