Pytorch学习笔记--Bilibili刘二大人Pytorch教学代码汇总（注释及运行结果）

目录

Part1 03Gradient_Descent1

Part2 03Gradient_Descent2

​​​​​​​​​​​​​​Part3 05LinearRegression

Part4 06Logistic_Regression

Part5 07Multiple_Dimension_Input

Part6  08Dataset and Dataloader

Part7 09Softmax_Classifier（运行结果见另一篇博客）

​​​​​​​Part8 10_Basic_CNN

Part9 12RNN_Basic-RNNCell

Part10 13_RNN_Classifier

​​​​​​​

Part1 03Gradient_Descent1

# 输入训练数据
x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]

# 设置初始参数
w = 1.0  # 初始权重
alpha = 0.005 #初始梯度下降法的学习率

# 定义计算y_hat的函数
def forward(x):
    return x * w

# 定义计算平均损失的函数
def cost(xs, ys):
    sum_cost = 0
    for x, y in zip(xs, ys):  # zip函数的功能是打包为元组列表
        y_pred = forward(x)
        sum_cost += (y_pred - y) ** 2
    return sum_cost / len(xs)

def gradient(xs, ys):
    grad = 0
    for x, y in zip(xs, ys):
        grad += 2 * x * (x * w - y)
    return grad / len(xs)

print('Predict (before training)', 4, forward(4))  # 计算训练前初始参数对应的y_hat值
for epoch in range(1000):
    cost_val = cost(x_data, y_data)   # 计算平均损失值
    grad_val = gradient(x_data, y_data) # 计算梯度值
    w -= alpha * grad_val # 更新权重w
    print('Epoch', epoch, 'w = ', w, 'loss = ', cost_val) # 输出当前迭代次数的权重值和平均损失值

print('Predict (after training)', 4, forward(4)) #计算训练权重w后，对应的y_hat值

Part2 03Gradient_Descent2

# 输入训练数据
x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]

# 设置初始参数
w = 1.0  # 初始权重
alpha = 0.005 #初始梯度下降法的学习率

# 定义计算y_hat的函数
def forward(x):
    return x * w

# 定义计算单个样本损失的函数
def loss(xs, ys):
    y_pred = forward(x) # 计算预测值y_hat
    single_lost = (y_pred - ys) ** 2 # 计算误差
    return single_lost

def gradient(xs, ys):
    grad = 2 * x * (x * w - y)
    return grad

print('Predict (before training)', 4, forward(4))  # 计算训练前初始参数对应的y_hat值
for epoch in range(1000): # 迭代次数
    for x, y in zip(x_data, y_data): # 遍历数据
        grad_val = gradient(x, y)    # 计算当前数据的梯度值
        w -= alpha * grad_val        # 更新权重w
        print("\tgrad: ", x, y, grad_val)
        los = loss(x, y)  # 计算当前数据的损失值
    print('progress: ', epoch, 'w = ', w, 'loss = ', los)

print('Predict (after training)', 4, forward(4)) # 计算训练权重w后，对应的y_hat值

​​​​​​​​​​​​​​Part3 05LinearRegression

# Prepare dataset
import torch
x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[2.0], [4.0], [6.0]])

# Design Model using Class
class LinearModel(torch.nn.Module):
    def __init__(self):      #构造函数
        super(LinearModel, self).__init__()  #调用父类的构造函数
        self.linear = torch.nn.Linear(1, 1)  #in_features   out_featurs 输入纬度和输出维度

    def forward(self, x):   #逻辑运算函数
        y_pred = self.linear(x)
        return y_pred

model = LinearModel()  #创建对象

# Construct Loss and Optimizer

criterion = torch.nn.MSELoss(size_average = False)

optimizer = torch.optim.SGD(model.parameters(), lr = 0.01)

# Training Cycle
for epoch in range(1000):  #循环迭代
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch, loss)

    optimizer.zero_grad()   #梯度置零
    loss.backward()  #计算梯度
    optimizer.step() #更新权重 等价于w.data = w.data - 0.01*w.grad.data

# Output weight and bias
print('w = ', model.linear.weight.item()) #输出权重w,item是转换为标量，只显示数值
print('b = ', model.linear.bias.item())

# Test Model
x_test = torch.Tensor([[4.0]])
y_test = model(x_test)
print('y_pred = ', y_test.data)

Part4 06Logistic_Regression

import torch
import torch.nn.functional as F
import numpy as np
import matplotlib.pyplot as plt

x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[0], [0], [1]])

