传统RNN网络及其案例--人名分类

Sout xza2024-05-23 15:44

传统的RNN模型简介

RNN

先上图

这图看起来莫名其妙，想拿着跟CNN对比着学第一眼看上去有点摸不着头脑，其实我们可以把每一个时刻的图展开来，如下

其中，为了简化计算，我们默认每一个隐层参数相同，这样看来RNN的结构就比较简单了，相比较CNN来说，RNN引入了更多的时序信息。

LSTM

在训练 RNN 时，每个时间步的输出都依赖于之前时间步的状态，这种依赖关系形成了一个链式结构。当反向传播时，梯度需要通过多个时间步传播回去，由于链式法则的存在，这个过程中梯度会多次进行乘法运算。如果这些乘法运算的结果小于1，梯度就会随着时间步的增加逐渐衰减，最终可能消失到几乎为零，就会导致梯度消失。RNN 中常用的激活函数如 Sigmoid 或者 tanh 函数，它们的输出范围都在 (0, 1) 或者 (-1, 1) 之间。在反向传播时，如果梯度在这些函数的导数范围内，则可以稳定地传播；但如果超出了这个范围，梯度可能会指数级增长或减少，导致梯度爆炸。而且这些在处理长序列时特别容易发生，因此，出现了RNN的改良版，LSTM。

先看图：

谈到LSTM就无法避免的提及它的三个门和最上面的记忆单元

  1. 记忆单元：记忆单元是LSTM的核心，用于存储信息。它可以看作是一条信息通道，贯穿整个 LSTM单元链条，允许信息直接传递，减少信息丢失。

  2. 遗忘门：遗忘门决定哪些信息需要从记忆单元中删除。它通过sigmoid函数（将当前输入和前一时刻的隐藏状态作为输入）输出一个0到1之间的值。接近0的值表示需要遗忘的信息，接近1的值表示需要保留的信息。

    f t = σ ( W f ⋅ [ h t − 1 , x t ] + b f ) f_t = \sigma(W_f \cdot [h_{t-1}, x_t] + b_f) ft=σ(Wf⋅[ht−1,xt]+bf)

  3. 输入门： 输入门决定哪些新的信息需要添加到记忆单元中。它由两个部分组成：一个sigmoid层决定哪些值将被更新；一个tanh层生成新的候选值向量。

    i t = σ ( W i ⋅ [ h t − 1 , x t ] + b i ) i_t = \sigma(W_i \cdot [h_{t-1}, x_t] + b_i) it=σ(Wi⋅[ht−1,xt]+bi)

    C ~ t = tanh ⁡ ( W C ⋅ [ h t − 1 , x t ] + b C ) \tilde{C}t = \tanh(W_C \cdot [h{t-1}, x_t] + b_C) C~t=tanh(WC⋅[ht−1,xt]+bC)

  4. 输出门：输出门决定记忆单元的哪些部分将被输出作为当前时刻的隐藏状态。它通过sigmoid层和tanh层来实现。

    o t = σ ( W o ⋅ [ h t − 1 , x t ] + b o ) o_t = \sigma(W_o \cdot [h_{t-1}, x_t] + b_o) ot=σ(Wo⋅[ht−1,xt]+bo)

    h t = o t ∗ tanh ⁡ ( C t ) h_t = o_t * \tanh(C_t) ht=ot∗tanh(Ct)

    LSTM的工作流程如下

  5. 遗忘阶段：计算遗忘门的值，以确定当前记忆单元状态中需要遗忘的部分。
    C t = f t ∗ C t − 1 C_t = f_t * C_{t-1} Ct=ft∗Ct−1

  6. 输入阶段：计算输入门的值，并生成新的候选记忆内容。
    C t = C t + i t ∗ C ~ t C_t = C_t + i_t * \tilde{C}_t Ct=Ct+it∗C~t

  7. 更新记忆单元：结合遗忘门和输入门的输出，更新当前记忆单元的状态。

  8. 输出阶段：计算输出门的值，并生成新的隐藏状态。
    完整公式流程：

f t = σ ( W f ⋅ [ h t − 1 , x t ] + b f ) f_t = \sigma(W_f \cdot [h_{t-1}, x_t] + b_f) ft=σ(Wf⋅[ht−1,xt]+bf)

i t = σ ( W i ⋅ [ h t − 1 , x t ] + b i ) i_t = \sigma(W_i \cdot [h_{t-1}, x_t] + b_i) it=σ(Wi⋅[ht−1,xt]+bi)

