import numpy as np
import matplotlib.pyplot as plt
x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]
def forward(x):
    return x * w
def loss(x, y):
    y_pred = forward(x)
    return (y_pred - y) * (y_pred - y)
w_list = []
mse_list = []
for w in np.arange(0.0, 4.1, 0.1):
    print('w=', w)
    l_sum = 0
    for x_val, y_val in zip(x_data, y_data):
        y_pred_val = forward(x_val)
        loss_val = loss(x_val, y_val)
        l_sum += loss_val
        print('\t', x_val, y_val, y_pred_val, loss_val)
    print('MSE=', l_sum / 3)
    w_list.append(w)
    mse_list.append(l_sum / 3)
plt.plot(w_list, mse_list)
plt.ylabel('Loss')
plt.xlabel('w')
plt.show()

# 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

# 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
反向传播
import torch
x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]
w = torch.Tensor([1.0])
w.requires_grad = True  # 需要计算梯度
def forward(x):
    return x * w  # tensor
def loss(x, y):
    y_pred = forward(x)
    return (y_pred - y) ** 2
print('predict (before training)', 4, forward(4).item())
for epoch in range(100):
    for x, y in zip(x_data, y_data):
        l = loss(x, y) # 前向，计算loss
        l.backward() # 做完后计算图会释放
        print('\tgrad:', x, y, w.grad.item())  # item取值，要是张量计算图一直累积
        w.data -= 0.01 * w.grad.data  # 不取data会是TENSOR有计算图
        w.grad.data.zero_()  # 计算出来的梯度不清零会累加
    print("progress:", epoch, l.item())
print('predict (after training)', 4, forward(4).item())

# 1、算预测值
# 2、算loss
# 3、梯度设为0，并反向传播
# 3、梯度更新
import torch
x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[2.0], [4.0], [6.0]])
# 构造线性模型,后面都是使用这样的模板
# 至少实现两个函数，__init__构造函数和forward()前馈函数
# backward()会根据我们的计算图自动构建
# 可以继承Functions来构建自己的计算块
class LinerModel(torch.nn.Module):
    def __init__(self):
        # 调用父类的构造
        super(LinerModel, self).__init__()
        # 构造Linear这个对象，对输入数据做线性变换
        # class torch.nn.Linear(in_features, out_features, bias=True)
        # in_features - 每个输入样本的大小
        # out_features - 每个输出样本的大小
        # bias - 若设置为False，这层不会学习偏置。默认值：True
        self.linear = torch.nn.Linear(1, 1)
    def forward(self, x):
        y_pred = self.linear(x)
        return y_pred
model = LinerModel() # 实例化，可调用
# 定义MSE(均方差)损失函数，size_average=False不求均值
criterion = torch.nn.MSELoss(size_average=False)
# optim优化模块的SGD，第一个参数就是传递权重，model.parameters()model的所有权重
# 优化器对象
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
for epoch in range(100):
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    # loss为一个对象，loss不会产生计算图，但会自动调用__str__()所以不会出错
    print(epoch, loss)
    # 梯度归零
    optimizer.zero_grad()
    # 反向传播
    loss.backward()
    # 根据梯度和预先设置的学习率进行更新（权重更新）
    optimizer.step()
# 打印权重和偏置值,weight是一个值但是一个矩阵
print('w=', model.linear.weight.item())
print('b=', model.linear.bias.item())
# 测试
x_test = torch.Tensor([4.0])
y_test = model(x_test)
print('y_pred=', y_test.data)

