PyTorch 模型未收敛

Question

我正在对一系列图像训练二元分类模型。 该模型源自torchvision中的resnet18，我将最后一个FC设为nn.Linear(512, 1)

损失函数为BCELoss

但是，即使经过 5000 次迭代，该模型也没有显示出任何收敛迹象。

我怀疑我可能在训练阶段做错了什么？但我找不到错误在哪里。

这是我的代码：

型号：

## Model
import torch.nn as nn
import torch.nn.functional as F
import torchvision.models as models

resnet18 = models.resnet18(pretrained= True)
resnet18.fc = nn.Linear(512, 1)

参数、损失、优化器：

## parameter
epochs = 200
learning_rate = 0.1
momen = 0.9
batch = 8
criterion = nn.BCELoss()
resnet18.to(device)
opt = optim.SGD(resnet18.parameters(), lr = learning_rate, momentum = momen)

数据加载器：

# Generators
training_set = Dataset(X_train)
training_generator = torch.utils.data.DataLoader(training_set, batch_size= batch, shuffle=True)

validation_set = Dataset(X_test)
validation_generator = torch.utils.data.DataLoader(validation_set, batch_size=1, shuffle=False)

培训：

# training
history = []
for t in range(epochs):  
  for i, data in enumerate(training_generator, 0):

    inputs, labels = data
    # check if input size == batch size #
    if inputs.shape[0] < batch:
      break

#    print("labels", labels, labels.dtype)

    # move data to GPU #
    inputs, labels = inputs.to(device), labels.to(device)

    opt.zero_grad()
    # Prediction #
    y_pred = resnet18(inputs).view(batch,)
    y_pred = (y_pred > 0).float().requires_grad_()
#    print("y_pred", y_pred, y_pred.dtype)

    # Calculating loss #
    loss = criterion(y_pred, labels.view(batch,))
    loss.backward()
    opt.step()
    
    if i % 10 == 0:
      history.append(loss.item())
      print("Epoch: {}, iter: {}, loss: {}".format(t, i, loss.item())


torch.save(resnet18, 'trained_resnet18.pt')

编辑：

损失值是这样的：

Epoch: 3, iter: 310, loss: 0.0
Epoch: 3, iter: 320, loss: 37.5
Epoch: 3, iter: 330, loss: 37.5
Epoch: 3, iter: 340, loss: 0.0
Epoch: 3, iter: 350, loss: 37.5
Epoch: 3, iter: 360, loss: 50.0
Epoch: 3, iter: 370, loss: 37.5
Epoch: 3, iter: 380, loss: 25.0
Epoch: 3, iter: 390, loss: 12.5

Answer 1

我相信错误在于以下行：

y_pred = (y_pred > 0).float().requires_grad_()

您尝试以一种奇怪的方式对模型预测进行二值化，我建议改为：

y_pred = torch.sigmoid(y_pred)

并将其传递给损失函数。

说明

模型的输出可以是任何值，但我们希望将这些值归一化以驻留在[0,1] 范围内。这正是 sigmoid 函数所做的。一旦我们得到[0,1] 范围内的值，与二进制标签的比较就会有意义，更接近 1 将是“1”，反之亦然。

您可以参考以下链接：https://www.youtube.com/watch?v=WsFasV46KgQ