Local variable 'loss' referenced before assignment

#1

it gives me this error; local variable ‘loss’ referenced before assignment

def train_epoch(models, loss_module, criterion, optimizers_backbone, optimizers_module, dataloaders, epoch, epoch_loss):

    loss_module.train()
    global iters
    for data in tqdm(dataloaders['train'], leave=False, total=len(dataloaders['train'])):
        with torch.cuda.device(CUDA_VISIBLE_DEVICES):
            inputs = data[0].cuda()
            labels = data[1].cuda()

        iters += 1

        optimizers_backbone.zero_grad()
        optimizers_module.zero_grad()

        scores, _, features = models(inputs) 
        target_loss = criterion(scores, labels)
        
        if epoch > epoch_loss:
            features[0] = features[0].detach()
            features[1] = features[1].detach()
            features[2] = features[2].detach()
            features[3] = features[3].detach()

        pred_loss = loss_module(features)
        pred_loss = pred_loss.view(pred_loss.size(0))
        m_module_loss   = LossPredLoss(pred_loss, target_loss, margin=MARGIN)
        m_backbone_loss = torch.sum(target_loss) / target_loss.size(0)        
        loss = m_backbone_loss + WEIGHT * m_module_loss 
        
        loss.backward()
        optimizers_backbone.step()
        optimizers_module.step()
    
    return loss
#2

Which line occurs the error?
If it is return loss, then check out the for loop iterate at least once.

#3

I don’t think so for-loop is running at least once.

Screenshot from 2022-07-20 17-25-59
Screenshot from 2022-07-20 17-25-591236×236 27.3 KB

#4

It seems dataloaders is invalid.
print len(dataloaders['train']) then it may returns 0

#5

in Train() where I am called train_epoch(), I have printed the data loaders

DataLoader {‘train’: <torch.utils.data.dataloader.DataLoader object at 0x7f4d756dbc10>, ‘test’: <torch.utils.data.dataloader.DataLoader object at 0x7f4d756dbb20>}
DataLoader {‘train’: <torch.utils.data.dataloader.DataLoader object at 0x7f4d756dbc10>, ‘test’: <torch.utils.data.dataloader.DataLoader object at 0x7f4d756dbb20>}

def train(models, loss_module, criterion, optimizers_backbone, optimizers_module, scheduler_backbone, scheduler_module, dataloaders, num_epochs, epoch_loss):
    print('>> Train a Model.')
    best_acc = 0.
    
    for epoch in range(num_epochs):

        best_loss = torch.tensor([0.5]).cuda()
        print("DataLoader", dataloaders)
        
        loss = train_epoch(models, loss_module, criterion, optimizers_backbone, optimizers_module, dataloaders, epoch, epoch_loss)

        scheduler_backbone.step()
        scheduler_module.step()

        if False and epoch % 20  == 7:
            acc = test(models, epoch, method, dataloaders, mode='test')
            # acc = test(models, dataloaders, mc, 'test')
            if best_acc < acc:
                best_acc = acc
                print('Val Acc: {:.3f} \t Best Acc: {:.3f}'.format(acc, best_acc))
    print('>> Finished.')
#6

This code works absolutely fine for CIFAR-100 when I tried this for ImageNet, it started giving this error. and now even not working for CIFAR100