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()
处理多维特征的输入
import numpy as np
import torch
xy = np.loadtxt('diabetes.csv.gz', delimiter=',', dtype=np.float32)
x_data = torch.from_numpy(xy[:, :-1])
# [-1]加中括号拿出来是矩阵，不加是向量
y_data = torch.from_numpy(xy[:, [-1]])
class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear1 = torch.nn.Linear(8, 6)
        self.linear2 = torch.nn.Linear(6, 4)
        self.linear3 = torch.nn.Linear(4, 1)
        # 这是nn下的Sigmoid是一个模块没有参数，在function调用的Sigmoid是函数
        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)  # 损失函数
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)  # 优化函数，随机梯度递减
for epoch in range(100):
    # 前馈
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch, loss.item())
    # 反馈
    optimizer.zero_grad()
    loss.backward()
    # 更新
    optimizer.step()
加载数据集
import numpy as np
import torch
from torch.utils.data import Dataset  # Dataset是一个抽象类，只能被继承，不能实例化
from torch.utils.data import DataLoader  # 可以直接实例化
'''
四步：准备数据集-设计模型-构建损失函数和优化器-周期训练
'''
class DiabetesDataset(Dataset):
    def __init__(self, filepath):
        xy = np.loadtxt(filepath, delimiter=',', dtype=np.float32)
        self.len = xy.shape[0]
        self.x_data = torch.from_numpy(xy[:, :-1])
        self.y_data = torch.from_numpy(xy[:, [-1]])
    def __getitem__(self, index):  # 实例化对象后，该类能支持下标操作，通过index拿出数据
        return self.x_data[index], self.y_data[index]
    def __len__(self):
        return self.len
dataset = DiabetesDataset('diabetes.csv.gz')
# dataset数据集，batch_size小批量的容量，shuffle是否要打乱，num_workers要几个并行进程来读
# DataLoader的实例化对象不能直接使用，因为windows和linux的多线程运行不一样，所以一般要放在函数里运行
train_loader = DataLoader(dataset=dataset, batch_size=32, shuffle=True, num_workers=2)
class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear1 = torch.nn.Linear(8, 6)
        self.linear2 = torch.nn.Linear(6, 4)
        self.linear3 = torch.nn.Linear(4, 1)
        # 这是nn下的Sigmoid是一个模块没有参数，在function调用的Sigmoid是函数
        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)  # 损失函数
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)  # 优化函数，随机梯度递减
# 变成嵌套循环，实现Mini-Batch
for epoch in range(100):
    # 从数据集0开始迭代
    # 可以简写为for i, (inputs, labels) in enumerate(train_loader, 0):
    for i, data in enumerate(train_loader, 0):
        # 准备数据
        inputs, labels = data
        # 前馈
        y_pred = model(inputs)
        loss = criterion(y_pred, labels)
        print(epoch, i, loss.item())
        # 反馈
        optimizer.zero_grad()
        loss.backward()
        # 更新
        optimizer.step()
多分类问题
import torch
from torchvision import transforms  # 对图像进行处理的工具
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F  # 使用激活函数relu()的包
import torch.optim as optim  # 优化器的包
batch_size = 64
# 对图像进行预处理，将图像转换为
transform = transforms.Compose([
    # 将原始图像PIL变为张量tensor(H*W*C),再将[0,255]区间转换为[0.1,1.0]
    transforms.ToTensor(),
    # 使用均值和标准差对张量图像进行归一化
    transforms.Normalize((0.1307,), (0.3081,))
])
train_dataset = datasets.MNIST(root='dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='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):
        super(Net, self).__init__()
        self.l1 = torch.nn.Linear(784, 512)
        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):
        # 改变形状，相当于numpy的reshape
        # view中一个参数定为-1，代表动态调整这个维度上的元素个数，以保证元素的总数不变。
        x = x.view(-1, 784)
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))
        return self.l5(x)
model = Net()
# 交叉熵损失函数
criterion = torch.nn.CrossEntropyLoss()
# model.parameters()直接使用的模型的所有参数
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)  # momentum动量
def train(epoch):
    running_loss = 0.0
    # 返回了数据下标和数据
    for batch_idx, data in enumerate(train_loader, 0):
        # 送入两个张量，一个张量是64个图像的特征，一个张量图片对应的数字
        inputs, target = data
        # 梯度归零
        optimizer.zero_grad()
        # forward+backward+update
        outputs = model(inputs)
        # 计算损失，用的交叉熵损失函数
        loss = criterion(outputs, target)
        # 反馈
        loss.backward()
        # 随机梯度下降更新
        optimizer.step()
        # 每300次输出一次
        running_loss += loss.item()
        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
    # 不会计算梯度
    with torch.no_grad():
        for data in test_loader:  # 拿数据
            images, labels = data
            outputs = model(images)  # 预测
            # outputs.data是一个矩阵，每一行10个量，最大值的下标就是预测值
            _, predicted = torch.max(outputs.data, dim=1)  # 沿着第一维度，找最大值的下标，返回最大值和下标
            total += labels.size(0)  # labels.size(0)=64 每个都是64个元素，就可以计算总的元素
            # (predicted == labels).sum()这个是张量，而加了item()变为一个数字，即相等的数量
            correct += (predicted == labels).sum().item()
    print('Accuracy on test set:%d %%' % (100 * correct / total))  # 正确的数量除以总数
if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()

