fnn手动实现和nn实现(包括3种激活函数、隐藏层)

原文网址：https://blog.csdn.net/m0_52910424/article/details/127819278

fnn手动实现:

import time
import matplotlib.pyplot as plt
import numpy as np
import torch
import torch.nn as nn
import torchvision
from torch.nn.functional import cross_entropy, binary_cross_entropy
from torch.nn import CrossEntropyLoss
from torchvision import transforms
from sklearn import  metrics
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # 如果有gpu则在gpu上计算 加快计算速度
print(f'当前使用的device为{device}')
# 数据集定义
# 构建回归数据集合 - traindataloader1, testdataloader1
data_num, train_num, test_num = 10000, 7000, 3000 # 分别为样本总数量，训练集样本数量和测试集样本数量
true_w, true_b = 0.0056 * torch.ones(500,1), 0.028 
features = torch.randn(data_num, 500)
labels = torch.matmul(features,true_w) + true_b # 按高斯分布
labels += torch.tensor(np.random.normal(0,0.01,size=labels.size()),dtype=torch.float32)
# 划分训练集和测试集
train_features, test_features = features[:train_num,:], features[train_num:,:]
train_labels, test_labels = labels[:train_num], labels[train_num:]
batch_size = 128
traindataset1 = torch.utils.data.TensorDataset(train_features,train_labels)
testdataset1 = torch.utils.data.TensorDataset(test_features, test_labels)
traindataloader1 = torch.utils.data.DataLoader(dataset=traindataset1,batch_size=batch_size,shuffle=True)
testdataloader1 = torch.utils.data.DataLoader(dataset=testdataset1,batch_size=batch_size,shuffle=True)

# 构二分类数据集合
data_num, train_num, test_num = 10000, 7000, 3000  # 分别为样本总数量，训练集样本数量和测试集样本数量
# 第一个数据集 符合均值为 0.5 标准差为1 得分布
features1 = torch.normal(mean=0.2, std=2, size=(data_num, 200), dtype=torch.float32)
labels1 = torch.ones(data_num)
# 第二个数据集 符合均值为 -0.5 标准差为1的分布
features2 = torch.normal(mean=-0.2, std=2, size=(data_num, 200), dtype=torch.float32)
labels2 = torch.zeros(data_num)

# 构建训练数据集
train_features2 = torch.cat((features1[:train_num], features2[:train_num]), dim=0)  # size torch.Size([14000, 200])
train_labels2 = torch.cat((labels1[:train_num], labels2[:train_num]), dim=-1)  # size  torch.Size([6000, 200])
# 构建测试数据集
test_features2 = torch.cat((features1[train_num:], features2[train_num:]), dim=0)  # torch.Size([14000])
test_labels2 = torch.cat((labels1[train_num:], labels2[train_num:]), dim=-1)  # torch.Size([6000])
batch_size = 128
# Build the training and testing dataset
traindataset2 = torch.utils.data.TensorDataset(train_features2, train_labels2)
testdataset2 = torch.utils.data.TensorDataset(test_features2, test_labels2)
traindataloader2 = torch.utils.data.DataLoader(dataset=traindataset2,batch_size=batch_size,shuffle=True)
testdataloader2 = torch.utils.data.DataLoader(dataset=testdataset2,batch_size=batch_size,shuffle=True)

# 定义多分类数据集 - train_dataloader - test_dataloader
batch_size = 128
# Build the training and testing dataset
traindataset3 = torchvision.datasets.FashionMNIST(root='.\\FashionMNIST\\Train',
                                                  train=True,
                                                  download=True,
                                                  transform=transforms.ToTensor())
testdataset3 = torchvision.datasets.FashionMNIST(root='.\\FashionMNIST\\Test',
                                                 train=False,
                                                 download=True,
                                                 transform=transforms.ToTensor())
traindataloader3 = torch.utils.data.DataLoader(traindataset3, batch_size=batch_size, shuffle=True)
testdataloader3 = torch.utils.data.DataLoader(testdataset3, batch_size=batch_size, shuffle=False)
# 绘制图像的代码
def picture(name, trainl, testl, type='Loss'):
    plt.rcParams["font.sans-serif"]=["SimHei"] #设置字体
    plt.rcParams["axes.unicode_minus"]=False #该语句解决图像中的"-"负号的乱码问题
    plt.title(name) # 命名
    plt.plot(trainl, c='g', label='Train '+ type)
    plt.plot(testl, c='r', label='Test '+type)
    plt.xlabel('Epoch')
    plt.ylabel('Loss')
    plt.legend()
    plt.grid(True)
print(f'回归数据集   样本总数量{len(traindataset1) + len(testdataset1)},训练样本数量{len(traindataset1)},测试样本数量{len(testdataset1)}')
print(f'二分类数据集 样本总数量{len(traindataset2) + len(testdataset2)},训练样本数量{len(traindataset2)},测试样本数量{len(testdataset2)}')
print(f'多分类数据集 样本总数量{len(traindataset3) + len(testdataset3)},训练样本数量{len(traindataset3)},测试样本数量{len(testdataset3)}')



# 定义自己的前馈神经网络
class MyNet1():
    def __init__(self):
        # 设置隐藏层和输出层的节点数
        num_inputs, num_hiddens, num_outputs = 500, 256, 1
        w_1 = torch.tensor(np.random.normal(0,0.01,(num_hiddens,num_inputs)),dtype=torch.float32,requires_grad=True)
        b_1 = torch.zeros(num_hiddens, dtype=torch.float32,requires_grad=True)
        w_2 = torch.tensor(np.random.normal(0, 0.01,(num_outputs, num_hiddens)),dtype=torch.float32,requires_grad=True)
        b_2 = torch.zeros(num_outputs,dtype=torch.float32, requires_grad=True)
        self.params = [w_1, b_1, w_2, b_2]

        # 定义模型结构
        self.input_layer = lambda x: x.view(x.shape[0],-1)
        self.hidden_layer = lambda x: self.my_relu(torch.matmul(x,w_1.t())+b_1)
        self.output_layer = lambda x: torch.matmul(x,w_2.t()) + b_2

    def my_relu(self, x):
        return torch.max(input=x,other=torch.tensor(0.0))

    def forward(self,x):
        x = self.input_layer(x)
        x = self.my_relu(self.hidden_layer(x))
        x = self.output_layer(x)
        return x
def mySGD(params, lr, batchsize):
    for param in params:
        param.data -= lr*param.grad / batchsize

def mse(pred, true):
    ans = torch.sum((true-pred)**2) / len(pred)
    # print(ans)
    return ans

# 训练
model1 = MyNet1()  # logistics模型
criterion = CrossEntropyLoss()   # 损失函数
lr = 0.05   # 学习率
batchsize = 128 
epochs = 40 #训练轮数
train_all_loss1 = [] # 记录训练集上得loss变化
test_all_loss1 = [] #记录测试集上的loss变化
begintime1 = time.time()
for epoch in range(epochs):
    train_l = 0
    for data, labels in traindataloader1:
        pred = model1.forward(data)
        train_each_loss = mse(pred.view(-1,1), labels.view(-1,1)) #计算每次的损失值
        train_each_loss.backward() # 反向传播
        mySGD(model1.params, lr, batchsize) # 使用小批量随机梯度下降迭代模型参数
        # 梯度清零
        train_l += train_each_loss.item()
        for param in model1.params:
            param.grad.data.zero_()
        # print(train_each_loss)
    train_all_loss1.append(train_l) # 添加损失值到列表中
    with torch.no_grad():
        test_loss = 0
        for data, labels in traindataloader1:
            pred = model1.forward(data)
            test_each_loss = mse(pred, labels)
            test_loss += test_each_loss.item()
        test_all_loss1.append(test_loss)
    if epoch==0 or (epoch+1) % 4 == 0:
        print('epoch: %d | train loss:%.5f | test loss:%.5f'%(epoch+1,train_all_loss1[-1],test_all_loss1[-1]))
endtime1 = time.time()
print("手动实现前馈网络-回归实验 %d轮 总用时: %.3fs"%(epochs,endtime1-begintime1))