C ~ t = tanh ⁡ ( W C ⋅ [ h t − 1 , x t ] + b C ) \tilde{C}t = \tanh(W_C \cdot [h{t-1}, x_t] + b_C) C~t=tanh(WC⋅[ht−1,xt]+bC)

C t = f t ∗ C t − 1 + i t ∗ C ~ t C_t = f_t * C_{t-1} + i_t * \tilde{C}_t Ct=ft∗Ct−1+it∗C~t

o t = σ ( W o ⋅ [ h t − 1 , x t ] + b o ) o_t = \sigma(W_o \cdot [h_{t-1}, x_t] + b_o) ot=σ(Wo⋅[ht−1,xt]+bo)

h t = o t ∗ tanh ⁡ ( C t ) h_t = o_t * \tanh(C_t) ht=ot∗tanh(Ct)

GRU

LSTM固然很强，解决了RNN对于长序列模型表现很拉跨的难题，但是仔细查看LSTM的过程就会发现，相对于RNN来说他引入了太多的参数，很容易就过拟合和训练时间大大加长，因此，GRU改进这一问题

  1. 更新门：更新门控制着前一时间步的信息和当前时间步的新信息之间的混合。它通过sigmoid函数决定有多少过去的信息需要保留，以及有多少新的信息需要添加。

    z t = σ ( W z ⋅ [ h t − 1 , x t ] + b z ) z_t = \sigma(W_z \cdot [h_{t-1}, x_t] + b_z) zt=σ(Wz⋅[ht−1,xt]+bz)

  2. 重置门：重置门控制着前一时间步的隐藏状态在当前时间步中被遗忘的比例。它通过sigmoid函数决定有多少前一时间步的信息需要被重置。

    r t = σ ( W r ⋅ [ h t − 1 , x t ] + b r ) r_t = \sigma(W_r \cdot [h_{t-1}, x_t] + b_r) rt=σ(Wr⋅[ht−1,xt]+br)

  3. 候选隐藏状态：候选隐藏状态结合了重置门的结果，决定当前时间步的隐藏状态。

    h ~ t = tanh ⁡ ( W ⋅ [ r t ∗ h t − 1 , x t ] + b ) \tilde{h}t = \tanh(W \cdot [r_t * h{t-1}, x_t] + b) h~t=tanh(W⋅[rt∗ht−1,xt]+b)

  4. 隐藏状态：最终的隐藏状态是更新门和候选隐藏状态的组合。

    h t = ( 1 − z t ) ∗ h t − 1 + z t ∗ h ~ t h_t = (1 - z_t) * h_{t-1} + z_t * \tilde{h}_t ht=(1−zt)∗ht−1+zt∗h~t

工作流程如下：

  1. 重置阶段：计算重置门的值，以确定前一时间步的信息在当前时间步中被重置的比例。

    r t = σ ( W r ⋅ [ h t − 1 , x t ] + b r ) r_t = \sigma(W_r \cdot [h_{t-1}, x_t] + b_r) rt=σ(Wr⋅[ht−1,xt]+br)

  2. 更新阶段：计算更新门的值，以确定有多少信息从前一时间步保留到当前时间步。

    z t = σ ( W z ⋅ [ h t − 1 , x t ] + b z ) z_t = \sigma(W_z \cdot [h_{t-1}, x_t] + b_z) zt=σ(Wz⋅[ht−1,xt]+bz)

  3. 候选隐藏状态阶段：计算候选隐藏状态，该状态结合了重置门的结果和当前输入信息。

    h ~ t = tanh ⁡ ( W ⋅ [ r t ∗ h t − 1 , x t ] + b ) \tilde{h}t = \tanh(W \cdot [r_t * h{t-1}, x_t] + b) h~t=tanh(W⋅[rt∗ht−1,xt]+b)