import torch
# 输入的通道就是上图的n,输出的通道就是上图的m
in_channels, out_channels = 5, 10
width, height = 100, 100  # 图像的大小
kernel_size = 3  # 卷积盒的大小
batch_size = 1  # 批量大小
# 随机生成了一个小批量=1的5*100*100的张量
input = torch.randn(batch_size, in_channels, width, height)
# Conv2d对由多个输入平面组成的输入信号进行二维卷积
conv_layer = torch.nn.Conv2d(in_channels, out_channels, kernel_size=kernel_size)
output = conv_layer(input)
# print(input)
print(input.shape)
print(output.shape)
print(conv_layer.weight.shape)

torch.Size([1, 5, 100, 100])
torch.Size([1, 10, 98, 98])
torch.Size([10, 5, 3, 3])
padding
import torch
input = [3, 4, 6, 5, 7,
         2, 4, 6, 8, 2,
         1, 6, 7, 8, 4,
         9, 7, 4, 6, 2,
         3, 7, 5, 4, 1]
input = torch.Tensor(input).view(1, 1, 5, 5)
# bias=False不加偏置量
conv_layer = torch.nn.Conv2d(1, 1, kernel_size=3, padding=1, bias=False)
kernel = torch.Tensor([1, 2, 3, 4, 5, 6, 7, 8, 9]).view(1, 1, 3, 3)
# 把kernel赋值给卷积层权重，做初始化
conv_layer.weight.data = kernel.data
output = conv_layer(input)
print(output)

tensor([[[[ 91., 168., 224., 215., 127.],
          [114., 211., 295., 262., 149.],
          [192., 259., 282., 214., 122.],
          [194., 251., 253., 169.,  86.],
          [ 96., 112., 110.,  68.,  31.]]]], grad_fn=<ThnnConv2DBackward>)
Layer-stride步长
import torch
input = [3, 4, 6, 5, 7,
         2, 4, 6, 8, 2,
         1, 6, 7, 8, 4,
         9, 7, 4, 6, 2,
         3, 7, 5, 4, 1]
input = torch.Tensor(input).view(1, 1, 5, 5)
# bias=False不加偏置量
conv_layer = torch.nn.Conv2d(1, 1, kernel_size=3, stride=2, bias=False)
kernel = torch.Tensor([1, 2, 3, 4, 5, 6, 7, 8, 9]).view(1, 1, 3, 3)
# 把kernel赋值给卷积层权重，做初始化
conv_layer.weight.data = kernel.data
output = conv_layer(input)
print(output)

tensor([[[[211., 262.],
          [251., 169.]]]], grad_fn=<ThnnConv2DBackward>)
Max Pooling Layer最大池化层
最大池化层是没有权重的
import torch
input = [3, 9, 6, 5,
         2, 4, 6, 8,
         1, 6, 2, 1,
         3, 7, 4, 6]
input = torch.Tensor(input).view(1, 1, 4, 4)
maxpooling_layer = torch.nn.MaxPool2d(kernel_size=2)
output = maxpooling_layer(input)
print(output)

tensor([[[[9., 8.],
          [7., 6.]]]])
import torch
from torchvision import transforms  # 对图像进行处理的工具
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F  # 使用激活函数relu()的包
import torch.optim as optim  # 优化器的包
batch_size = 64
# 对图像进行预处理，将图像转换为
transform = transforms.Compose([
    # 将原始图像PIL变为张量tensor(H*W*C),再将[0,255]区间转换为[0.1,1.0]
    transforms.ToTensor(),
    # 使用均值和标准差对张量图像进行归一化
    transforms.Normalize((0.1307,), (0.3081,))
])
train_dataset = datasets.MNIST(root='dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='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):
        super(Net, self).__init__()
        # 定义两个卷积层
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)
        # 定义一个池化层
        self.pooling = torch.nn.MaxPool2d(2)
        # 定义一个全连接的线性层
        self.fc = torch.nn.Linear(320, 10)
    def forward(self, x):
        # Flatten data from (n, 1, 28, 28) to (n, 784)
        # x.size(0)就是取的n
        batch_size = x.size(0)
        # 用relu做非线性激活
        # 先做卷积再做池化再做relu
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        # 做view把数据变为做全连接网络所需要的输入
        x = x.view(batch_size, -1)
        return self.fc(x)
        # 因为最后一层要做交叉熵损失，所以最后一层不做激活
model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
# 交叉熵损失函数
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)  # momentum动量
def train(epoch):
    running_loss = 0.0
    # 返回了数据下标和数据
    for batch_idx, data in enumerate(train_loader, 0):
        # 送入两个张量，一个张量是64个图像的特征，一个张量图片对应的数字
        inputs, target = data
        # 把输入输出迁入GPU
        inputs, target = inputs.to(device), target.to(device)
        # 梯度归零
        optimizer.zero_grad()
        # forward+backward+update
        outputs = model(inputs)
        # 计算损失，用的交叉熵损失函数
        loss = criterion(outputs, target)
        # 反馈
        loss.backward()
        # 随机梯度下降更新
        optimizer.step()
        # 每300次输出一次
        running_loss += loss.item()
        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
    # 不会计算梯度
    with torch.no_grad():
        for data in test_loader:  # 拿数据
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = model(images)  # 预测
            # outputs.data是一个矩阵，每一行10个量，最大值的下标就是预测值
            _, predicted = torch.max(outputs.data, dim=1)  # 沿着第一维度，找最大值的下标，返回最大值和下标
            total += labels.size(0)  # labels.size(0)=64 每个都是64个元素，就可以计算总的元素
            # (predicted == labels).sum()这个是张量，而加了item()变为一个数字，即相等的数量
            correct += (predicted == labels).sum().item()
    print('Accuracy on test set:%d %%' % (100 * correct / total))  # 正确的数量除以总数
if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()