# 定义自己的前馈神经网络
class MyNet2():
    def __init__(self):
        # 设置隐藏层和输出层的节点数
        num_inputs, num_hiddens, num_outputs = 200, 256, 1
        w_1 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens, num_inputs)), dtype=torch.float32,
                           requires_grad=True)
        b_1 = torch.zeros(num_hiddens, dtype=torch.float32, requires_grad=True)
        w_2 = torch.tensor(np.random.normal(0, 0.01, (num_outputs, num_hiddens)), dtype=torch.float32,
                           requires_grad=True)
        b_2 = torch.zeros(num_outputs, dtype=torch.float32, requires_grad=True)
        self.params = [w_1, b_1, w_2, b_2]

        # 定义模型结构
        self.input_layer = lambda x: x.view(x.shape[0], -1)
        self.hidden_layer = lambda x: self.my_relu(torch.matmul(x, w_1.t()) + b_1)
        self.output_layer = lambda x: torch.matmul(x, w_2.t()) + b_2
        self.fn_logistic = self.logistic

    def my_relu(self, x):
        return torch.max(input=x, other=torch.tensor(0.0))

    def logistic(self, x):  # 定义logistic函数
        x = 1.0 / (1.0 + torch.exp(-x))
        return x

    # 定义前向传播
    def forward(self, x):
        x = self.input_layer(x)
        x = self.my_relu(self.hidden_layer(x))
        x = self.fn_logistic(self.output_layer(x))
        return x


def mySGD(params, lr):
    for param in params:
        param.data -= lr * param.grad

# 训练
model2 = MyNet2()
lr = 0.01  # 学习率
epochs = 40  # 训练轮数
train_all_loss2 = []  # 记录训练集上得loss变化
test_all_loss2 = []  # 记录测试集上的loss变化
train_Acc12, test_Acc12 = [], []
begintime2 = time.time()
for epoch in range(epochs):
    train_l, train_epoch_count = 0, 0
    for data, labels in traindataloader2:
        pred = model2.forward(data)
        train_each_loss = binary_cross_entropy(pred.view(-1), labels.view(-1))  # 计算每次的损失值
        train_l += train_each_loss.item()
        train_each_loss.backward()  # 反向传播
        mySGD(model2.params, lr)  # 使用随机梯度下降迭代模型参数
        # 梯度清零
        for param in model2.params:
            param.grad.data.zero_()
        # print(train_each_loss)
        train_epoch_count += (torch.tensor(np.where(pred > 0.5, 1, 0)).view(-1) == labels).sum()
    train_Acc12.append((train_epoch_count/len(traindataset2)).item())
    train_all_loss2.append(train_l)  # 添加损失值到列表中
    with torch.no_grad():
        test_l, test_epoch_count = 0, 0
        for data, labels in testdataloader2:
            pred = model2.forward(data)
            test_each_loss = binary_cross_entropy(pred.view(-1), labels.view(-1))
            test_l += test_each_loss.item()
            test_epoch_count += (torch.tensor(np.where(pred > 0.5, 1, 0)).view(-1) == labels.view(-1)).sum()
        test_Acc12.append((test_epoch_count/len(testdataset2)).item())
        test_all_loss2.append(test_l)
    if epoch == 0 or (epoch + 1) % 4 == 0:
        print('epoch: %d | train loss:%.5f | test loss:%.5f | train acc:%.5f | test acc:%.5f'  % (epoch + 1, train_all_loss2[-1], test_all_loss2[-1], train_Acc12[-1], test_Acc12[-1]))
endtime2 = time.time()
print("手动实现前馈网络-二分类实验 %d轮 总用时: %.3f" % (epochs, endtime2 - begintime2))


# 定义自己的前馈神经网络
class MyNet3():
    def __init__(self):
        # 设置隐藏层和输出层的节点数
        num_inputs, num_hiddens, num_outputs = 28 * 28, 256, 10  # 十分类问题
        w_1 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens, num_inputs)), dtype=torch.float32,
                           requires_grad=True)
        b_1 = torch.zeros(num_hiddens, dtype=torch.float32, requires_grad=True)
        w_2 = torch.tensor(np.random.normal(0, 0.01, (num_outputs, num_hiddens)), dtype=torch.float32,
                           requires_grad=True)
        b_2 = torch.zeros(num_outputs, dtype=torch.float32, requires_grad=True)
        self.params = [w_1, b_1, w_2, b_2]

        # 定义模型结构
        self.input_layer = lambda x: x.view(x.shape[0], -1)
        self.hidden_layer = lambda x: self.my_relu(torch.matmul(x, w_1.t()) + b_1)
        self.output_layer = lambda x: torch.matmul(x, w_2.t()) + b_2

    def my_relu(self, x):
        return torch.max(input=x, other=torch.tensor(0.0))