##
class LogisticRegressionModel(torch.nn.Module):
    def __init__(self): #构造函数
        super(LogisticRegressionModel, self).__init__()
        self.linear = torch.nn.Linear(1, 1) #线性层

    def forward(self, x):
        y_pred = F.sigmoid(self.linear(x)) #激活函数
        return y_pred

model = LogisticRegressionModel()

##
criterion = torch.nn.BCELoss(size_average = False) #计算损失
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01) #优化器

##
for epoch in range(1000):
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch, loss.item())

    optimizer.zero_grad() # 梯度置0
    loss.backward() # 计算梯度，反向传播
    optimizer.step() # 更新参数

##
x = np.linspace(0, 10, 200)
x_t = torch.Tensor(x).view((200, 1))
y_t = model(x_t)
y = y_t.data.numpy()
plt.plot(x, y)
plt.plot([0, 10], [0.5, 0.5], c='r')
plt.xlabel('Hours')
plt.ylabel('Probability of Pass')
plt.grid()
plt.show()

Part5 07Multiple_Dimension_Input

import numpy as np
import torch

xy = np.loadtxt('diabetes.csv.gz', delimiter = ',', dtype = np.float32) #文件名，数据间分隔符，数据类型
x_data = torch.from_numpy(xy[:, :-1])    #读取前N-1列数据
y_data = torch.from_numpy(xy[:, [-1]])   #读取最后一列数据


class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()   #通过初始化父类属性以初始化自身继承了父类的那部分属性
        self.linear1 = torch.nn.Linear(8, 6)
        self.linear2 = torch.nn.Linear(6, 4)
        self.linear3 = torch.nn.Linear(4, 1)
        self.sigmoid = torch.nn.Sigmoid()

    def forward(self, x):
        x = self.sigmoid(self.linear1(x))
        x = self.sigmoid(self.linear2(x))
        x = self.sigmoid(self.linear3(x))
        return x

model = Model()

criterion = torch.nn.BCELoss(size_average = True)
optimizer = torch.optim.SGD(model.parameters(), lr = 0.1)

for epoch in range(1000):
    # Forward
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch, loss.item())

    # Backward
    optimizer.zero_grad()
    loss.backward()

    # Updata
    optimizer.step()

Part6  08Dataset and Dataloader

import numpy as np
import torch
from torch.utils.data import Dataset, DataLoader

class DiabetesDataset(Dataset):
    def __init__(self, filepath):
        xy = np.loadtxt(filepath, delimiter = ',', dtype = np.float32) #文件名，数据间分隔符，数据类型
        self.len = xy.shape[0] #计算样本数
        self.x_data = torch.from_numpy(xy[:, :-1]) #读取前N-1列数据
        self.y_data = torch.from_numpy(xy[:, [-1]]) #读取最后一列数据

    def __getitem__(self, index):
        return self.x_data[index], self.y_data[index] #返回指定索引的数据

    def __len__(self):
        return self.len   # 返回数据的样本数

dataset = DiabetesDataset('diabetes.csv.gz') # 导入糖尿病样例数据
train_loader = DataLoader(dataset = dataset, batch_size = 32, shuffle = True, num_workers = 0) #数据集，批(batch)大小，是否打乱，进程数

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__() # 通过初始化父类属性以初始化自身继承了父类的那部分属性
        self.linear1 = torch.nn.Linear(8, 6)
        self.linear2 = torch.nn.Linear(6, 4)
        self.linear3 = torch.nn.Linear(4, 1)
        self.sigmoid = torch.nn.Sigmoid()

    def forward(self, x):
        x = self.sigmoid(self.linear1(x)) # 激活函数
        x = self.sigmoid(self.linear2(x))
        x = self.sigmoid(self.linear3(x))
        return x

model = Model()

criterion = torch.nn.BCELoss(size_average = True) # 计算损失
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01) # 优化器


for epoch in range(100): #一个epoch表示所有样本训练一次, 一个iteration表示一个batchsize大小的样本训练一次
    for i, data in enumerate(train_loader, 0): #枚举遍历函数(返回索引和对象), 数据集和遍历起始位置
        #1.Prepare data
        inputs, labels = data   #特征数据列，标签数据列
        #2.Forward
        y_pred = model(inputs)
        loss = criterion(y_pred, labels)
        print(epoch, i, loss.item())
        #3.Backward
        optimizer.zero_grad()
        loss.backward()
        #4.Updata
        optimizer.step()