import torch
import torch.nn as nn
from torchvision import transforms  # 对图像进行处理的工具
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F  # 使用激活函数relu()的包
import torch.optim as optim  # 优化器的包
batch_size = 64
# 对图像进行预处理，将图像转换为
transform = transforms.Compose([
    # 将原始图像PIL变为张量tensor(H*W*C),再将[0,255]区间转换为[0.1,1.0]
    transforms.ToTensor(),
    # 使用均值和标准差对张量图像进行归一化
    transforms.Normalize((0.1307,), (0.3081,))
])
train_dataset = datasets.MNIST(root='dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)
class InceptionA(nn.Module):
    def __init__(self, in_channels):
        super(InceptionA, self).__init__()
        # 第一个通道，输入通道为in_channels,输出通道为16，卷积盒的大小为1*1的卷积层
        self.branch1x1 = nn.Conv2d(in_channels, 16, kernel_size=1)
        # 第二个通道
        self.branch5x5_1 = nn.Conv2d(in_channels, 16, kernel_size=1)
        self.branch5x5_2 = nn.Conv2d(16, 24, kernel_size=5, padding=2)
        # 第三个通道
        self.branch3x3_1 = nn.Conv2d(in_channels, 16, kernel_size=1)
        self.branch3x3_2 = nn.Conv2d(16, 24, kernel_size=3, padding=1)
        self.branch3x3_3 = nn.Conv2d(24, 24, kernel_size=3, padding=1)
        # 第四个通道
        self.branch_pool = nn.Conv2d(in_channels, 24, kernel_size=1)
    def forward(self, x):
        branch1x1 = self.branch1x1(x)
        branch5x5 = self.branch5x5_1(x)
        branch5x5 = self.branch5x5_2(branch5x5)
        branch3x3 = self.branch3x3_1(x)
        branch3x3 = self.branch3x3_2(branch3x3)
        branch3x3 = self.branch3x3_3(branch3x3)
        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)
        # 拼接
        outputs = [branch1x1, branch5x5, branch3x3, branch_pool]
        return torch.cat(outputs, dim=1)
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(88, 20, kernel_size=5)
        self.incep1 = InceptionA(in_channels=10)
        self.incep2 = InceptionA(in_channels=20)
        self.mp = nn.MaxPool2d(2)
        self.fc = nn.Linear(1408, 10)
    def forward(self, x):
        in_size = x.size(0)
        x = F.relu(self.mp(self.conv1(x)))
        x = self.incep1(x)
        x = F.relu(self.mp(self.conv2(x)))
        x = self.incep2(x)
        x = x.view(in_size, -1)
        x = self.fc(x)
        return x
model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
# 交叉熵损失函数
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)  # momentum动量
def train(epoch):
    running_loss = 0.0
    # 返回了数据下标和数据
    for batch_idx, data in enumerate(train_loader, 0):
        # 送入两个张量，一个张量是64个图像的特征，一个张量图片对应的数字
        inputs, target = data
        # 把输入输出迁入GPU
        inputs, target = inputs.to(device), target.to(device)
        # 梯度归零
        optimizer.zero_grad()
        # forward+backward+update
        outputs = model(inputs)
        # 计算损失，用的交叉熵损失函数
        loss = criterion(outputs, target)
        # 反馈
        loss.backward()
        # 随机梯度下降更新
        optimizer.step()
        # 每300次输出一次
        running_loss += loss.item()
        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
    # 不会计算梯度
    with torch.no_grad():
        for data in test_loader:  # 拿数据
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = model(images)  # 预测
            # outputs.data是一个矩阵，每一行10个量，最大值的下标就是预测值
            _, predicted = torch.max(outputs.data, dim=1)  # 沿着第一维度，找最大值的下标，返回最大值和下标
            total += labels.size(0)  # labels.size(0)=64 每个都是64个元素，就可以计算总的元素
            # (predicted == labels).sum()这个是张量，而加了item()变为一个数字，即相等的数量
            correct += (predicted == labels).sum().item()
    print('Accuracy on test set:%d %%' % (100 * correct / total))  # 正确的数量除以总数
if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()