    # 定义前向传播
    def forward(self, x):
        x = self.input_layer(x)
        x = self.hidden_layer(x)
        x = self.output_layer(x)
        return x


def mySGD(params, lr, batchsize):
    for param in params:
        param.data -= lr * param.grad / batchsize

# 训练
model3 = MyNet3()  # logistics模型
criterion = cross_entropy  # 损失函数
lr = 0.15  # 学习率
epochs = 40  # 训练轮数
train_all_loss3 = []  # 记录训练集上得loss变化
test_all_loss3 = []  # 记录测试集上的loss变化
train_ACC13, test_ACC13 = [], [] # 记录正确的个数
begintime3 = time.time()
for epoch in range(epochs):
    train_l,train_acc_num = 0, 0
    for data, labels in traindataloader3:
        pred = model3.forward(data)
        train_each_loss = criterion(pred, labels)  # 计算每次的损失值
        train_l += train_each_loss.item()
        train_each_loss.backward()  # 反向传播
        mySGD(model3.params, lr, 128)  # 使用小批量随机梯度下降迭代模型参数
        # 梯度清零
        train_acc_num += (pred.argmax(dim=1)==labels).sum().item()
        for param in model3.params:
            param.grad.data.zero_()
        # print(train_each_loss)
    train_all_loss3.append(train_l)  # 添加损失值到列表中
    train_ACC13.append(train_acc_num / len(traindataset3)) # 添加准确率到列表中
    with torch.no_grad():
        test_l, test_acc_num = 0, 0
        for data, labels in testdataloader3:
            pred = model3.forward(data)
            test_each_loss = criterion(pred, labels)
            test_l += test_each_loss.item()
            test_acc_num += (pred.argmax(dim=1)==labels).sum().item()
        test_all_loss3.append(test_l)
        test_ACC13.append(test_acc_num / len(testdataset3))   # # 添加准确率到列表中
    if epoch == 0 or (epoch + 1) % 4 == 0:
        print('epoch: %d | train loss:%.5f | test loss:%.5f | train acc: %.2f | test acc: %.2f'
              % (epoch + 1, train_l, test_l, train_ACC13[-1],test_ACC13[-1]))
endtime3 = time.time()
print("手动实现前馈网络-多分类实验 %d轮 总用时: %.3f" % (epochs, endtime3 - begintime3))



plt.figure(figsize=(12,3))
plt.title('Loss')
plt.subplot(131)
picture('前馈网络-回归-Loss',train_all_loss1,test_all_loss1)
plt.subplot(132)
picture('前馈网络-二分类-loss',train_all_loss2,test_all_loss2)
plt.subplot(133)
picture('前馈网络-多分类-loss',train_all_loss3,test_all_loss3)
plt.show()


plt.figure(figsize=(8, 3))
plt.subplot(121)
picture('前馈网络-二分类-ACC',train_Acc12,test_Acc12,type='ACC')
plt.subplot(122)
picture('前馈网络-多分类---ACC', train_ACC13,test_ACC13, type='ACC')
plt.show()

nn实现(包括3种激活函数、多层隐藏层):

import time
import matplotlib.pyplot as plt
import numpy as np
import torch
import torch.nn as nn
import torchvision
from torch.nn.functional import cross_entropy, binary_cross_entropy
from torch.nn import CrossEntropyLoss
from torchvision import transforms
from sklearn import  metrics
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # 如果有gpu则在gpu上计算 加快计算速度
print(f'当前使用的device为{device}')
# 数据集定义
# 构建回归数据集合 - traindataloader1, testdataloader1
data_num, train_num, test_num = 10000, 7000, 3000 # 分别为样本总数量，训练集样本数量和测试集样本数量
true_w, true_b = 0.0056 * torch.ones(500,1), 0.028 
features = torch.randn(10000, 500)
labels = torch.matmul(features,true_w) + true_b # 按高斯分布
labels += torch.tensor(np.random.normal(0,0.01,size=labels.size()),dtype=torch.float32)
# 划分训练集和测试集
train_features, test_features = features[:train_num,:], features[train_num:,:]
train_labels, test_labels = labels[:train_num], labels[train_num:]
batch_size = 128
traindataset1 = torch.utils.data.TensorDataset(train_features,train_labels)
testdataset1 = torch.utils.data.TensorDataset(test_features, test_labels)
traindataloader1 = torch.utils.data.DataLoader(dataset=traindataset1,batch_size=batch_size,shuffle=True)
testdataloader1 = torch.utils.data.DataLoader(dataset=testdataset1,batch_size=batch_size,shuffle=True)

