【问题标题】:PyTorch Getting Custom Loss Function RunningPyTorch 运行自定义损失函数
【发布时间】:2018-09-24 01:21:14
【问题描述】:

我正在尝试通过扩展 nn.Module 来使用自定义损失函数,但我无法克服错误

变量的元素 0 不需要 grad 并且没有 grad_fn

注意:我的标签是大小为 num_samples 的列表,但每个批次在整个批次中都具有相同的标签,因此我们通过调用 .diag() 将整个批次的标签缩小为单个标签

我的代码如下,基于transfer learning tutorial:

def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
    since = time.time()

    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0

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

        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
            if phase == 'train':
                scheduler.step()
                model.train(True)  # Set model to training mode
            else:
                model.train(False)  # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for data in dataloaders[phase]:
                # get the inputs
                inputs, labels = data
                inputs = inputs.float()


                # wrap them in Variable
                if use_gpu:
                    inputs = Variable(inputs.cuda())
                    labels = Variable(labels.cuda())
                else:
                    inputs = Variable(inputs)
                    labels = Variable(labels)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                outputs = model(inputs)
                #outputs = nn.functional.sigmoid(outputs).round()
                _, preds = torch.max(outputs, 1)
                label = labels.diag().float()
                preds = preds.float()
                loss = criterion(preds, label)
                # backward + optimize only if in training phase
                if phase == 'train':
                    loss.backward()
                    optimizer.step()

                # statistics
                running_loss += loss.data[0] * inputs.size(0)
                running_corrects += torch.sum(pred == label.data)

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects / dataset_sizes[phase]

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

            # deep copy the model
            if phase == 'val' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())

        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))

    # load best model weights
    model.load_state_dict(best_model_wts)
    return model

我的损失函数定义如下:

class CustLoss(nn.Module):
    def __init__(self):
        super(CustLoss, self).__init__()
    def forward(self, outputs, labels):
        return cust_loss(outputs, labels)

def cust_loss(pred, targets):
    '''preds are arrays of size classes with floats in them'''
    '''targets are arrays of all the classes from the batch'''
    '''we sum the classes from the batch and find the num correct'''
    r = torch.sum(pred == targets)
    return r

然后我运行以下命令来运行模型:

model_ft = models.resnet18(pretrained=True)
for param in model_ft.parameters():
    param.requires_grad = False

num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 3)

if use_gpu:
    model_ft = model_ft.cuda()

criterion = CustLoss()

# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(model_ft.fc.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,num_epochs=25)

我尝试让它与其他损失函数一起使用,但无济于事。当loss.backward() 被调用时,我总是得到同样的错误。

我的理解是,如果我扩展 nn.Module,就不需要自定义实现 loss.backward

【问题讨论】:

    标签: python-3.x pytorch loss-function autograd


    【解决方案1】:

    您正在继承 nn.Module 以定义一个函数,在您的情况下为损失函数。因此,当您计算loss.backward() 时,它会尝试将梯度存储在损失本身中,而不是模型中,并且损失中没有用于存储梯度的变量。你的损失需要是一个函数而不是一个模块。见Extending autograd

    这里有两个选择-

    1. 最简单的一种是直接将cust_loss函数作为criterion参数传递给train_model
    2. 您可以扩展 torch.autograd.Function 来定义自定义损失(如果您愿意,还可以使用后向函数)。

    附: - 提到您需要实现自定义损失函数的倒退。这并非总是如此。仅当您的损失函数在某些时候不可微时才需要。但是,我认为您不需要这样做。

    【讨论】:

      猜你喜欢
      • 2019-05-27
      • 2021-11-13
      • 1970-01-01
      • 2020-02-25
      • 2021-02-20
      • 2021-09-26
      • 2021-10-03
      • 2019-04-12
      • 2018-08-04
      相关资源
      最近更新 更多