Always get the correct 0.

[sxzy]

HI I have tried to implement your code in my experiment on UCF101.
but I did't get any improvement and always get the zero correct.
It is a little strange.
my code
``
def train_1epoch(self):
print('==> Epoch:[{0}/{1}][training stage]'.format(self.epoch, self.nb_epochs))
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
top1 = AverageMeter()
top5 = AverageMeter() #switch to train mode
self.model.train()
end = time.time()
train_loss = AverageMeter()
total = 0
correct = 0
# mini-batch training
progress = tqdm(self.train_loader)
for i, (data_dict,label) in enumerate(progress):

       # measure data loading time
        data_time.update(time.time() - end)
       # generate mixed inputs, two one-hot label vectors and mixing coefficient 
        # transfer the label into one-hot Encoder

        # label = torch.zeros(label.shape[0], 101).scatter_(1, label.reshape(-1, 1), 1).cuda()
        # print(label.shape[0])
        label = label.cuda()
        # compute output
        output = Variable(torch.zeros(len(data_dict['img1']),101).float()).cuda()
        # print(len(data_dict['img1'])

        for i in range(len(data_dict)):
            key = 'img'+str(i)
            input_var = (data_dict[key]).cuda()
            # generate mixed inputs, two one-hot label vectors and mixing coefficient 
            input_var, label_a, label_b, lam = mixup_data(input_var, label, args.alpha, True)
            input_var, label_a, label_b = Variable(input_var), Variable(label_a), Variable(label_b)
            output += self.model(input_var)

        criterion = self.criterion
        loss = mixup_criterion(criterion, output, label_a, label_b, lam)
        # print(label_a.argmax(dim=1).data,label_b.argmax(dim=1).data)
        # loss = loss_func(criterion, output)
        # print(args.alpha, lam)
        # compute gradient and do SGD step
        self.optimizer.zero_grad()
        loss.backward()
        self.optimizer.step()

        # measure accuracy and record loss
        # train_loss += loss.data[0]
        train_loss.update(loss.data[0], data_dict[key].size(0))
        # print(loss.data[0])
        _, predicted = torch.max(output.data, 1)
        total += label.size(0)
        # print(label.size(0))
        correct += lam * predicted.eq(label_a.data).cpu().sum() + (1 - lam) * predicted.eq(label_b.data).cpu().sum()
        # print(predicted.eq(label_a.argmax(dim=1).data).cpu().sum())
        # print(label_a.data)
        # measure elapsed time
        batch_time.update(time.time() - end)
        end = time.time()
    
    info = {'Epoch':[self.epoch],
            'Batch Time':[round(batch_time.avg,3)],
            'Data Time':[round(data_time.avg,3)],
            'Loss':[round(train_loss.avg,5)],
            'correct':[round(correct,4)],
            'Prec@1':[round(correct/total,4)],
            'Prec@5':[round(correct/total,4)],
            'lr': self.optimizer.param_groups[0]['lr'],
	        'weight-decay': args.decay
            }
    record_info(info, 'record/spatial/rgb_train.csv','train')

``
I did't know where is wrong....

[staceycy]

@sxzy I met the same problem.

I changed the line:
'correct += lam * predicted.eq(label_a.data).cpu().sum() + (1 - lam) * predicted.eq(label_b.data).cpu().sum()'
to:
'correct += lam * predicted.eq(targets_a.data).cpu().sum().item() + (1 - lam) * predicted.eq(targets_b.data).cpu().sum().item()'.

Then the accuracy becomes normal.
However, i don't know about the reason since I am new to Pytorch,

[sxzy]

@sxzy I met the same problem.

I changed the line:
'correct += lam * predicted.eq(label_a.data).cpu().sum() + (1 - lam) * predicted.eq(label_b.data).cpu().sum()'
to:
'correct += lam * predicted.eq(targets_a.data).cpu().sum().item() + (1 - lam) * predicted.eq(targets_b.data).cpu().sum().item()'.

Then the accuracy becomes normal.
However, i don't know about the reason since I am new to Pytorch,
Ok. I see . I will try your method later.
Thank you!