# 构二分类数据集合
data_num, train_num, test_num = 10000, 7000, 3000  # 分别为样本总数量，训练集样本数量和测试集样本数量
# 第一个数据集 符合均值为 0.5 标准差为1 得分布
features1 = torch.normal(mean=0.2, std=2, size=(data_num, 200), dtype=torch.float32)
labels1 = torch.ones(data_num)
# 第二个数据集 符合均值为 -0.5 标准差为1的分布
features2 = torch.normal(mean=-0.2, std=2, size=(data_num, 200), dtype=torch.float32)
labels2 = torch.zeros(data_num)

# 构建训练数据集
train_features2 = torch.cat((features1[:train_num], features2[:train_num]), dim=0)  # size torch.Size([14000, 200])
train_labels2 = torch.cat((labels1[:train_num], labels2[:train_num]), dim=-1)  # size  torch.Size([6000, 200])
# 构建测试数据集
test_features2 = torch.cat((features1[train_num:], features2[train_num:]), dim=0)  # torch.Size([14000])
test_labels2 = torch.cat((labels1[train_num:], labels2[train_num:]), dim=-1)  # torch.Size([6000])
batch_size = 128
# Build the training and testing dataset
traindataset2 = torch.utils.data.TensorDataset(train_features2, train_labels2)
testdataset2 = torch.utils.data.TensorDataset(test_features2, test_labels2)
traindataloader2 = torch.utils.data.DataLoader(dataset=traindataset2,batch_size=batch_size,shuffle=True)
testdataloader2 = torch.utils.data.DataLoader(dataset=testdataset2,batch_size=batch_size,shuffle=True)

# 定义多分类数据集 - train_dataloader - test_dataloader
batch_size = 128
# Build the training and testing dataset
traindataset3 = torchvision.datasets.FashionMNIST(root='.\\FashionMNIST\\Train',
                                                  train=True,
                                                  download=True,
                                                  transform=transforms.ToTensor())
testdataset3 = torchvision.datasets.FashionMNIST(root='.\\FashionMNIST\\Test',
                                                 train=False,
                                                 download=True,
                                                 transform=transforms.ToTensor())
traindataloader3 = torch.utils.data.DataLoader(traindataset3, batch_size=batch_size, shuffle=True)
testdataloader3 = torch.utils.data.DataLoader(testdataset3, batch_size=batch_size, shuffle=False)
# 绘制图像的代码
def picture(name, trainl, testl, type='Loss'):
    plt.rcParams["font.sans-serif"]=["SimHei"] #设置字体
    plt.rcParams["axes.unicode_minus"]=False #该语句解决图像中的"-"负号的乱码问题
    plt.title(name) # 命名
    plt.plot(trainl, c='g', label='Train '+ type)
    plt.plot(testl, c='r', label='Test '+type)
    plt.xlabel('Epoch')
    plt.ylabel('Loss')
    plt.legend()
    plt.grid(True)
print(f'回归数据集   样本总数量{len(traindataset1) + len(testdataset1)},训练样本数量{len(traindataset1)},测试样本数量{len(testdataset1)}')
print(f'二分类数据集 样本总数量{len(traindataset2) + len(testdataset2)},训练样本数量{len(traindataset2)},测试样本数量{len(testdataset2)}')
print(f'多分类数据集 样本总数量{len(traindataset3) + len(testdataset3)},训练样本数量{len(traindataset3)},测试样本数量{len(testdataset3)}')