  4. 隐藏状态更新阶段：结合更新门和候选隐藏状态，更新当前时间步的隐藏状态。

    h t = ( 1 − z t ) ∗ h t − 1 + z t ∗ h ~ t h_t = (1 - z_t) * h_{t-1} + z_t * \tilde{h}_t ht=(1−zt)∗ht−1+zt∗h~t

    完整工作流程

    z t = σ ( W z ⋅ [ h t − 1 , x t ] + b z ) z_t = \sigma(W_z \cdot [h_{t-1}, x_t] + b_z) zt=σ(Wz⋅[ht−1,xt]+bz)

    r t = σ ( W r ⋅ [ h t − 1 , x t ] + b r ) r_t = \sigma(W_r \cdot [h_{t-1}, x_t] + b_r) rt=σ(Wr⋅[ht−1,xt]+br)

    h ~ t = tanh ⁡ ( W ⋅ [ r t ∗ h t − 1 , x t ] + b ) \tilde{h}t = \tanh(W \cdot [r_t * h{t-1}, x_t] + b) h~t=tanh(W⋅[rt∗ht−1,xt]+b)

    h t = ( 1 − z t ) ∗ h t − 1 + z t ∗ h ~ t h_t = (1 - z_t) * h_{t-1} + z_t * \tilde{h}_t ht=(1−zt)∗ht−1+zt∗h~t

使用传统RNN模型来进行人名分类

1. 准备工作

  1. 要用到的数据集点此下载https://download.pytorch.org/tutorial/data.zip，备用地址，点击下载https://www.123pan.com/s/vgXtjv-BFU3v.html

  2. 导入一些包和写一个读取数据的函数（这段代码不是重点，直接抄就行了，只需要记住几个关键的变量）

    category_lines: 人名类别与具体人名对应关系的字典，形式为{人名类别:[人名1，人名2，...]}
all_categories：所有的类别构成的列表
all_letters：所有的字符
    python 复制代码 
    import torch
from io import open
import glob
import os
import unicodedata
import string
import random
import time
import math
import torch.nn as nn
import matplotlib.pyplot as plt

data_path = './data/names/'
all_letters = string.ascii_letters + " .,;'"
def unicodeToAscii(text):
    """
    Converts a Unicode string to an ASCII string.

    Args:
        text (str): The Unicode string to convert.

    Returns:
        str: The ASCII string.
    """
    return ''.join([
        unicodedata.normalize('NFKD', char)
        for char in text
        if not unicodedata.combining(char)
    ]).encode('ascii', 'ignore').decode('ascii')


def readLines(filename):
    lines = open(filename, encoding='utf-8').read().strip().split('\n')
    return [unicodeToAscii(line) for line in lines]

# 构建一个人名类别与具体人名对应关系的字典
category_lines = {}

# 构建所有类别的列表
all_categories = []

# 遍历所有的文件，使用glob.glob中可以利用正则表达式遍历
for filename in glob.glob(data_path + '*.txt'):
    category = os.path.splitext(os.path.basename(filename))[0]
    all_categories.append(category)
    lines = readLines(filename)
    # 将类别与人名对应关系存储到字典中
    category_lines[category] = lines

# 测试
print(category_lines['Italian'][:5])

  3. 字符无法直接被网络识别，因此要将其编码，这里使用最简单的one-hot编码，实现一个函数lineToTensor(line)，将输入的名字编码成张量

    python 复制代码 
    def lineToTensor(line):
    # 首先初始化一个全0的张量，大小为len(line) * 1 * n_letters
    # 代表人名每个字母都用一个(1 * n_letters)的one-hot向量表示
    tensor = torch.zeros(len(line), 1, len(all_letters))
    # 遍历人名的每个字母, 并搜索其在所有字母中的位置，将其对应的位置置为1
    for li, letter in enumerate(line):
        tensor[li][0][all_letters.find(letter)] = 1
        
    return tensor
# 测试
line = "Bai"
tensor = lineToTensor(line)
print("line_tensor:", tensor)
print("line_tensor_size:", tensor.size())