运行时为了节省时间(设定EPOCHS=10)，运行过程中容易出现DataLoader worker (pid(s) 1982) exited unexpectedly的错误，需修改 num_workers的值为0（源码为2）。

Part7 09Softmax_Classifier（运行结果见另一篇博客）

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(), #将shape为(H, W, C)的img转为shape为(C, H, W)的tensor,将每一个数值归一化到[0,1]
    transforms.Normalize((0.1307, ), (0.3081, )) #按通道进行数据标准化
])

train_dataset = datasets.MNIST(root = '../Pycharm/dataset/mnist/', train = True, download = True, transform = transform)

train_loader = DataLoader(train_dataset, shuffle = True, batch_size = batch_size)

test_dataset = datasets.MNIST(root = '../Pycharm/dataset/mnist/', train = False, download = True, transform = transform)

test_loader = DataLoader(test_dataset, shuffle = False, batch_size = batch_size)

class Net(torch.nn.Module):
    def __init__(self):    # 构造函数
        super(Net, self).__init__()
        self.l1 = torch.nn.Linear(784, 512) # 线性层，输入纬度，输出纬度
        self.l2 = torch.nn.Linear(512, 256)
        self.l3 = torch.nn.Linear(256, 128)
        self.l4 = torch.nn.Linear(128, 64)
        self.l5 = torch.nn.Linear(64, 10)


    def forward(self, x):
        x = x.view(-1, 784)  # view函数相当于numpy中的reshape函数，-1表示一个不确定的数，784表示确定的列
        x = F.relu(self.l1(x)) # relu()激活函数
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))
        return self.l5(x)

model = Net()

criterion = torch.nn.CrossEntropyLoss()  # 计算交叉熵损失
optimizer = optim.SGD(model.parameters(), lr = 0.01, momentum = 0.5) #构建优化器，lr为学习率，momentum为冲量因子

def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0): # 遍历函数，0表示从第0个元素开始，返回数据下标和数值
        inputs, target = data #特征，标签
        optimizer.zero_grad() #梯度归零

        # forward + backward + updata
        outputs = model(inputs)
        loss = criterion(outputs, target) #计算损失
        loss.backward() #反向传播梯度值
        optimizer.step() #更新参数

        running_loss += loss.item() #得到元素张量的一个元素值，将张量转换成浮点数
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():  #数据不计算梯度
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim = 1) #predicted为tensor每行最大值的索引
            total += labels.size(0) #总样本
            correct += (predicted == labels).sum().item() #预测准确的样本数
    print('Accuracy on test set: %d %%' % (100 * correct / total)) #准确率

def main():
    for epoch in range(10):
        train(epoch)
        test()

main()

​​​​​​​Part8 10_Basic_CNN

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(), #将shape为(H, W, C)的img转为shape为(C, H, W)的tensor,将每一个数值归一化到[0,1]
    transforms.Normalize((0.1307, ), (0.3081, )) #按通道进行数据标准化
])

train_dataset = datasets.MNIST(root = '../Pycharm/dataset/mnist/', train = True, download = True, transform = transform)

train_loader = DataLoader(train_dataset, shuffle = True, batch_size = batch_size)

test_dataset = datasets.MNIST(root = '../Pycharm/dataset/mnist/', train = False, download = True, transform = transform)

test_loader = DataLoader(test_dataset, shuffle = False, batch_size = batch_size)

class Net(torch.nn.Module):
    def __init__(self):    # 构造函数
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size = 5) #卷积层1
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size = 5) #卷积层2
        self.pooling = torch.nn.MaxPool2d(2) # 2x2最大池化
        self.fc = torch.nn.Linear(320, 10)

    def forward(self, x):
        # Flatten data from(n, 1, 28, 28) to (n, 784)
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x))) # 卷积、池化、激活函数
        x = F.relu(self.pooling(self.conv2(x)))
        x = x.view(batch_size, -1) # reshape, -1表示一个不确定的数
        x = self.fc(x)
        return x

model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") # 调用GPU或CPU
model.to(device)

criterion = torch.nn.CrossEntropyLoss()  # 计算交叉熵损失
optimizer = optim.SGD(model.parameters(), lr = 0.01, momentum = 0.5) #构建优化器，lr为学习率，momentum为冲量因子

def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0): # 遍历函数，0表示从第0个元素开始，返回数据下标和数值
        inputs, target = data #特征，标签
        inputs, target = inputs.to(device), target.to(device)
        optimizer.zero_grad() #梯度归零