def ComPlot(datalist,title='1',ylabel='Loss',flag='act'):
    plt.rcParams["font.sans-serif"]=["SimHei"] #设置字体
    plt.rcParams["axes.unicode_minus"]=False #该语句解决图像中的"-"负号的乱码问题
    plt.title(title)
    plt.xlabel('Epoch')
    plt.ylabel(ylabel)
    plt.plot(datalist[0],label='Tanh' if flag=='act' else '[128]')
    plt.plot(datalist[1],label='Sigmoid' if flag=='act' else '[512 256]')
    plt.plot(datalist[2],label='ELu' if flag=='act' else '[512 256 128 64]')
    plt.plot(datalist[3],label='Relu' if flag=='act' else '[256]')
    plt.legend()
    plt.grid(True)





from torch.optim import SGD
from torch.nn import MSELoss
# 利用torch.nn实现前馈神经网络-回归任务 代码
# 定义自己的前馈神经网络
class MyNet21(nn.Module):
    def __init__(self):
        super(MyNet21, self).__init__()
        # 设置隐藏层和输出层的节点数
        num_inputs, num_hiddens, num_outputs = 500, 256, 1
        # 定义模型结构
        self.input_layer = nn.Flatten()
        self.hidden_layer = nn.Linear(num_inputs, num_hiddens)
        self.output_layer = nn.Linear(num_hiddens, num_outputs)
        self.relu = nn.ReLU()

    # 定义前向传播
    def forward(self, x):
        x = self.input_layer(x)
        x = self.relu(self.hidden_layer(x))
        x = self.output_layer(x)
        return x

# 训练
model21 = MyNet21()  # logistics模型
model21 = model21.to(device)
print(model21)
criterion = MSELoss()  # 损失函数
criterion = criterion.to(device)
optimizer = SGD(model21.parameters(), lr=0.1)  # 优化函数
epochs = 40  # 训练轮数
train_all_loss21 = []  # 记录训练集上得loss变化
test_all_loss21 = []  # 记录测试集上的loss变化
begintime21 = time.time()
for epoch in range(epochs):
    train_l = 0
    for data, labels in traindataloader1:
        data, labels = data.to(device=device), labels.to(device)
        pred = model21(data)
        train_each_loss = criterion(pred.view(-1, 1), labels.view(-1, 1))  # 计算每次的损失值
        optimizer.zero_grad()  # 梯度清零
        train_each_loss.backward()  # 反向传播
        optimizer.step()  # 梯度更新
        train_l += train_each_loss.item()
    train_all_loss21.append(train_l)  # 添加损失值到列表中
    with torch.no_grad():
        test_loss = 0
        for data, labels in testdataloader1:
            data, labels = data.to(device), labels.to(device)
            pred = model21(data)
            test_each_loss = criterion(pred,labels)
            test_loss += test_each_loss.item()
        test_all_loss21.append(test_loss)
    if epoch == 0 or (epoch + 1) % 10 == 0:
        print('epoch: %d | train loss:%.5f | test loss:%.5f' % (epoch + 1, train_all_loss21[-1], test_all_loss21[-1]))
endtime21 = time.time()
print("torch.nn实现前馈网络-回归实验 %d轮 总用时: %.3fs" % (epochs, endtime21 - begintime21))


# 利用torch.nn实现前馈神经网络-二分类任务
import time
from torch.optim import SGD
from torch.nn.functional import binary_cross_entropy
# 利用torch.nn实现前馈神经网络-回归任务 代码
# 定义自己的前馈神经网络
class MyNet22(nn.Module):
    def __init__(self):
        super(MyNet22, self).__init__()
        # 设置隐藏层和输出层的节点数
        num_inputs, num_hiddens, num_outputs = 200, 256, 1
        # 定义模型结构
        self.input_layer = nn.Flatten()
        self.hidden_layer = nn.Linear(num_inputs, num_hiddens)
        self.output_layer = nn.Linear(num_hiddens, num_outputs)
        self.relu = nn.ReLU()

    def logistic(self, x):  # 定义logistic函数
        x = 1.0 / (1.0 + torch.exp(-x))
        return x
    # 定义前向传播
    def forward(self, x):
        x = self.input_layer(x)
        x = self.relu(self.hidden_layer(x))
        x = self.logistic(self.output_layer(x))
        return x