2. 模型搭建

  1. 搭建RNN模型

    python 复制代码 
    class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, num_layers=1):
        super(RNN, self).__init__()
        # input_size: 输入数据的特征维度
        # hidden_size: RNN隐藏层的最后一个维度
        # output_size: RNN网络最后线性层的输出维度
        # num_layers: RNN网络的层数
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.num_layers = num_layers
        self.rnn = nn.RNN(input_size, hidden_size, num_layers)
        self.linear = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=-1)
        
    def forward(self, input1, hidden):
        # input: 人名分类器中的输入张量，形状是1*n_letters
        # hidden: 代表隐藏层张量，形状是self.num_layers*1*hidden_size
        # 输入到RNN中的张量要求是三维张量，所以需要用unsqueeze()函数扩充维度
        input1 = input1.unsqueeze(0)
        rr, hn = self.rnn(input1, hidden)
        # 将RNN中获得的结果通过线性层变换和softmax函数输出
        return self.softmax(self.linear(rr)), hn
    
    def initHidden(self):
        # 初始化隐藏层张量，全0张量，维度是3
        return torch.zeros(self.num_layers, 1, self.hidden_size)

  2. 搭建LSTM模型

    python 复制代码 
    class LSTM(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, num_layers=1):
        super(LSTM, self).__init__()
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers)
        self.linear = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=-1)
        
    def forward(self, input1, hidden, c):
        # 注意：LSTM网络的输入有三个张量，不能忘记细胞状态C
        input1 = input1.unsqueeze(0)
        rr, (hn, cn) = self.lstm(input1, (hidden, c))
        return self.softmax(self.linear(rr)), hn, cn
    
    def initHiddenAndC(self):
        c = hidden = torch.zeros(self.num_layers, 1, self.hidden_size)
        return hidden, c

  3. 搭建GRU模型

    python 复制代码 
    class GRU(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, num_layers=1):
        super(GRU, self).__init__()
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.num_layers = num_layers
        self.gru = nn.GRU(input_size, hidden_size, num_layers)
        self.linear = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=-1)
        
    def forward(self, input1, hidden):
        input1 = input1.unsqueeze(0)
        rr, hn = self.gru(input1, hidden)
        return self.softmax(self.linear(rr)), hn
    
    def initHidden(self):
        return torch.zeros(self.num_layers, 1, self.hidden_size)

3. 模型的实例化与训练

  1. 定义一些参数以及实例化模型

    python 复制代码 
    # 参数
input_size = len(all_letters)
n_hidden = 128
output_size = n_categories
input1 = lineToTensor('B').squeeze(0)
hidden = c = torch.zeros(1, 1, n_hidden)

rnn = RNN(input_size, n_hidden, output_size)
lstm = LSTM(input_size, n_hidden, output_size)
gru = GRU(input_size, n_hidden, output_size)

# 测试
rnn_output, rnn_hidden = rnn(input1, hidden)
lstm_output, lstm_hidden, next_c = lstm(input1, hidden, c)
gru_output, gru_hidden = gru(input1, hidden)

# 打印输出信息
print("rnn_output:", rnn_output)
print("rnn_shape:", rnn_output.shape)
print("********************************")
print("lstm_output:", lstm_output)
print("lstm_shape:", lstm_output.shape)
print("********************************")
print("gru_output:", gru_output)
print("gru_shape:", gru_output.shape)

  2. categoryFromOutput(output)函数功能为从模型输出中获取最大值和最大值的索引

    python 复制代码 
    def categoryFromOutput(output):
    # 从输出中获取最大值和最大值的索引
    top_n, top_i = output.topk(1)
    category_i = top_i[0].item()
    return all_categories[category_i], category_i

  3. randomTrainingExample()函数功能为随机选训练所需的数据

    python 复制代码 
    def randomTrainingExample():
    # 随机选择一个类别
    category = random.choice(all_categories)
    # 从该类别中随机选择一个人名
    line = random.choice(category_lines[category])
    # 将人名转换为张量
    category_tensor = torch.tensor([all_categories.index(category)], dtype=torch.long)
    line_tensor = lineToTensor(line)
    return category, line, category_tensor, line_tensor

  4. 构建训练函数

    python 复制代码 
    # 构建传统RNN训练函数
criterion = nn.NLLLoss()
learning_rate = 0.005
def trainRNN(category_tensor, line_tensor):
    hidden = rnn.initHidden()
    rnn.zero_grad()
    output = None
    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)
    