import torch.nn as nn
import torch.nn.functional as F
class ResidualBlock(nn.Module):
    def __init__(self,channels):
        super(ResidualBlock,self).__init__()
        self.channels = channels
        self.conv1 = nn.Conv2d(channels,channels,kernel_size=3,padding=1)
        self.conv2 = nn.Conv2d(channels,channels,kernel_size=3,padding=1)
    def forward(self,x):
        y = F.relu(self.conv1(x))
        y = self.conv2(y)
        return F.relu(x+y)
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 16, kernel_size=5)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=5)
        self.mp = nn.MaxPool2d(2)
        self.rblock1 = ResidualBlock(16)
        self.rblock2 = ResidualBlock(32)
        self.fc = nn.Linear(512, 10)
    def forward(self, x):
        in_size = x.size(0)
        x = self.mp(F.relu(self.conv1(x)))
        x = self.rblock1(x)
        x = self.mp(F.relu(self.conv2(x)))
        x = self.rblock2(x)
        x = x.view(in_size, -1)
        x = self.fc(x)
        return x

import torch
from torch import nn
class Rnn(nn.Module):
def __init__(self, INPUT_SIZE):
super(Rnn, self).__init__()
self.rnn = nn.RNN(
input_size=INPUT_SIZE,
hidden_size=32,
num_layers=1,
batch_first=True
)
self.out = nn.Linear(32, 1)
def forward(self, x, h_state):
r_out, h_state = self.rnn(x, h_state)
outs = []
for time in range(r_out.size(1)):
outs.append(self.out(r_out[:, time, :]))
return torch.stack(outs, dim=1), h_state

import numpy as np
import matplotlib.pyplot as plt
import torch
from torch import nn
import rnn
# 定义一些超参数
TIME_STEP = 10
INPUT_SIZE = 1
LR = 0.02
# # 创造一些数据
# steps = np.linspace(0, np.pi*2, 100, dtype=np.float)
# x_np = np.sin(steps)
# y_np = np.cos(steps)
# #
# # “看”数据
# plt.plot(steps, y_np, 'r-', label='target(cos)')
# plt.plot(steps, x_np, 'b-', label='input(sin)')
# plt.legend(loc='best')
# plt.show()
# 选择模型
model = rnn.Rnn(INPUT_SIZE)
print(model)
# 定义优化器和损失函数
loss_func = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=LR)
h_state = None # 第一次的时候，暂存为0
for step in range(300):
start, end = step * np.pi, (step+1)*np.pi
steps = np.linspace(start, end, TIME_STEP, dtype=np.float32)
x_np = np.sin(steps)
y_np = np.cos(steps)
x = torch.from_numpy(x_np[np.newaxis, :, np.newaxis])
y = torch.from_numpy(y_np[np.newaxis, :, np.newaxis])
prediction, h_state = model(x, h_state)
h_state = h_state.data
loss = loss_func(prediction, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()

plt.plot(steps, y_np.flatten(), 'r-')
plt.plot(steps, prediction.data.numpy().flatten(), 'b-')
plt.show()