# 训练
model22 = MyNet22()  # logistics模型
model22 = model22.to(device)
print(model22)
optimizer = SGD(model22.parameters(), lr=0.001)  # 优化函数
epochs = 40  # 训练轮数
train_all_loss22 = []  # 记录训练集上得loss变化
test_all_loss22 = []  # 记录测试集上的loss变化
train_ACC22, test_ACC22 = [], []
begintime22 = time.time()
for epoch in range(epochs):
    train_l, train_epoch_count, test_epoch_count = 0, 0, 0 # 每一轮的训练损失值 训练集正确个数 测试集正确个数
    for data, labels in traindataloader2:
        data, labels = data.to(device), labels.to(device)
        pred = model22(data)
        train_each_loss = binary_cross_entropy(pred.view(-1), labels.view(-1))  # 计算每次的损失值
        optimizer.zero_grad()  # 梯度清零
        train_each_loss.backward()  # 反向传播
        optimizer.step()  # 梯度更新
        train_l += train_each_loss.item()
        pred = torch.tensor(np.where(pred.cpu()>0.5, 1, 0))  # 大于 0.5时候，预测标签为 1 否则为0
        each_count = (pred.view(-1) == labels.cpu()).sum() # 每一个batchsize的正确个数
        train_epoch_count += each_count # 计算每个epoch上的正确个数
    train_ACC22.append(train_epoch_count / len(traindataset2))
    train_all_loss22.append(train_l)  # 添加损失值到列表中
    with torch.no_grad():
        test_loss, each_count = 0, 0
        for data, labels in testdataloader2:
            data, labels = data.to(device), labels.to(device)
            pred = model22(data)
            test_each_loss = binary_cross_entropy(pred.view(-1),labels)
            test_loss += test_each_loss.item()
            # .cpu 为转换到cpu上计算
            pred = torch.tensor(np.where(pred.cpu() > 0.5, 1, 0))
            each_count = (pred.view(-1)==labels.cpu().view(-1)).sum()
            test_epoch_count += each_count
        test_all_loss22.append(test_loss)
        test_ACC22.append(test_epoch_count / len(testdataset2))
    if epoch == 0 or (epoch + 1) % 4 == 0:
        print('epoch: %d | train loss:%.5f test loss:%.5f | train acc:%.5f | test acc:%.5f' % (epoch + 1, train_all_loss22[-1], 
                                                                                               test_all_loss22[-1], train_ACC22[-1], test_ACC22[-1]))

endtime22 = time.time()
print("torch.nn实现前馈网络-二分类实验 %d轮 总用时: %.3fs" % (epochs, endtime22 - begintime22))



# 利用torch.nn实现前馈神经网络-多分类任务
from collections import OrderedDict
from torch.nn import CrossEntropyLoss
from torch.optim import SGD
# 定义自己的前馈神经网络
class MyNet23(nn.Module):
    """
    参数：  num_input：输入每层神经元个数，为一个列表数据
            num_hiddens：隐藏层神经元个数
            num_outs： 输出层神经元个数
            num_hiddenlayer : 隐藏层的个数
    """
    def __init__(self,num_hiddenlayer=1, num_inputs=28*28,num_hiddens=[256],num_outs=10,act='relu'):
        super(MyNet23, self).__init__()
        # 设置隐藏层和输出层的节点数
        self.num_inputs, self.num_hiddens, self.num_outputs = num_inputs,num_hiddens,num_outs # 十分类问题

        # 定义模型结构
        self.input_layer = nn.Flatten()
        # 若只有一层隐藏层
        if num_hiddenlayer ==1:
            self.hidden_layers = nn.Linear(self.num_inputs,self.num_hiddens[-1])
        else: # 若有多个隐藏层
            self.hidden_layers = nn.Sequential()
            self.hidden_layers.add_module("hidden_layer1", nn.Linear(self.num_inputs,self.num_hiddens[0]))
            for i in range(0,num_hiddenlayer-1):
                name = str('hidden_layer'+str(i+2))
                self.hidden_layers.add_module(name, nn.Linear(self.num_hiddens[i],self.num_hiddens[i+1]))
        self.output_layer = nn.Linear(self.num_hiddens[-1], self.num_outputs)
        # 指代需要使用什么样子的激活函数
        if act == 'relu':
            self.act = nn.ReLU()
        elif act == 'sigmoid':
            self.act = nn.Sigmoid()
        elif act == 'tanh':
            self.act = nn.Tanh()
        elif act == 'elu':
            self.act = nn.ELU()
        print(f'你本次使用的激活函数为 {act}')

    def logistic(self, x):  # 定义logistic函数
        x = 1.0 / (1.0 + torch.exp(-x))
        return x
    # 定义前向传播
    def forward(self, x):
        x = self.input_layer(x)
        x = self.act(self.hidden_layers(x))
        x = self.output_layer(x)
        return x