    # rnn对象由nn.RNN实例化得到，最终输出得到的是三维张量，为了满足category_tensor的维度要求，需要将其转换为二维张量
    loss = criterion(output.squeeze(0), category_tensor)
    loss.backward()
    # 更新参数
    for p in rnn.parameters():
        p.data.add_(-learning_rate, p.grad.data)
    return output, loss.item()

def trainLSTM(category_tensor, line_tensor):
    hidden, c = lstm.initHiddenAndC()
    lstm.zero_grad()
    output = None
    for i in range(line_tensor.size()[0]):
        output, hidden, c = lstm(line_tensor[i], hidden, c)
    
    loss = criterion(output.squeeze(0), category_tensor)
    loss.backward()
    for p in lstm.parameters():
        p.data.add_(-learning_rate, p.grad.data)
    return output, loss.item()

def trainGRU(category_tensor, line_tensor):
    hidden = gru.initHidden()
    gru.zero_grad()
    output = None
    for i in range(line_tensor.size()[0]):
        output, hidden = gru(line_tensor[i], hidden)
    
    loss = criterion(output.squeeze(0), category_tensor)
    loss.backward()
    for p in gru.parameters():
        p.data.add_(-learning_rate, p.grad.data)
    return output, loss.item()

  5. 绘图的辅助函数timeSince(since)用于记录代码运行时间

    python 复制代码 
    # 构建时间计算函数
def timeSince(since):
    now = time.time()
    s = now - since
    m = math.floor(s / 60)
    s -= m * 60
    return "%dm %ds" % (m, s)

  6. 构建完整的训练函数

    python 复制代码 
    # 训练轮次
n_iters = 1000
# 每隔print_every打印一次信息
print_every = 50
# 每个plot_every作为一次绘图采样点
plot_every = 10
def train(train_type_fn):
    # 每个制图间隔损失保存列表
    all_losses = []
    # 获得开始的时间戳
    start = time.time()
    current_loss = 0
    for iter in range(1, n_iters + 1):
        category, line, category_tensor, line_tensor = randomTrainingExample()
        output, loss = train_type_fn(category_tensor, line_tensor)
        current_loss += loss
        if iter % print_every == 0:
            guess, guess_i = categoryFromOutput(output)
            correct = "✓" if guess == category else "✗ (%s)" % category
            print("%d %d%% (%s) %.4f %s / %s %s" % (iter, iter / n_iters * 100, timeSince(start), loss, line, guess, correct))
        if iter % plot_every == 0:
            all_losses.append(current_loss / plot_every)
            current_loss = 0
    return all_losses, int(time.time() - start)

  7. 训练并绘图

    python 复制代码 
    # 训练并制作对比图
all_losses1, period1 = train(trainRNN)
all_losses2, period2 = train(trainLSTM)
all_losses3, period3 = train(trainGRU)

plt.figure(0)
plt.plot(all_losses1, label='RNN')
plt.plot(all_losses2, color='red', label='LSTM')
plt.plot(all_losses3, color='green', label='GRU')
plt.legend(loc='upper left')

plt.figure(1)
x_data = ['RNN', 'LSTM', 'GRU']
y_data = [period1, period2, period3]
plt.bar(range(len(x_data)), y_data, color='green', tick_label=x_data)

  8. 为方便测试，训练轮次只设置了一千，图形跑出来看不是很清楚，以下为训练1e5次的效果

4. 构建评估函数和预测函数

  1. 评估函数

    python 复制代码 
    def evaluateRNN(line_tensor):
    output = None
    hidden = rnn.initHidden()
    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)
    return output.squeeze(0)

def evaluateLSTM(line_tensor):
    output = None
    hidden, c = lstm.initHiddenAndC()
    for i in range(line_tensor.size()[0]):
        output, hidden, c = lstm(line_tensor[i], hidden, c)
    return output.squeeze(0)

def evaluateGRU(line_tensor):
    output = None
    hidden = gru.initHidden()
    for i in range(line_tensor.size()[0]):
        output, hidden = gru(line_tensor[i], hidden)
    return output.squeeze(0)

