seq-seq编解码网络

编解码网络

从看图说话简述编解码网络

一个苹果放在我们眼前，苹果对于小孩来说就是输入，那么人类如何认知呢，这个苹果的大小，颜色，以及人是怎么理解这个苹果，到目前为止，人类对苹果这个图像进行编码，提取了对苹果的认知。老师问，你对这个苹果怎么看，这个时候，小孩要做的就是针对刚才对苹果的认知，讲一讲自己对苹果的理解，这个过程就是一个解码的过程。编码和解码通常存在的领域是不通的领域。比如翻译模型，中文翻译英文。看到 我开心，这个词 首先进行编码，达成对住这句话的认知，然后 输出 i am haapy 这个时候就是解码。

框架

总体的框架，我们都知道，是一个 A–>B的过程。A,B 分别是什么呢，那就非常的多，我们可以套用很多的模型，比如RNN,LSTM,GRU, TRANSFORMERS 非常多。
我们先从一个最基本 RNN–>RNN模型来进行理解。

该部分我们构建语料,是一个构建 反义词对。

import torch
import numpy as np
import torch.nn as nn
import torch.utils.data as Data

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# S: Symbol that shows starting of decoding input
# E: Symbol that shows starting of decoding output
# ?: Symbol that will fill in blank sequence if current batch data size is short than n_step

letter = [c for c in 'SE?abcdefghijklmnopqrstuvwxyz']
letter2idx = {n: i for i, n in enumerate(letter)}

seq_data = [['man', 'women'], ['black', 'white'], ['king', 'queen'], ['girl', 'boy'], ['up', 'down'], ['high', 'low']]

# Seq2Seq Parameter
n_step = max([max(len(i), len(j)) for i, j in seq_data]) # max_len(=5)
n_hidden = 128
n_class = len(letter2idx) # classfication problem
batch_size = 3

def make_data(seq_data):
    enc_input_all, dec_input_all, dec_output_all = [], [], []

    for seq in seq_data:
        for i in range(2):
            seq[i] = seq[i] + '?' * (n_step - len(seq[i])) # 'man??', 'women'

        enc_input = [letter2idx[n] for n in (seq[0] + 'E')] # ['m', 'a', 'n', '?', '?', 'E']
        dec_input = [letter2idx[n] for n in ('S' + seq[1])] # ['S', 'w', 'o', 'm', 'e', 'n']
        dec_output = [letter2idx[n] for n in (seq[1] + 'E')] # ['w', 'o', 'm', 'e', 'n', 'E']

        enc_input_all.append(np.eye(n_class)[enc_input])
        dec_input_all.append(np.eye(n_class)[dec_input])
        dec_output_all.append(dec_output) # not one-hot

    # make tensor
    return torch.Tensor(enc_input_all), torch.Tensor(dec_input_all), torch.LongTensor(dec_output_all)

'''
enc_input_all: [6, n_step+1 (because of 'E'), n_class]
dec_input_all: [6, n_step+1 (because of 'S'), n_class]
dec_output_all: [6, n_step+1 (because of 'E')]
'''
class TranslateDataSet(Data.Dataset):
    def __init__(self, enc_input_all, dec_input_all, dec_output_all):
        self.enc_input_all = enc_input_all
        self.dec_input_all = dec_input_all
        self.dec_output_all = dec_output_all
    
    def __len__(self): # return dataset size
        return len(self.enc_input_all)
    
    def __getitem__(self, idx):
        return self.enc_input_all[idx], self.dec_input_all[idx], self.dec_output_all[idx]

loader = Data.DataLoader(TranslateDataSet(enc_input_all, dec_input_all, dec_output_all), batch_size, True)

下面我们来看下，seq2seq的模块，这里 我们encoder和decoder 都使用最简单的 RNN网络。我们来看forward模块，首先通过 encoder模块，得到 h_t,这个h_t就是最后一步的隐藏层的输出。也就是我们如何对输入进行认知的。然后我们通过decoder模块，进行编码。最后一层 self.fc 将解码的输出映射到向量空间。这样就可以计算损失函数了。

# Model
class Seq2Seq(nn.Module):
    def __init__(self):
        super(Seq2Seq, self).__init__()
        self.encoder = nn.RNN(input_size=n_class, hidden_size=n_hidden, dropout=0.5) # encoder
        self.decoder = nn.RNN(input_size=n_class, hidden_size=n_hidden, dropout=0.5) # decoder
        self.fc = nn.Linear(n_hidden, n_class)

    def forward(self, enc_input, enc_hidden, dec_input):
        # enc_input(=input_batch): [batch_size, n_step+1, n_class]
        # dec_inpu(=output_batch): [batch_size, n_step+1, n_class]
        enc_input = enc_input.transpose(0, 1) # enc_input: [n_step+1, batch_size, n_class]
        dec_input = dec_input.transpose(0, 1) # dec_input: [n_step+1, batch_size, n_class]

        # h_t : [num_layers(=1) * num_directions(=1), batch_size, n_hidden]
        _, h_t = self.encoder(enc_input, enc_hidden)
        # outputs : [n_step+1, batch_size, num_directions(=1) * n_hidden(=128)]
        outputs, _ = self.decoder(dec_input, h_t)

        model = self.fc(outputs) # model : [n_step+1, batch_size, n_class]
        return model

下面是模型训练的部分

model = Seq2Seq().to(device)
criterion = nn.CrossEntropyLoss().to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

for epoch in range(500):
  for enc_input_batch, dec_input_batch, dec_output_batch in loader:
      # make hidden shape [num_layers * num_directions, batch_size, n_hidden]
      h_0 = torch.zeros(1, batch_size, n_hidden).to(device)

      (enc_input_batch, dec_intput_batch, dec_output_batch) = (enc_input_batch.to(device), dec_input_batch.to(device), dec_output_batch.to(device))
      # enc_input_batch : [batch_size, n_step+1, n_class]
      # dec_intput_batch : [batch_size, n_step+1, n_class]
      # dec_output_batch : [batch_size, n_step+1], not one-hot
      pred = model(enc_input_batch, h_0, dec_intput_batch)
      # pred : [n_step+1, batch_size, n_class]
      pred = pred.transpose(0, 1) # [batch_size, n_step+1(=6), n_class]
      loss = 0
      for i in range(len(dec_output_batch)):
          # pred[i] : [n_step+1, n_class]
          # dec_output_batch[i] : [n_step+1]
          loss += criterion(pred[i], dec_output_batch[i])
      if (epoch + 1) % 10 == 0:
          print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.6f}'.format(loss))
          
      optimizer.zero_grad()
      loss.backward()
      optimizer.step()

# Test
def translate(word):
    enc_input, dec_input, _ = make_data([[word, '?' * n_step]])
    enc_input, dec_input = enc_input.to(device), dec_input.to(device)
    # make hidden shape [num_layers * num_directions, batch_size, n_hidden]
    hidden = torch.zeros(1, 1, n_hidden).to(device)
    output = model(enc_input, hidden, dec_input)
    # output : [n_step+1, batch_size, n_class]

    predict = output.data.max(2, keepdim=True)[1] # select n_class dimension
    decoded = [letter[i] for i in predict]
    translated = ''.join(decoded[:decoded.index('E')])

    return translated.replace('?', '')

print('test')
print('man ->', translate('man'))
print('mans ->', translate('mans'))
print('king ->', translate('king'))
print('black ->', translate('black'))
print('up ->', translate('up'))