NNDL 作业9 RNN - SRN

最新推荐文章于 2024-09-14 16:43:45 发布

又是忙碌的一天

最新推荐文章于 2024-09-14 16:43:45 发布

阅读量924

点赞数 25

文章标签： rnn 人工智能深度学习

本文链接：https://blog.csdn.net/t2786024916/article/details/134754871

版权

4.简单总结nn.RNNCell、nn.RNN

5.谈一谈对“序列”、“序列到序列”的理解

6.总结本周理论课和作业，写心得体会

1. 实现SRN

（1）使用Numpy

import numpy as np
inputs = np.array([[1., 1.],
                   [1., 1.],
                   [2., 2.]]) #初始化输入序列
print('inputs is:',inputs)

state_t=np.zeros(2, ) #初始化储存器
print("state_t is:",state_t)

w1, w2, w3, w4, w5, w6, w7, w8 = 1., 1., 1., 1., 1., 1., 1., 1.
U1, U2, U3, U4 = 1., 1., 1., 1.
print('--------------------------------------')

for input_t in inputs:
    print('inputs is ', input_t)
    print('state_t is ', state_t)
    in_h1 = np.dot([w1, w3], input_t) + np.dot([U2, U4], state_t)
    in_h2 = np.dot([w2, w4], input_t) + np.dot([U1, U3], state_t)
    state_t = in_h1, in_h2
    output_y1 = np.dot([w5, w7], [in_h1, in_h2])
    output_y2 = np.dot([w6, w8], [in_h1, in_h2])
    print('output_y is ', output_y1, output_y2)
    print('---------------')

（2）在1的基础上，增加激活函数tanh

import numpy as np
inputs = np.array([[1., 1.],
                   [1., 1.],
                   [2., 2.]]) #初始化输入序列
print('inputs is:',inputs)

state_t=np.zeros(2, ) #初始化储存器
print("state_t is:",state_t)

w1, w2, w3, w4, w5, w6, w7, w8 = 1., 1., 1., 1., 1., 1., 1., 1.
U1, U2, U3, U4 = 1., 1., 1., 1.
print('--------------------------------------')

for input_t in inputs:
    print('inputs is ', input_t)
    print('state_t is ', state_t)
    in_h1 = np.tanh(np.dot([w1, w3], input_t) + np.dot([U2, U4], state_t))
    in_h2 = np.tanh(np.dot([w2, w4], input_t) + np.dot([U1, U3], state_t))
    state_t = in_h1, in_h2
    output_y1 = np.dot([w5, w7], [in_h1, in_h2])
    output_y2 = np.dot([w6, w8], [in_h1, in_h2])
    print('output_y is ', output_y1, output_y2)
    print('---------------')

（3）使用nn.RNNCell实现

import torch

batch_size=1
seq_len=3 #序列长度
input_size = 2  # 输入序列维度
hidden_size = 2  # 隐藏层维度
output_size = 2  # 输出层维度

#RNNCell
cell=torch.nn.RNNCell(input_size=input_size,hidden_size=hidden_size)
#初始化参数
for name,param in cell.named_parameters():
    if name.startswith("weight"):
        torch.nn.init.ones_(param)
    else:
        torch.nn.init.zeros_(param)
#线性层
liner=torch.nn.Linear(hidden_size,output_size)
liner.weight.data=torch.Tensor([[1,1],[1,1]])
liner.bias.data=torch.Tensor([0.0])
 
seq=torch.Tensor([[[1, 1]],
                    [[1, 1]],
                    [[2, 2]]])
hidden = torch.zeros(batch_size, hidden_size)
output = torch.zeros(batch_size, output_size)

for idx, input in enumerate(seq):
    print('=' * 20, idx, '=' * 20)

    print('Input :', input)
    print('hidden :', hidden)

    hidden = cell(input, hidden)
    output = liner(hidden)
    print('output :', output)

（4）使用nn.RNN实现

import torch
 
batch_size = 1
seq_len = 3
input_size = 2
hidden_size = 2
num_layers = 1
output_size = 2
 
cell = torch.nn.RNN(input_size=input_size, hidden_size=hidden_size, num_layers=num_layers)
for name, param in cell.named_parameters():  # 初始化参数
    if name.startswith("weight"):
        torch.nn.init.ones_(param)
    else:
        torch.nn.init.zeros_(param)
 
# 线性层
liner = torch.nn.Linear(hidden_size, output_size)
liner.weight.data = torch.Tensor([[1, 1], [1, 1]])
liner.bias.data = torch.Tensor([0.0])
 
inputs = torch.Tensor([[[1, 1]],
                       [[1, 1]],
                       [[2, 2]]])
hidden = torch.zeros(num_layers, batch_size, hidden_size)
out, hidden = cell(inputs, hidden)
 
print('Input :', inputs[0])
print('hidden:', 0, 0)
print('Output:', liner(out[0]))
print('--------------------------------------')
print('Input :', inputs[1])
print('hidden:', out[0])
print('Output:', liner(out[1]))
print('--------------------------------------')
print('Input :', inputs[2])
print('hidden:', out[1])
print('Output:', liner(out[2]))

2. 实现“序列到序列”

h0相当于初始隐状态输入，h是正常的输入，1、2、3、4分别是不同的隐状态进入到下一个RNN Cell中去，由上一个的隐状态向量和当前输入确定当前输出和隐状态向量输出，从而将“hello”翻译成了"ohlol".

这是翻译的详细过程展示，其中有一个字典，我们按照这个字典对“hello进行编码”（这里是独热编码）得到的码片序列为：0100 1000 0010 0010 0001从而喂入数据进行运算，喂入之后，通过初始化隐状态向量和当前输入做隐状态向量的更新和当前的一个输出，再进行解码器按照字典对照表解码，从而输出第一个字母，依次类推，从而得到输出序列。

# 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)

这段代码是一个基本的Seq2Seq模型，用于序列到序列的预测任务，通常用于机器翻译等任务中。代码中定义了一个Seq2Seq类，其中包括编码器（encoder）、解码器（decoder）和全连接层（fc）。在forward方法中，输入经过编码器后，得到隐藏状态h_t，然后将隐藏状态作为解码器的初始状态，最终通过全连接层得到输出。

在训练模型时，可以使用交叉熵损失函数（CrossEntropyLoss）和Adam优化器进行优化。

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'))