其他分享
首页 > 其他分享> > pytorch学习第三章——卷积神经网络图像识别

pytorch学习第三章——卷积神经网络图像识别

作者:互联网

卷积神经网络学习手写数字

# 定义超参数 
input_size = 28  #图像的总尺寸28*28
num_classes = 10  #标签的种类数
num_epochs = 3  #训练的总循环周期
batch_size = 64  #一个撮(批次)的大小,64张图片

# 训练集
train_dataset = datasets.MNIST(root='./data',  
                            train=True,   
                            transform=transforms.ToTensor(),  
                            download=True) 

# 测试集
test_dataset = datasets.MNIST(root='./data', 
                           train=False, 
                           transform=transforms.ToTensor())

# 构建batch数据
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, 
                                           batch_size=batch_size, 
                                           shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, 
                                           batch_size=batch_size, 
                                           shuffle=True)

定义模型

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(         # 输入大小 (1, 28, 28)
            nn.Conv2d(
                in_channels=1,              # 灰度图
                out_channels=16,            # 要得到几多少个特征图
                kernel_size=5,              # 卷积核大小
                stride=1,                   # 步长
                padding=2,                  # 如果希望卷积后大小跟原来一样,需要设置padding=(kernel_size-1)/2 if stride=1
            ),                              # 输出的特征图为 (16, 28, 28)
            nn.ReLU(),                      # relu层
            nn.MaxPool2d(kernel_size=2),    # 进行池化操作(2x2 区域), 输出结果为: (16, 14, 14)
        )
        self.conv2 = nn.Sequential(         # 下一个套餐的输入 (16, 14, 14)
            nn.Conv2d(16, 32, 5, 1, 2),     # 输出 (32, 14, 14)
            nn.ReLU(),                      # relu层
            nn.MaxPool2d(2),                # 输出 (32, 7, 7)
        )
        self.out = nn.Linear(32 * 7 * 7, 10)   # 全连接层得到的结果

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)           # flatten操作,结果为:(batch_size, 32 * 7 * 7)
        output = self.out(x)
        return output

训练过程

# 实例化
net = CNN() 
#损失函数
criterion = nn.CrossEntropyLoss() 
#优化器
optimizer = optim.Adam(net.parameters(), lr=0.001) #定义优化器,普通的随机梯度下降算法

#开始训练循环
for epoch in range(num_epochs):
    #当前epoch的结果保存下来
    train_rights = [] 
    
    for batch_idx, (data, target) in enumerate(train_loader):  #针对容器中的每一个批进行循环
        net.train()                             
        output = net(data) 
        loss = criterion(output, target) 
        optimizer.zero_grad() 
        loss.backward() 
        optimizer.step() 
        right = accuracy(output, target) 
        train_rights.append(right) 

    
        if batch_idx % 100 == 0: 
            
            net.eval() 
            val_rights = [] 
            
            for (data, target) in test_loader:
                output = net(data) 
                right = accuracy(output, target) 
                val_rights.append(right)
                
            #准确率计算
            train_r = (sum([tup[0] for tup in train_rights]), sum([tup[1] for tup in train_rights]))
            val_r = (sum([tup[0] for tup in val_rights]), sum([tup[1] for tup in val_rights]))

            print('当前epoch: {} [{}/{} ({:.0f}%)]\t损失: {:.6f}\t训练集准确率: {:.2f}%\t测试集正确率: {:.2f}%'.format(
                epoch, batch_idx * batch_size, len(train_loader.dataset),
                100. * batch_idx / len(train_loader), 
                loss.data, 
                100. * train_r[0].numpy() / train_r[1], 
                100. * val_r[0].numpy() / val_r[1]))

迁移学习

数据预处理

data_transforms = {
    'train': transforms.Compose([transforms.RandomRotation(45),#随机旋转,-45到45度之间随机选
        transforms.CenterCrop(224),#从中心开始裁剪
        transforms.RandomHorizontalFlip(p=0.5),#随机水平翻转 选择一个概率概率
        transforms.RandomVerticalFlip(p=0.5),#随机垂直翻转
        transforms.ColorJitter(brightness=0.2, contrast=0.1, saturation=0.1, hue=0.1),#参数1为亮度,参数2为对比度,参数3为饱和度,参数4为色相
        transforms.RandomGrayscale(p=0.025),#概率转换成灰度率,3通道就是R=G=B
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])#均值,标准差
    ]),
    'valid': transforms.Compose([transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

ImageFolder假设所有的文件按文件夹保存好,每个文件夹下面存贮同一类别的图片,文件夹的名字为分类的名字

batch_size = 8

image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'valid']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, shuffle=True) for x in ['train', 'valid']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'valid']}
class_names = image_datasets['train'].classes