        # forward + backward + updata
        outputs = model(inputs)
        loss = criterion(outputs, target) #计算损失
        loss.backward() #反向传播梯度值
        optimizer.step() #更新参数

        running_loss += loss.item() #得到元素张量的一个元素值，将张量转换成浮点数
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():  #数据不计算梯度
        for data in test_loader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim = 1) #predicted为tensor每行最大值的索引
            total += labels.size(0) # 总样本
            correct += (predicted == labels).sum().item() #预测准确的样本数
    print('Accuracy on test set: %d %%' % (100 * correct / total)) #准确率

def main():
    for epoch in range(10):
        train(epoch)
        test()

main()

Part9 12RNN_Basic-RNNCell

import torch

input_size = 4
hidden_size = 4
batch_size = 1

# train 'hello' To 'ohlol'
idx2char = ['e', 'h', 'l', 'o']  # 字典
x_data = [1, 0, 2, 2, 3]  # 输入字符'hello'序号
y_data = [3, 1, 2, 3, 2]  # 输出字符'ohlol'序号

one_hot_lookup = [[1, 0, 0, 0],
                  [0, 1, 0, 0],
                  [0, 0, 1, 0],
                  [0, 0, 0, 1]]
x_one_hot = [one_hot_lookup[x] for x in x_data]  # 将输入字符转换成向量形式，作为RnnCell输入向量

inputs = torch.Tensor(x_one_hot).view(-1, batch_size, input_size) # seq_len = -1，表示不确定
labels = torch.LongTensor(y_data).view(-1, 1) # seq_len = -1， 表示不确定

class Model(torch.nn.Module):
    def __init__(self, input_size, hidden_size, batch_size): # 构造函数
        super(Model, self).__init__()
        self.batch_size = batch_size
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.rnncell = torch.nn.RNNCell(input_size = self.input_size, hidden_size = self.hidden_size) # RnnCell单元

    def forward(self, input, hidden):
        hidden = self.rnncell(input, hidden) # h_t = RNNCell( h_(t-1), x_t )
        return hidden

    def init_hidden(self):  # 初始化RNN输入h_0
        return torch.zeros(self.batch_size, self.hidden_size)

net = Model(input_size, hidden_size, batch_size)

criterion = torch.nn.CrossEntropyLoss() # 计算交叉熵
optimizer = torch.optim.Adam(net.parameters(), lr = 0.1) # 参数优化器

for epoch in range(15):
    loss = 0
    optimizer.zero_grad() # 梯度置0
    hidden = net.init_hidden() # 获得h_0
    print('Predicted string:', end = '')
    for input, label in zip(inputs, labels): # 按序列取值
        hidden = net(input, hidden) # 进行单个序列的RNNCell训练
        loss += criterion(hidden, label) # 所有序列的损失累加
        _, idx = hidden.max(dim = 1) # 求出概率最大的字符
        print(idx2char[idx.item()], end = '') # 输出概率最大的字符

    loss.backward() # 反向传播
    optimizer.step() # 更新参数

    print(', Epoch [%d/15] loss = %.4f' % (epoch + 1, loss.item())) # 输出训练结果

Part10 13_RNN_Classifier

Pycharm 运行（顺序略有修改）

# 导入第三方库
from torch.utils.data import Dataset, DataLoader
from torch.nn.utils.rnn import pack_padded_sequence
import torch
import gzip
import csv
import matplotlib.pyplot as plt
import numpy as np
import time
import math

# 参数设置
HIDDEN_SIZE = 100
BATCH_SIZE = 256
N_LAYER = 2
N_EPOCHS = 100
N_CHARS = 128
USE_GPU = False

# 数据类
class NameDataset(Dataset):
    def __init__(self, is_train_set = True): #构造函数
        filename = 'names_train.csv.gz' if is_train_set else 'names_test.csv.gz' # 数据集的位置根据自己的文件夹设定，
                                                                                 # 此处与刘二老师的源码不同
        with gzip.open(filename, 'rt') as f:
            reader = csv.reader(f)
            rows = list(reader)
        self.names = [row[0] for row in rows] # names
        self.len = len(self.names) # 样本数
        self.countries = [row[1] for row in rows] # countries
        self.country_list = list(sorted(set(self.countries))) # set()去重，删除重复的数据； sorted()排序
        self.country_dict = self.getCountryDict()
        self.country_num = len(self.country_list) # 国家数