  2. 预测函数

    python 复制代码 
    def predict(input_line, evaluate, n_predictions=3):
    print("\n> %s" % input_line)
    with torch.no_grad():
        output = evaluate(lineToTensor(input_line))
        topv, topi = output.topk(n_predictions, 1, True)
        predictions = []
        for i in range(n_predictions):
            value = topv[0][i].item()
            category_index = topi[0][i].item()
            print("(%.2f) %s" % (value, all_categories[category_index]))
            predictions.append([value, all_categories[category_index]])
            
# 测试
for evaluate_fn in [evaluateRNN, evaluateLSTM, evaluateGRU]:
    predict('Dovesky', evaluate_fn)
    predict('Jackson', evaluate_fn)
    predict('Satoshi', evaluate_fn)

  3. 完整代码版（方便复制来测试）

    python 复制代码 
    import torch
from io import open
import glob
import os
import unicodedata
import string
import random
import time
import math
import torch.nn as nn
import matplotlib.pyplot as plt
data_path = './data/names/'


all_letters = string.ascii_letters + " .,;'"
def unicodeToAscii(text):
    """
    Converts a Unicode string to an ASCII string.

    Args:
        text (str): The Unicode string to convert.

    Returns:
        str: The ASCII string.
    """
    return ''.join([
        unicodedata.normalize('NFKD', char)
        for char in text
        if not unicodedata.combining(char)
    ]).encode('ascii', 'ignore').decode('ascii')


def readLines(filename):
    lines = open(filename, encoding='utf-8').read().strip().split('\n')
    return [unicodeToAscii(line) for line in lines]

# 构建一个人名类别与具体人名对应关系的字典
category_lines = {}

# 构建所有类别的列表
all_categories = []

# 遍历所有的文件，使用glob.glob中可以利用正则表达式遍历
for filename in glob.glob(data_path + '*.txt'):
    category = os.path.splitext(os.path.basename(filename))[0]
    all_categories.append(category)
    lines = readLines(filename)
    # 将类别与人名对应关系存储到字典中
    category_lines[category] = lines
    
n_categories = len(all_categories)


def lineToTensor(line):
    # 首先初始化一个全0的张量，大小为len(line) * 1 * n_letters
    # 代表人名每个字母都用一个(1 * n_letters)的one-hot向量表示
    tensor = torch.zeros(len(line), 1, len(all_letters))
    # 遍历人名的每个字母, 并搜索其在所有字母中的位置，将其对应的位置置为1
    for li, letter in enumerate(line):
        tensor[li][0][all_letters.find(letter)] = 1
        
    return tensor

class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, num_layers=1):
        super(RNN, self).__init__()
        # input_size: 输入数据的特征维度
        # hidden_size: RNN隐藏层的最后一个维度
        # output_size: RNN网络最后线性层的输出维度
        # num_layers: RNN网络的层数
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.num_layers = num_layers
        self.rnn = nn.RNN(input_size, hidden_size, num_layers)
        self.linear = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=-1)
        
    def forward(self, input1, hidden):
        # input: 人名分类器中的输入张量，形状是1*n_letters
        # hidden: 代表隐藏层张量，形状是self.num_layers*1*hidden_size
        # 输入到RNN中的张量要求是三维张量，所以需要用unsqueeze()函数扩充维度
        input1 = input1.unsqueeze(0)
        rr, hn = self.rnn(input1, hidden)
        # 将RNN中获得的结果通过线性层变换和softmax函数输出
        return self.softmax(self.linear(rr)), hn
    
    def initHidden(self):
        # 初始化隐藏层张量，全0张量，维度是3
        return torch.zeros(self.num_layers, 1, self.hidden_size)
    
    
class LSTM(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, num_layers=1):
        super(LSTM, self).__init__()
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers)
        self.linear = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=-1)
        
    def forward(self, input1, hidden, c):
        # 注意：LSTM网络的输入有三个张量，不能忘记细胞状态C
        input1 = input1.unsqueeze(0)
        rr, (hn, cn) = self.lstm(input1, (hidden, c))
        return self.softmax(self.linear(rr)), hn, cn
    
    def initHiddenAndC(self):
        c = hidden = torch.zeros(self.num_layers, 1, self.hidden_size)
        return hidden, c
    
class GRU(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, num_layers=1):
        super(GRU, self).__init__()
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.num_layers = num_layers
        self.gru = nn.GRU(input_size, hidden_size, num_layers)
        self.linear = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=-1)
        
    def forward(self, input1, hidden):
        input1 = input1.unsqueeze(0)
        rr, hn = self.gru(input1, hidden)
        return self.softmax(self.linear(rr)), hn
    
    def initHidden(self):
        return torch.zeros(self.num_layers, 1, self.hidden_size)
    
