PyTorch学习（十一）-- Homework_CNN Model

第10讲 CNN Model传送门：Basic CNN Model
作业如下：

根据讲解视频，自己编写了一个网络，结构如下：

3个CONV层，3个激活层（RELU），3个Pooling层，3个FC 层

实现代码如下：

# -*- coding: UTF-8 -*-
'''===============================================
@Author ：kidding
@Date   ：2021/2/8 14:19
@File   ：Basic_CNN_Exercise
@IDE    ：PyCharm
=================================================='''
import torch
import numpy as np
from torchvision import transforms
from torchvision import datasets
import torch.nn.functional as F
from torch.utils.data import DataLoader,Dataset
import matplotlib.pyplot as plt
'''
1、PrePare Dataset
'''
batch_size = 32
#transforms.ToTensor() 将一个PIL图像 转变为一个Tensor，像素值为[0,1]
transform = transforms.Compose([transforms.ToTensor(),
                               transforms.Normalize((0.1307,),(0.3081,))
                               ])
train_dataset = datasets.MNIST(root='./dataset/mnist',train=True,download=False,transform=transform)
train_loader = DataLoader(train_dataset,batch_size=batch_size,shuffle=True)

test_dataset =  datasets.MNIST(root='./dataset/mnist',train=False,download=False,transform=transform)
test_loader = DataLoader(test_dataset,batch_size=batch_size,shuffle=False)
'''
2、Design Model
'''
class Net(torch.nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.conv1 = torch.nn.Conv2d(1,10,kernel_size=5)#输出的通道为10，kernel_size是卷积核的大小，这里定义的是5x5
        self.conv2 = torch.nn.Conv2d(10,20,kernel_size=5)
        self.conv3 = torch.nn.Conv2d(20,40,kernel_size=3)
        self.pooling = torch.nn.MaxPool2d(2)
        # 最后是我们做分类用的线性层
        self.fc1 = torch.nn.Linear(40,60)
        self.fc2 = torch.nn.Linear(60,30)
        self.fc3 = torch.nn.Linear(30,10)

    def forward(self,x):
        #将输入图像（n,1,28,28）展平为 （n,784）
        batch_size = x.size(0) #求batch_size x.size(0)表示张量 x 的维度
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = F.relu(self.pooling(self.conv3(x)))
        x = x.view(batch_size,-1) #展平操作
        x = self.fc1(x)
        x = self.fc2(x)
        x = self.fc3(x) #最后一层不做RELU激活。
        return x

#实例化
model = Net()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

'''
3、Construct loss and optimizer
'''
#定义一个损失函数，来计算我们模型输出的值和标准值的差距
criterion = torch.nn.CrossEntropyLoss()
#定义一个优化器，训练模型咋训练的，就靠这个，他会反向的更改相应层的权重
optimizer = torch.optim.SGD(model.parameters(),lr=0.01,momentum = 0.5)

'''
4、Training Cycle : forward-->backward-->update
'''
def train(epoch):
    running_loss = 0.0
    for batch_idx,data in enumerate(train_loader,0): #每次取一个样本
        inputs,target = data
        inputs, target = inputs.to(device), target.to(device)
        optimizer.zero_grad() #优化器清0

        #forward
        outputs = model(inputs)
        loss = criterion(outputs,target)

        # backeard 反向求梯度
        loss.backward()
        # update 更新权重
        optimizer.step()

        running_loss += loss.item() #把损失加起来
        # 每600次输出一下数据
        if batch_idx % 600 == 599:
            print("Epoch:",epoch+1,"batch_idx:",batch_idx+1,"Loss={:.4f}".format(running_loss/600))
            running_loss = 0.0
    return running_loss/600

def test():
    correct = 0
    total = 0
    with torch.no_grad(): #测试不会计算梯度
        for data in test_loader:
            images,labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = model(images)
            # 我们取概率最大的那个数作为输出
            _,predicted = torch.max(outputs.data,dim=1) #取出最大值的下标   "_,"为占位符，代表每行最大值的下标， dim = 1 列是第0个维度，行是第1个维度
            total += labels.size(0)
            # 计算正确率
            correct += (predicted == labels).sum().item() # 张量之间的比较运算
    print('Accuracy on test set: %d %% [%d/%d]' % (100 * correct / total, correct, total))
    return correct / total
'''
5、main
'''
if __name__=='__main__':
    epoch_list = []  # 保存epoch
    acc_list = []  # 保存每个epoch的准确率
    Loss_List = []  # 保存每个epoch对应的loss

    for epoch in range(10):
        loss = train(epoch)
        acc = test()

        epoch_list.append(epoch)
        acc_list.append(acc)
        Loss_List.append(loss)

    plt.plot(epoch_list, Loss_List)
    plt.ylabel('Loss')
    plt.xlabel('Epoch')
    plt.grid(ls='--')  
    plt.show()

    plt.plot(epoch_list, acc_list)
    plt.ylabel('accuracy')
    plt.xlabel('epoch')
    plt.grid(ls='--')  
    plt.show()

网络效果：

在经过10轮的训练之后，Loss和Accuracy图像如下：