    def __getitem__(self, index): # 取数据
        return self.names[index], self.country_dict[self.countries[index]]

    def __len__(self): # 取样本数
        return self.len

    def getCountryDict(self):
        country_dict = dict()
        for idx, country_name in enumerate(self.country_list, 0): # 从0开始遍历
            country_dict[country_name] = idx  # 构造键字对，为国家编码；如：{'china': 1, 'japan': 2}
        return country_dict

    def idx2country(self, index):
        return self.country_list[index] # 根据索引取出相应的国家名

    def getCountriesNum(self):
        return self.country_num # 返回国家数

# 导入数据集
trainset = NameDataset(is_train_set = True) # 训练集
trainloader = DataLoader(trainset, batch_size = BATCH_SIZE, shuffle = True)
testset = NameDataset(is_train_set = False) # 测试集
testloader = DataLoader(testset, batch_size = BATCH_SIZE, shuffle = False)

N_COUNTRY = trainset.getCountriesNum() # 国家数

#
class RNNClassifier(torch.nn.Module):
    def __init__(self, input_size, hidden_size, output_size, n_layers = 1, bidirectional = True): # bidirectional：单双向循环
        super(RNNClassifier, self).__init__() # 构造函数
        self.hidden_size = hidden_size # 网络输出维度
        self.n_layers = n_layers # 层
        self.n_directions = 2 if bidirectional else 1 # 双向循环，输出的hidden是正向和反向hidden的拼接，所以要 *2

        self.embedding = torch.nn.Embedding(input_size, hidden_size) #嵌入层
        self.gru = torch.nn.GRU(hidden_size, hidden_size, n_layers, bidirectional = bidirectional) # GRU循环神经网络
        self.fc = torch.nn.Linear(hidden_size * self.n_directions, output_size) # 全连接层

    def _init_hidden(self, batch_size): #初始化h_0
        hidden = torch.zeros(self.n_layers * self.n_directions, batch_size, self.hidden_size) # 双向： *2
        return create_tensor(hidden)

    def forward(self, input, seq_lengths):
        # input shape : B x S -> S x B
        input = input.t() # 转置
        batch_size = input.size(1) # 计算batch_size

        hidden = self._init_hidden(batch_size) # 获得h_0
        embedding = self.embedding(input)

        # pack them up
        gru_input = pack_padded_sequence(embedding, seq_lengths) # 打包
        output, hidden = self.gru(gru_input, hidden)
        if self.n_directions == 2: #双向循环
            hidden_cat = torch.cat([hidden[-1], hidden[-2]], dim = 1) # 拼接hidden
        else:
            hidden_cat = hidden[-1]
        fc_output = self.fc(hidden_cat) # 全连接层
        return fc_output

def name2list(name):
    arr = [ord(c) for c in name] # 函数ord()返回每一个字母的ascii值
    return arr, len(arr) # 返回元组

def make_tensors(names, countries):
    sequences_and_lengths = [name2list(name) for name in names] # 元组
    name_sequences = [sl[0] for sl in sequences_and_lengths] # 取名字，实为一组ascii码
    seq_lengths = torch.LongTensor([sl[1] for sl in sequences_and_lengths]) # LongTensor型，取长度
    countries = countries.long()

    # make tensor of name, BatchSize x SeqLen
    seq_tensor = torch.zeros(len(name_sequences), seq_lengths.max()).long() # 初始化一个全零的tensor，行：名字数，列：最长的ascii名字
    for idx, (seq, seq_len) in enumerate(zip(name_sequences, seq_lengths), 0): # 遍历
        seq_tensor[idx, :seq_len] = torch.LongTensor(seq)  # 将ascii码 依次输入到全零的tensor中（对应位置覆盖相应的ascii值，替代相应长度）

    # sort by length to use pack_padded_sequence
    seq_lengths, perm_idx = seq_lengths.sort(dim = 0, descending = True) # 排序，依据序列长度降序
    seq_tensor = seq_tensor[perm_idx]
    countries = countries[perm_idx]

    return create_tensor(seq_tensor), create_tensor(seq_lengths), create_tensor(countries)

def create_tensor(tensor):  # 是否使用GPU
    if USE_GPU:
        device = torch.device("cuda:0")
        tensor = tensor.to(device)
    return tensor

def time_since(since): # 计算程序运行的时间
    s = time.time() - since
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m, s)

def trainModel(epoch):
    total_loss = 0
    for i, (names, countries) in enumerate(trainloader, 1):
        inputs, seq_lengths, target = make_tensors(names, countries) # 生成符合尺寸大小的Tensor数据
        output = classifier(inputs, seq_lengths) # 输入至网络训练
        loss = criterion(output, target) # 计算损失
        optimizer.zero_grad() # 梯度置0
        loss.backward() # 反向传播
        optimizer.step() # 优化参数

        total_loss += loss.item()
        if i % 10 == 0:
            print(f'[{time_since(start)}] Epoch {epoch}', end = '')
            print(f'[{i * len(inputs)}/{len(trainset)}]', end = '')
            print(f'loss={total_loss / (i * len(inputs))}')
    return total_loss

def testModel():
    correct = 0
    total = len(testset)
    print("evaluating trained model ...")
    with torch.no_grad():
        for i, (names, countries) in enumerate(testloader, 1):
            inputs, seq_lengths, target = make_tensors(names, countries)
            output = classifier(inputs, seq_lengths)
            pred = output.max(dim = 1, keepdim = True)[1]
            correct += pred.eq(target.view_as(pred)).sum().item()

        percent = '%.2f' % (100 * correct / total)
        print(f'Test set: Accuracy {correct}/{total} {percent}%')

    return correct/total


def main():
    if USE_GPU:
        device = torch.device("cuda:0")
        classifier.to(device)

    print("Training for %d epochs..." % N_EPOCHS)
    acc_list = []
    for epoch in range(1, N_EPOCHS + 1):
        # Train cycle
        trainModel(epoch)
        acc = testModel()
        acc_list.append(acc)

    epoch = np.arange(1, len(acc_list) + 1, 1)
    acc_list = np.array(acc_list)
    plt.plot(epoch, acc_list)
    plt.xlabel('Epoch')
    plt.ylabel('Accuracy')
    plt.grid()
    plt.show()

classifier = RNNClassifier(N_CHARS, HIDDEN_SIZE, N_COUNTRY, N_LAYER) # 生成模型对象
criterion = torch.nn.CrossEntropyLoss() # 交叉熵损失计算器
optimizer = torch.optim.Adam(classifier.parameters(), lr=0.001) # 优化器
start = time.time() # 开始时间

main()

Anaconda(Jupyter Notebook 运行）-刘二老师源码

# 导入第三方库
from torch.utils.data import Dataset, DataLoader
from torch.nn.utils.rnn import pack_padded_sequence
import torch
import gzip
import csv
import matplotlib.pyplot as plt
import numpy as np
import time
import math

# 参数设置
HIDDEN_SIZE = 100
BATCH_SIZE = 256
N_LAYER = 2
N_EPOCHS = 10
N_CHARS = 128
USE_GPU = False

# 数据类
class NameDataset(Dataset):
    def __init__(self, is_train_set = True):
        filename = 'names_train.csv.gz' if is_train_set else 'names_test.csv.gz' # 按所在文件夹修改
        with gzip.open(filename, 'rt') as f:
            reader = csv.reader(f)
            rows = list(reader)
        self.names = [row[0] for row in rows]
        self.len = len(self.names)
        self.countries = [row[1] for row in rows]
        self.country_list = list(sorted(set(self.countries)))
        self.country_dict = self.getCountryDict()
        self.country_num = len(self.country_list)

    def __getitem__(self, index):
        return self.names[index], self.country_dict[self.countries[index]]

    def __len__(self):
        return self.len

    def getCountryDict(self):
        country_dict = dict()
        for idx, country_name in enumerate(self.country_list, 0):
            country_dict[country_name] = idx
        return country_dict

    def idx2country(self, index):
        return self.country_list[index]

    def getCountriesNum(self):
        return self.country_num

# 导入数据集
trainset = NameDataset(is_train_set = True)
trainloader = DataLoader(trainset, batch_size = BATCH_SIZE, shuffle = True)
testset = NameDataset(is_train_set = False)
testloader = DataLoader(testset, batch_size = BATCH_SIZE, shuffle = False)