# 参数
input_size = len(all_letters)
n_hidden = 128
output_size = n_categories
hidden = c = torch.zeros(1, 1, n_hidden)

rnn = RNN(input_size, n_hidden, output_size)
lstm = LSTM(input_size, n_hidden, output_size)
gru = GRU(input_size, n_hidden, output_size)

def categoryFromOutput(output):
    # 从输出中获取最大值和最大值的索引
    top_n, top_i = output.topk(1)
    category_i = top_i[0].item()
    return all_categories[category_i], category_i

# category, category_i = categoryFromOutput(rnn_output)
# print("category:", category)
# print("category_i:", category_i)

def randomTrainingExample():
    # 随机选择一个类别
    category = random.choice(all_categories)
    # 从该类别中随机选择一个人名
    line = random.choice(category_lines[category])
    # 将人名转换为张量
    category_tensor = torch.tensor([all_categories.index(category)], dtype=torch.long)
    line_tensor = lineToTensor(line)
    return category, line, category_tensor, line_tensor


# 构建传统RNN训练函数
criterion = nn.NLLLoss()
learning_rate = 0.005
def trainRNN(category_tensor, line_tensor):
    hidden = rnn.initHidden()
    rnn.zero_grad()
    output = None
    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)
    
    # rnn对象由nn.RNN实例化得到，最终输出得到的是三维张量，为了满足category_tensor的维度要求，需要将其转换为二维张量
    loss = criterion(output.squeeze(0), category_tensor)
    loss.backward()
    # 更新参数
    for p in rnn.parameters():
        p.data.add_(-learning_rate, p.grad.data)
    return output, loss.item()

def trainLSTM(category_tensor, line_tensor):
    hidden, c = lstm.initHiddenAndC()
    lstm.zero_grad()
    output = None
    for i in range(line_tensor.size()[0]):
        output, hidden, c = lstm(line_tensor[i], hidden, c)
    
    loss = criterion(output.squeeze(0), category_tensor)
    loss.backward()
    for p in lstm.parameters():
        p.data.add_(-learning_rate, p.grad.data)
    return output, loss.item()

def trainGRU(category_tensor, line_tensor):
    hidden = gru.initHidden()
    gru.zero_grad()
    output = None
    for i in range(line_tensor.size()[0]):
        output, hidden = gru(line_tensor[i], hidden)
    
    loss = criterion(output.squeeze(0), category_tensor)
    loss.backward()
    for p in gru.parameters():
        p.data.add_(-learning_rate, p.grad.data)
    return output, loss.item()

# 构建时间计算函数
def timeSince(since):
    now = time.time()
    s = now - since
    m = math.floor(s / 60)
    s -= m * 60
    return "%dm %ds" % (m, s)


# 完整的训练函数
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
n_iters = 1000
print_every = 50
plot_every = 10
def train(train_type_fn):
    # 每个制图间隔损失保存列表
    all_losses = []
    # 获得开始的时间戳
    start = time.time()
    current_loss = 0
    for iter in range(1, n_iters + 1):
        category, line, category_tensor, line_tensor = randomTrainingExample()
        output, loss = train_type_fn(category_tensor, line_tensor)
        current_loss += loss
        if iter % print_every == 0:
            guess, guess_i = categoryFromOutput(output)
            correct = "✓" if guess == category else "✗ (%s)" % category
            print("%d %d%% (%s) %.4f %s / %s %s" % (iter, iter / n_iters * 100, timeSince(start), loss, line, guess, correct))
        if iter % plot_every == 0:
            all_losses.append(current_loss / plot_every)
            current_loss = 0
    return all_losses, int(time.time() - start)