from torch.utils.data import Dataset
import pandas as pd
class NameDataset(Dataset):
    """数据集类"""
    def __init__(self, is_train_set=True):
        filename = './name_data/names_train.csv' if is_train_set else './name_data/names_test.csv'
        data = pd.read_csv(filename, header=None)
        self.names = data[0]
        self.len = len(self.names)
        self.countries = data[1]
        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 idx2country(self, index):
        return self.country_list[index]
    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 getCountriesNum(self):
        return self.country_num
定义函数，用于将读取到的数据转化为tensor。
def name2list(name):
    """返回ASCII码表示的姓名列表与列表长度"""
    arr = [ord(c) for c in name]
    return arr, len(arr)
def make_tensors(names, countries):
    # 元组列表，每个元组包含ASCII码表示的姓名列表与列表长度
    sequences_and_lengths = [name2list(name) for name in names]
    # 取出所有的ASCII码表示的姓名列表
    name_sequences = [sl[0] for sl in sequences_and_lengths]
    # 取出所有的列表长度
    seq_lengths = torch.LongTensor([sl[1] for sl in sequences_and_lengths])
    # 将countries转为long型
    countries = countries.long()
    # 接下来每个名字序列补零，使之长度一样。
    # 先初始化一个全为零的tensor，大小为 所有姓名的数量*最长姓名的长度
    seq_tensor = torch.zeros(len(name_sequences), seq_lengths.max()).long()
    # 将姓名序列覆盖到初始化的全零tensor上
    for idx, (seq, seq_len) in enumerate(zip(name_sequences, seq_lengths), 0):
        seq_tensor[idx, :seq_len] = torch.LongTensor(seq)
    # 根据序列长度seq_lengths对补零后tensor进行降序怕排列，方便后面加速计算。
    # 返回排序后的seq_lengths与索引变化列表
    seq_lengths, perm_idx = seq_lengths.sort(dim=0, descending=True)
    # 根据索引变化列表对ASCII码表示的姓名列表进行排序
    seq_tensor = seq_tensor[perm_idx]
    # 根据索引变化列表对countries进行排序，使姓名与国家还是一一对应关系
    # seq_tensor.shape : batch_size*max_seq_lengths,
    # seq_lengths.shape : batch_size
    # countries.shape : batch_size
    countries = countries[perm_idx]
    return seq_tensor, seq_lengths, countries

import torch
from torch.nn.utils.rnn import pack_padded_sequence
class RNNClassifier(torch.nn.Module):
    # input_size=128, hidden_size=100, output_size=18
    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  # 是否双向
        self.embedding = torch.nn.Embedding(input_size, hidden_size)  # 输入大小128，输出大小100。
        # 经过Embedding后input的大小是100，hidden_size的大小也是100，所以形参都是hidden_size。
        self.gru = torch.nn.GRU(hidden_size, hidden_size, n_layers, bidirectional=bidirectional)
        # 如果是双向，会输出两个hidden层，要进行拼接，所以线形成的input大小是 hidden_size * self.n_directions，输出是大小是18，是为18个国家的概率。
        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 hidden
    def forward(self, input, seq_lengths):
        # 先对input进行转置，input shape : batch_size*max_seq_lengths -> max_seq_lengths*batch_size 每一列表示姓名
        input = input.t()
        batch_size = input.size(1)  # 总共有多少列，既是batch_size的大小
        hidden = self._init_hidden(batch_size)  # 初始化隐藏层
        embedding = self.embedding(input)  # embedding.shape : max_seq_lengths*batch_size*hidden_size 12*64*100
        # pack_padded_sequence方便批量计算
        gru_input = pack_padded_sequence(embedding, seq_lengths)
        # 进入网络进行计算
        output, hidden = self.gru(gru_input, hidden)
        # 如果是双向的，需要进行拼接
        if self.n_directions == 2:
            hidden_cat = torch.cat([hidden[-1], hidden[-2]], dim=1)
        else:
            hidden_cat = hidden[-1]
        # 线性层输出大小为18
        fc_output = self.fc(hidden_cat)
        return fc_output

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):  # 这里的1意思是 i 从1开始。
        # make_tensors函数返回经过降序排列后的 姓名列表，列表长度，国家
        inputs, seq_lengths, target = make_tensors(names, countries)
        # 输入姓名列表与列表长度向前计算
        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(i)
            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

from torch.utils.data import DataLoader
import time
import math
if __name__ == '__main__':
    N_EPOCHS = 30  # epoch
    HIDDEN_SIZE = 100  # 隐藏层的大小，也是Embedding后输出的大小
    BATCH_SIZE = 64
    N_COUNTRY = 18  # 总共有18个类别的国家，为RNN后输出的大小
    N_LAYER = 2
    N_CHARS = 128  # 字母字典的大小，Embedding输入的大小
    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)
    # 建立分类模型
    classifier = RNNClassifier(N_CHARS, HIDDEN_SIZE, N_COUNTRY, N_LAYER)
    # 建立损失函数与优化器
    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)