# 训练
# 使用默认的参数即： num_inputs=28*28,num_hiddens=256,num_outs=10,act='relu'
model23 = MyNet23()  
model23 = model23.to(device)

# 将训练过程定义为一个函数，方便实验三和实验四调用
def train_and_test(model=model23):
    MyModel = model
    print(MyModel)
    optimizer = SGD(MyModel.parameters(), lr=0.01)  # 优化函数
    epochs = 40  # 训练轮数
    criterion = CrossEntropyLoss() # 损失函数
    train_all_loss23 = []  # 记录训练集上得loss变化
    test_all_loss23 = []  # 记录测试集上的loss变化
    train_ACC23, test_ACC23 = [], []
    begintime23 = time.time()
    for epoch in range(epochs):
        train_l, train_epoch_count, test_epoch_count = 0, 0, 0
        for data, labels in traindataloader3:
            data, labels = data.to(device), labels.to(device)
            pred = MyModel(data)
            train_each_loss = criterion(pred, labels.view(-1))  # 计算每次的损失值
            optimizer.zero_grad()  # 梯度清零
            train_each_loss.backward()  # 反向传播
            optimizer.step()  # 梯度更新
            train_l += train_each_loss.item()
            train_epoch_count += (pred.argmax(dim=1)==labels).sum()
        train_ACC23.append(train_epoch_count.cpu()/len(traindataset3))
        train_all_loss23.append(train_l)  # 添加损失值到列表中
        with torch.no_grad():
            test_loss, test_epoch_count= 0, 0
            for data, labels in testdataloader3:
                data, labels = data.to(device), labels.to(device)
                pred = MyModel(data)
                test_each_loss = criterion(pred,labels)
                test_loss += test_each_loss.item()
                test_epoch_count += (pred.argmax(dim=1)==labels).sum()
            test_all_loss23.append(test_loss)
            test_ACC23.append(test_epoch_count.cpu()/len(testdataset3))
        if epoch == 0 or (epoch + 1) % 4 == 0:
            print('epoch: %d | train loss:%.5f | test loss:%.5f | train acc:%5f test acc:%.5f:' % (epoch + 1, train_all_loss23[-1], test_all_loss23[-1],
                                                                                                                     train_ACC23[-1],test_ACC23[-1]))
    endtime23 = time.time()
    print("torch.nn实现前馈网络-多分类任务 %d轮 总用时: %.3fs" % (epochs, endtime23 - begintime23))
    # 返回训练集和测试集上的 损失值 与 准确率
    return train_all_loss23,test_all_loss23,train_ACC23,test_ACC23
train_all_loss23,test_all_loss23,train_ACC23,test_ACC23 = train_and_test(model=model23)



plt.figure(figsize=(12,3))
plt.subplot(131)
picture('前馈网络-回归-loss',train_all_loss21,test_all_loss21)
plt.subplot(132)
picture('前馈网络-二分类-loss',train_all_loss22,test_all_loss22)
plt.subplot(133)
picture('前馈网络-多分类-loss',train_all_loss23,test_all_loss23)
plt.show()


plt.figure(figsize=(8,3))
plt.subplot(121)
picture('前馈网络-二分类-ACC',train_ACC22,test_ACC22,type='ACC')
plt.subplot(122)
picture('前馈网络-多分类-ACC',train_ACC23,test_ACC23,type='ACC')
plt.show()



plt.figure(figsize=(16,3))
plt.subplot(141)
ComPlot([train_all_loss31,train_all_loss32,train_all_loss33,train_all_loss23],title='Train_Loss')
plt.subplot(142)
ComPlot([test_all_loss31,test_all_loss32,test_all_loss33,test_all_loss23],title='Test_Loss')
plt.subplot(143)
ComPlot([train_ACC31,train_ACC32,train_ACC33,train_ACC23],title='Train_ACC')
plt.subplot(144)
ComPlot([test_ACC31,test_ACC32,test_ACC33,test_ACC23],title='Test_ACC')
plt.show()