如何在培训UNET模型中处理NotimplemplementError？

Question

def train_fn(data_loader, model, optimizer):

model.train()
total_loss = 0.0

for images, masks in tqdm(data_loader):

  images = images.to(DEVICE)
  masks = masks.to(DEVICE)

  optimizer.zero_grad()
  logits, loss = model(images,masks)
  loss.backward()
  optimizer.step()

  total_loss += loss.item()



return total_loss/ len(data_loader)


def eval_fn(data_loader, model):

model.eval()
total_loss = 0.0

with torch.no_grad():

  for images, masks in tqdm(data_loader):

    images = images.to(DEVICE)
    masks = masks.to(DEVICE)

    logits, loss = model(images,masks)


    total_loss += loss.item()


return total_loss/ len(data_loader)

optimizer = torch.optim.Adam(model.parameters(), lr = LR)

best_valid_loss = np.Inf

for i in range(EPOCHS):


train_loss = train_fn(trainloader, model, optimizer)
valid_loss = eval_fn(validloader, model)

if valid_loss < best_valid_loss:
  torch.save(model.state_dict(), 'best_model.pt')
  print("SAVED_MODEL")
  best_valid_loss = valid_loss

print（f“ epoch：{i+1} train_loss：{train_loss}有效_loss：{有效_loss}”）

当我尝试训练模型时，我会出现以下错误：

0％| | 0/15 [00：00＆lt;？，？it/s]

NotimplemplededError Trackback（最近的最新通话最后） 在 （） 4 5 ----＆gt; 6 train_loss = train_fn（火车负载器，模型，优化器） 7有效_loss = eval_fn（有效载荷，模型） 8

2帧 /USR/local/lib/python3.7/dist-packages/torch/nn/modules/module.py.py in _forward_unimplemented（self， *input） 199个注册钩子，而后者默默地忽略了它们。 200“” - ＆gt; 201＃提高通知 202 203

NotimplementedError：

我该如何处理？

Answer 1

查看您在评论中提供的链接，您的模型定义看起来像这样：

class SegmentationModel(nn.Module):

  def __init__(self):
    super(SegmentationModel,self).__init__()

    self.arc = smp.Unet(
        encoder_name = ENCODER,
        encoder_weights = WEIGHTS,
        in_channels = 3,
        classes = 1,
        activation = None
    )

    def forward(self, images, masks = None):
      logits = self.arc(images)

      if masks != None:
        loss1 = DiceLoss(mode = 'binary')(logits, masks)
        loss2 = nn.BCEWithLogitsLoss()(logits,masks)
        return logits, loss1 + loss2

      return logits

如果您近距离看，您会看到 forward（）具有不稳定的额外凹痕，使其成为内部功能 __ INIT __（）而不是 SemengeationModel 的方法。将其转移到左侧，应该很好地工作：

class SegmentationModel(nn.Module):

  def __init__(self):
    super(SegmentationModel,self).__init__()

    self.arc = smp.Unet(
        encoder_name = ENCODER,
        encoder_weights = WEIGHTS,
        in_channels = 3,
        classes = 1,
        activation = None
    )

  def forward(self, images, masks = None):
    logits = self.arc(images)

    if masks != None:
      loss1 = DiceLoss(mode = 'binary')(logits, masks)
      loss2 = nn.BCEWithLogitsLoss()(logits,masks)
      return logits, loss1 + loss2

    return logits