迁移学习模型初始化

def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True):
    # 选择合适的模型,不同模型的初始化方法稍微有点区别
    model_ft = None
    input_size = 0

    if model_name == "resnet":
        """ Resnet152
        """
        model_ft = models.resnet152(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        num_ftrs = model_ft.fc.in_features
        model_ft.fc = nn.Sequential(nn.Linear(num_ftrs, 102),
                                   nn.LogSoftmax(dim=1))
        input_size = 224

    elif model_name == "alexnet":
        """ Alexnet
        """
        model_ft = models.alexnet(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        num_ftrs = model_ft.classifier[6].in_features
        model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
        input_size = 224

    elif model_name == "vgg":
        """ VGG11_bn
        """
        model_ft = models.vgg16(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        num_ftrs = model_ft.classifier[6].in_features
        model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
        input_size = 224

    elif model_name == "squeezenet":
        """ Squeezenet
        """
        model_ft = models.squeezenet1_0(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        model_ft.classifier[1] = nn.Conv2d(512, num_classes, kernel_size=(1,1), stride=(1,1))
        model_ft.num_classes = num_classes
        input_size = 224

    elif model_name == "densenet":
        """ Densenet
        """
        model_ft = models.densenet121(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        num_ftrs = model_ft.classifier.in_features
        model_ft.classifier = nn.Linear(num_ftrs, num_classes)
        input_size = 224

    elif model_name == "inception":
        """ Inception v3
        Be careful, expects (299,299) sized images and has auxiliary output
        """
        model_ft = models.inception_v3(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        # Handle the auxilary net
        num_ftrs = model_ft.AuxLogits.fc.in_features
        model_ft.AuxLogits.fc = nn.Linear(num_ftrs, num_classes)
        # Handle the primary net
        num_ftrs = model_ft.fc.in_features
        model_ft.fc = nn.Linear(num_ftrs,num_classes)
        input_size = 299

    else:
        print("Invalid model name, exiting...")
        exit()

    return model_ft, input_size

训练过程

def train_model(model, dataloaders, criterion, optimizer, num_epochs=25, is_inception=False,filename=filename):
    since = time.time()
    best_acc = 0
    """
    checkpoint = torch.load(filename)
    best_acc = checkpoint['best_acc']
    model.load_state_dict(checkpoint['state_dict'])
    optimizer.load_state_dict(checkpoint['optimizer'])
    model.class_to_idx = checkpoint['mapping']
    """
    model.to(device)

    val_acc_history = []
    train_acc_history = []
    train_losses = []
    valid_losses = []
    LRs = [optimizer.param_groups[0]['lr']]

    best_model_wts = copy.deepcopy(model.state_dict())

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # 训练和验证
        for phase in ['train', 'valid']:
            if phase == 'train':
                model.train()  # 训练
            else:
                model.eval()   # 验证

            running_loss = 0.0
            running_corrects = 0

            # 把数据都取个遍
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # 清零
                optimizer.zero_grad()
                # 只有训练的时候计算和更新梯度
                with torch.set_grad_enabled(phase == 'train'):
                    if is_inception and phase == 'train':
                        outputs, aux_outputs = model(inputs)
                        loss1 = criterion(outputs, labels)
                        loss2 = criterion(aux_outputs, labels)
                        loss = loss1 + 0.4*loss2
                    else:#resnet执行的是这里
                        outputs = model(inputs)
                        loss = criterion(outputs, labels)

                    _, preds = torch.max(outputs, 1)

                    # 训练阶段更新权重
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # 计算损失
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)

            epoch_loss = running_loss / len(dataloaders[phase].dataset)
            epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)
            
            
            time_elapsed = time.time() - since
            print('Time elapsed {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
            

            # 得到最好那次的模型
            if phase == 'valid' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())
                state = {
                  'state_dict': model.state_dict(),
                  'best_acc': best_acc,
                  'optimizer' : optimizer.state_dict(),
                }
                torch.save(state, filename)
            if phase == 'valid':
                val_acc_history.append(epoch_acc)
                valid_losses.append(epoch_loss)
                scheduler.step(epoch_loss)
            if phase == 'train':
                train_acc_history.append(epoch_acc)
                train_losses.append(epoch_loss)
        
        print('Optimizer learning rate : {:.7f}'.format(optimizer.param_groups[0]['lr']))
        LRs.append(optimizer.param_groups[0]['lr'])
        print()

    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
    print('Best val Acc: {:4f}'.format(best_acc))

    # 训练完后用最好的一次当做模型最终的结果
    model.load_state_dict(best_model_wts)
    return model, val_acc_history, train_acc_history, valid_losses, train_losses, LRs 

标签:acc,ft,卷积,num,pytorch,train,图像识别,model,size
来源: https://blog.csdn.net/csdn_ggboy/article/details/122536762