Question

我正在尝试使用AlexNet模型训练数据集。任务是多类分类（15个类）。我想知道为什么我的准确性很低。我尝试了不同的学习率，但并没有提高。

这是培训的摘录。

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=1e-3, momentum=0.9)  
#optimizer = optim.Adam(model.parameters(), lr=1e-2)  # 1e-3, 1e-8

def train_valid_model():

  num_epochs=5

since = time.time()
out_loss = open("history_loss_AlexNet_exp1.txt", "w")
out_acc = open("history_acc_AlexNet_exp1.txt", "w")

losses=[]
ACCes =[]
#losses = {}

for epoch in range(num_epochs):  # loop over the dataset multiple times
    print('Epoch {}/{}'.format(epoch, num_epochs - 1))
    print('-' * 50)        

    if epoch % 10 == 9:
       torch.save({
        'epoch': epoch + 1,
        'model_state_dict': model.state_dict(),
        'optimizer_state_dict': optimizer.state_dict(),
         'loss': loss
        }, 'AlexNet_exp1_epoch{}.pth'.format(epoch+1))

    for phase in ['train', 'valid', 'test']:
        if phase == 'train':

            model.train()  
        else:
            model.eval()   

        train_loss = 0.0
        total_train = 0
        correct_train = 0

        for t_image, target, image_path in dataLoaders[phase]:
            #print(t_image.size())
            #print(target)

            t_image = t_image.to(device)
            target = target.to(device)

            optimizer.zero_grad()

            with torch.set_grad_enabled(phase == 'train'):
                outputs = model(t_image) 
                outputs = F.softmax(outputs, dim=1)


                loss = criterion(outputs,target)         
                if phase == 'train':
                    loss.backward() 
                    optimizer.step()                           

            _, predicted = torch.max(outputs.data, 1)
            train_loss += loss.item()* t_image.size(0)
            correct_train += (predicted == target).sum().item()

        epoch_loss = train_loss / len(dataLoaders[phase].dataset)
        #losses[phase] = epoch_loss
        losses.append(epoch_loss)

        epoch_acc = 100 * correct_train / len(dataLoaders[phase].dataset) 
        ACCes.append(epoch_acc)

        print('{} Loss: {:.4f} {} Acc: {:.4f}'.format(phase, epoch_loss, phase, epoch_acc))

这是两个纪元的输出

时代0/4

火车损失：2.7026火车Acc：17.2509 有效损失：2.6936有效累积：28.7632 测试损失：2.6936测试帐户：28.7632

史诗1/4

火车损失：2.6425火车Acc：17.8019 有效损失：2.6357有效累积：28.7632 测试损失：2.6355测试帐户：28.7632

Answer 1

只是一个基本提示，它可能会帮助您入门，

import torchvision.models as models
alexnet = models.alexnet(pretrained=True)

使用alexnet时，您可以从预先训练的模型开始，我在您的代码中没有看到。如果只需要15个类，请确保在最后删除完全连接的层，并添加具有15个输出的新fc层，

您的alexnet看起来像这样：

AlexNet(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
    (1): ReLU(inplace)
    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (4): ReLU(inplace)
    (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU(inplace)
    (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (9): ReLU(inplace)
    (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace)
    (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(6, 6))
  (classifier): Sequential(
    (0): Dropout(p=0.5)
    (1): Linear(in_features=9216, out_features=4096, bias=True)
    (2): ReLU(inplace)
    (3): Dropout(p=0.5)
    (4): Linear(in_features=4096, out_features=4096, bias=True)
    (5): ReLU(inplace)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)

因此，您仅需要删除分类器（6）层。我认为here回答了如何删除fc6。

对于多标签分类，模型的最后一层应使用S型函数进行标签预测，而训练过程应使用binary_crossentropy函数或nn.BCELoss。

怪异的结果是训练AlexNet

时代0/4

史诗1/4

1 个答案: