NNDL 作业9 RNN - SRN

1. 实现SRN

（1）使用Numpy

结果：

（2）在1的基础上，增加激活函数tanh

结果：

（3）使用nn.RNNCell实现

结果：

（4）使用nn.RNN实现

结果：

2. 实现“序列到序列”

训练学习过程：

翻译时使用独热编码：

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

3. “编码器-解码器”的简单实现

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')

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, dec_input_all, dec_output_all = make_data(seq_data)


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)


# 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 = 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


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

for epoch in range(5000):
    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) % 1000 == 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'))
print('old ->', translate('old'))
print('high ->', translate('high'))

4.简单总结nn.RNNCell、nn.RNN

都是用来构建循环网络的模型，nn.RNN不能指定层数，n.RNNCell可以

input_size是word_embedding的维度

hidden_size是指memory size,即学习前hidden_size个神经元

5.谈一谈对“序列”、“序列到序列”的理解

序列是指一个有序的元素集合，这些元素可以是字符、词语、句子或其他任何形式的数据。在序列中，每个元素都有特定的位置和顺序。

序列到序列（Sequence-to-Sequence，简称Seq2Seq）是指一类机器学习算法，主要用于将一个序列映射到另一个序列，通常用于自然语言处理任务中，如机器翻译、对话系统和摘要生成等。

6.总结本周理论课和作业，写心得体会

这周学习了简单循环网络，使用numpy实现了一个SRN,在进行序列到序列的源代码分析时，也了解了seq2seq的结构。