# 训练并制作对比图
all_losses1, period1 = train(trainRNN)
all_losses2, period2 = train(trainLSTM)
all_losses3, period3 = train(trainGRU)

plt.figure(0)
plt.plot(all_losses1, label='RNN')
plt.plot(all_losses2, color='red', label='LSTM')
plt.plot(all_losses3, color='green', label='GRU')
plt.legend(loc='upper left')

plt.figure(1)
x_data = ['RNN', 'LSTM', 'GRU']
y_data = [period1, period2, period3]
plt.bar(range(len(x_data)), y_data, color='green', tick_label=x_data)

# 构建评估函数
def evaluateRNN(line_tensor):
    output = None
    hidden = rnn.initHidden()
    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)
    return output.squeeze(0)

def evaluateLSTM(line_tensor):
    output = None
    hidden, c = lstm.initHiddenAndC()
    for i in range(line_tensor.size()[0]):
        output, hidden, c = lstm(line_tensor[i], hidden, c)
    return output.squeeze(0)

def evaluateGRU(line_tensor):
    output = None
    hidden = gru.initHidden()
    for i in range(line_tensor.size()[0]):
        output, hidden = gru(line_tensor[i], hidden)
    return output.squeeze(0)

# 构建预测函数
def predict(input_line, evaluate, n_predictions=3):
    print("\n> %s" % input_line)
    with torch.no_grad():
        output = evaluate(lineToTensor(input_line))
        topv, topi = output.topk(n_predictions, 1, True)
        predictions = []
        for i in range(n_predictions):
            value = topv[0][i].item()
            category_index = topi[0][i].item()
            print("(%.2f) %s" % (value, all_categories[category_index]))
            predictions.append([value, all_categories[category_index]])
            
# 调用试试
for evaluate_fn in [evaluateRNN, evaluateLSTM, evaluateGRU]:
    predict('Dovesky', evaluate_fn)
    predict('Jackson', evaluate_fn)
    predict('Satoshi', evaluate_fn)
相关推荐
hsling松子1 小时前
使用PaddleHub智能生成，献上浓情国庆福
人工智能·算法·机器学习·语言模型·paddlepaddle
正在走向自律1 小时前
机器学习框架
人工智能·机器学习
好吃番茄2 小时前
U mamba配置问题；‘KeyError: ‘file_ending‘
人工智能·机器学习
CV-King3 小时前
opencv实战项目（三十）：使用傅里叶变换进行图像边缘检测
人工智能·opencv·算法·计算机视觉
禁默3 小时前
2024年计算机视觉与艺术研讨会（CVA 2024）
人工智能·计算机视觉
whaosoft-1434 小时前
大模型~合集3
人工智能
Dream-Y.ocean4 小时前
文心智能体平台AgenBuilder | 搭建智能体：情感顾问叶晴
人工智能·智能体
丶21364 小时前
【CUDA】【PyTorch】安装 PyTorch 与 CUDA 11.7 的详细步骤
人工智能·pytorch·python
春末的南方城市4 小时前
FLUX的ID保持项目也来了! 字节开源PuLID-FLUX-v0.9.0，开启一致性风格写真新纪元！
人工智能·计算机视觉·stable diffusion·aigc·图像生成
zmjia1114 小时前
AI大语言模型进阶应用及模型优化、本地化部署、从0-1搭建、智能体构建技术
人工智能·语言模型·自然语言处理
热门推荐
01【经验分享】Ubuntu22.04安装微信(linux官方版)02安卓系列机型永久去除data分区加密 详细步骤解析032024年高教社杯数学建模国赛C题超详细解题思路分析04CTF网络安全大赛简单的web抓包题目：HEADache05组基轨迹建模 GBTM的介绍与实现（Stata 或 R）06【2024数模国赛赛题思路公开】国赛B题思路丨附可运行代码丨无偿自提07pve(Proxmox VE)安装i225v网卡驱动08苍穹外卖面试总结09【2024高教社杯全国大学生数学建模竞赛】B题 生产过程中的决策问题——解题思路 代码 论文10RAG 实践- Ollama+RagFlow 部署本地知识库