N_COUNTRY = trainset.getCountriesNum()

class RNNClassifier(torch.nn.Module):
    def __init__(self, input_size, hidden_size, output_size, n_layers = 1, bidirectional = True):
        super(RNNClassifier, self).__init__()
        self.hidden_size = hidden_size
        self.n_layers = n_layers
        self.n_directions = 2 if bidirectional else 1

        self.embedding = torch.nn.Embedding(input_size, hidden_size)
        self.gru = torch.nn.GRU(hidden_size, hidden_size, n_layers, bidirectional = bidirectional)
        self.fc = torch.nn.Linear(hidden_size * self.n_directions, output_size)

    def _init_hidden(self, batch_size):
        hidden = torch.zeros(self.n_layers * self.n_directions, batch_size, self.hidden_size)
        return create_tensor(hidden)

    def forward(self, input, seq_lengths):
        # input shape : B x S -> S x B
        input = input.t()
        batch_size = input.size(1)

        hidden = self._init_hidden(batch_size)
        embedding = self.embedding(input)

        # pack them up
        gru_input = pack_padded_sequence(embedding, seq_lengths)
        output, hidden = self.gru(gru_input, hidden)
        if self.n_directions == 2:
            hidden_cat = torch.cat([hidden[-1], hidden[-2]], dim = 1)
        else:
            hidden_cat = hidden[-1]
        fc_output = self.fc(hidden_cat)
        return fc_output

def name2list(name):
    arr = [ord(c) for c in name]
    return arr, len(arr)

def make_tensors(names, countries):
    sequences_and_lengths = [name2list(name) for name in names]
    name_sequences = [sl[0] for sl in sequences_and_lengths]
    seq_lengths = torch.LongTensor([sl[1] for sl in sequences_and_lengths])
    countries = countries.long()

    # make tensor of name, BatchSize x SeqLen
    seq_tensor = torch.zeros(len(name_sequences), seq_lengths.max()).long()
    for idx, (seq, seq_len) in enumerate(zip(name_sequences, seq_lengths), 0):
        seq_tensor[idx, :seq_len] = torch.LongTensor(seq)

    # sort by length to use pack_padded_sequence
    seq_lengths, perm_idx = seq_lengths.sort(dim = 0, descending = True)
    seq_tensor = seq_tensor[perm_idx]
    countries = countries[perm_idx]

    return create_tensor(seq_tensor), create_tensor(seq_lengths), create_tensor(countries)

def create_tensor(tensor):
    if USE_GPU:
        device = torch.device("cuda:0")
        tensor = tensor.to(device)
    return tensor

def time_since(since):
    s = time.time() - since
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m, s)

def trainModel():
    total_loss = 0
    for i, (names, countries) in enumerate(trainloader, 1):
        inputs, seq_lengths, target = make_tensors(names, countries)
        output = classifier(inputs, seq_lengths)
        loss = criterion(output, target)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_loss += loss.item()
        if i % 10 == 0:
            print(f'[{time_since(start)}] Epoch {epoch}', end = '')
            print(f'[{i * len(inputs)}/{len(trainset)}]', end = '')
            print(f'loss={total_loss / (i * len(inputs))}')
    return total_loss

def testModel():
    correct = 0
    total = len(testset)
    print("evaluating trained model ...")
    with torch.no_grad():
        for i, (names, countries) in enumerate(testloader, 1):
            inputs, seq_lengths, target = make_tensors(names, countries)
            output = classifier(inputs, seq_lengths)
            pred = output.max(dim = 1, keepdim = True)[1]
            correct += pred.eq(target.view_as(pred)).sum().item()

        percent = '%.2f' % (100 * correct / total)
        print(f'Test set: Accuracy {correct}/{total} {percent}%')

    return correct/total

if __name__ == '__main__':
    classifier = RNNClassifier(N_CHARS, HIDDEN_SIZE, N_COUNTRY, N_LAYER)
    if USE_GPU:
        device = torch.device("cuda:0")
        classifier.to(device)

    criterion = torch.nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(classifier.parameters(), lr=0.001)
    start = time.time()

    print("Training for %d epochs..." % N_EPOCHS)
    acc_list = []
    for epoch in range(1, N_EPOCHS + 1):
        # Train cycle
        trainModel()
        acc = testModel()
        acc_list.append(acc)

    epoch = np.arange(1, len(acc_list) + 1, 1)
    acc_list = np.array(acc_list)
    plt.plot(epoch, acc_list)
    plt.xlabel('Epoch')
    plt.ylabel('Accuracy')
    plt.grid()
    plt.show()