'Tensor' object has no attribute 'meter'

1

When I use meter.AverageValueMeter() times wrong,
My code looks like this:

    loss_meter = meter.AverageValueMeter()
    previous_loss = 1e10
    # train
    for epoch in range(opt.max_epoch):
        
        loss_meter.reset()
        # confusion_matrix.reset()

        for ii,(data,label) in tqdm(enumerate(train_dataloader),total=len(train_data)):

            # train model 
            input = Variable(data)
            input = input.float()
            target = Variable(label)
            if opt.use_gpu:
                input = input.cuda()
                target = target.cuda()

            optimizer.zero_grad()
            score = model(input)
            loss = criterion(score,target) / (128 * 128)
            loss.backward()
            optimizer.step()  

  
            loss.meter.add(loss.item())
2

Hi,
Actually, I don’t know what meter is here but don’t you have typo?

You defined loss_meter but you are calling loss.meter. loss is a tensor and it does not have meter.

So, I think last line should be loss_meter.meter.add(loss.item())

Bests

3

thank you,i did typo . :sweat_smile:
the code should be loss_meter.add(loss.item) :sweat_smile: