深度学习之PyTorch —— CNN实现MNIST手写数字分类

#　运用ＣＮＮ分析ＭＮＩＳＴ手写数字分类

import torch 
import numpy as np
from torch.utils.data import DataLoader
from torchvision.datasets import mnist
from torch import  nn
from torch.autograd import Variable
from torch import  optim
from torchvision import transforms

# 定义CNN
class CNN(nn.Module):
    def __init__(self):
        super(CNN,self).__init__()
        
        self.layer1 = nn.Sequential(
                nn.Conv2d(1,16,kernel_size=3), # 16, 26 ,26
                nn.BatchNorm2d(16),
                nn.ReLU(inplace=True))
        
        self.layer2 = nn.Sequential(
                nn.Conv2d(16,32,kernel_size=3),# 32, 24, 24
                nn.BatchNorm2d(32),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=2,stride=2)) # 32, 12,12     (24-2) /2 +1
        
        self.layer3 = nn.Sequential(
                nn.Conv2d(32,64,kernel_size=3), # 64,10,10
                nn.BatchNorm2d(64),
                nn.ReLU(inplace=True))
        
        self.layer4 = nn.Sequential(
                nn.Conv2d(64,128,kernel_size=3),  # 128,8,8
                nn.BatchNorm2d(128),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=2,stride=2))  # 128, 4,4
        
        self.fc = nn.Sequential(
                nn.Linear(128 * 4 * 4,1024),
                nn.ReLU(inplace=True),
                nn.Linear(1024,128),
                nn.ReLU(inplace=True),
                nn.Linear(128,10))
        
    def forward(self,x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = x.view(x.size(0),-1)
        x = self.fc(x)
        
        return x


# 使用内置函数下载mnist数据集
train_set = mnist.MNIST('./data',train=True)
test_set = mnist.MNIST('./data',train=False)

# 预处理=>将各种预处理组合在一起
data_tf = transforms.Compose(
                [transforms.ToTensor(),
                 transforms.Normalize([0.5],[0.5])])

train_set = mnist.MNIST('./data',train=True,transform=data_tf,download=True)
test_set = mnist.MNIST('./data',train=False,transform=data_tf,download=True)

train_data = DataLoader(train_set,batch_size=64,shuffle=True)
test_data = DataLoader(test_set,batch_size=128,shuffle=False)

net = CNN()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(),1e-1)

nums_epoch = 20

# 开始训练
losses =[]
acces = []
eval_losses = []
eval_acces = []

for epoch in range(nums_epoch):
    train_loss = 0
    train_acc = 0
    net = net.train()
    for img , label in train_data:
        #img = img.reshape(img.size(0),-1) 
        img = Variable(img)
        label = Variable(label)
        
        # 前向传播
        out = net(img)
        loss = criterion(out,label)
        # 反向传播
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        # 记录误差
        train_loss += loss.item()
        # 计算分类的准确率
        _,pred = out.max(1)
        num_correct = (pred == label).sum().item()
        acc = num_correct / img.shape[0]
       
        train_acc += acc
        
    losses.append(train_loss / len(train_data))
    acces.append(train_acc / len(train_data))
    
    eval_loss = 0
    eval_acc = 0
    # 测试集不训练
    for img , label in test_data:
        #img = img.reshape(img.size(0),-1)
        img = Variable(img)
        label = Variable(label)
        
        out = net(img)
        
        loss = criterion(out,label)
        
        # 记录误差
        eval_loss += loss.item()
        
        _ , pred = out.max(1)
        num_correct = (pred==label).sum().item()
        acc = num_correct / img.shape[0]
        
        eval_acc += acc
    eval_losses.append(eval_loss / len(test_data))
    eval_acces.append(eval_acc / len(test_data))
    
    print('Epoch {} Train Loss {} Train  Accuracy {} Teat Loss {} Test Accuracy {}'.format(
        epoch+1, train_loss / len(train_data),train_acc / len(train_data), eval_loss / len(test_data), eval_acc / len(test_data)))

输出：

Epoch 1 Train Loss 0.14103838276348388 Train  Accuracy 0.9574893390191898 Teat Loss 0.03636252877738657 Test Accuracy 0.9888251582278481
Epoch 2 Train Loss 0.03642434606165774 Train  Accuracy 0.9888059701492538 Teat Loss 0.0744408220288497 Test Accuracy 0.9761669303797469
Epoch 3 Train Loss 0.025223525594483053 Train  Accuracy 0.9920542377398721 Teat Loss 0.02412710657131068 Test Accuracy 0.9920886075949367
Epoch 4 Train Loss 0.020014993536637535 Train  Accuracy 0.9937533315565032 Teat Loss 0.022930343906524816 Test Accuracy 0.9923852848101266
Epoch 5 Train Loss 0.015570432650668027 Train  Accuracy 0.9948694029850746 Teat Loss 0.019973596770174896 Test Accuracy 0.992879746835443
Epoch 6 Train Loss 0.011754893727584688 Train  Accuracy 0.99605210554371 Teat Loss 0.01934802131373671 Test Accuracy 0.9936708860759493

因个人用CPU运算速度问题，这次仅训练六次。相比上篇博客，比只简单用全连接神经网路准确率要高，达到99%。

有什么问题欢迎评论。

深度学习之PyTorch —— CNN实现MNIST手写数字分类

猜你喜欢