Function train

main_ce.py:188–237

one epoch training

(train_loader, model, criterion, optimizer, epoch, opt)

def train(train_loader, model, criterion, optimizer, epoch, opt):
    """one epoch training"""
    model.train()

    batch_time = AverageMeter()
    data_time = AverageMeter()
    losses = AverageMeter()
    top1 = AverageMeter()

    end = time.time()
    for idx, (images, labels) in enumerate(train_loader):
        data_time.update(time.time() - end)

        images = images.cuda(non_blocking=True)
        labels = labels.cuda(non_blocking=True)
        bsz = labels.shape[0]

        # warm-up learning rate
        warmup_learning_rate(opt, epoch, idx, len(train_loader), optimizer)

        # compute loss
        output = model(images)
        loss = criterion(output, labels)

        # update metric
        losses.update(loss.item(), bsz)
        acc1, acc5 = accuracy(output, labels, topk=(1, 5))
        top1.update(acc1[0], bsz)

        # SGD
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # measure elapsed time
        batch_time.update(time.time() - end)
        end = time.time()

        # print info
        if (idx + 1) % opt.print_freq == 0:
            print('Train: [{0}][{1}/{2}]\t'
                  'BT {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
                  'DT {data_time.val:.3f} ({data_time.avg:.3f})\t'
                  'loss {loss.val:.3f} ({loss.avg:.3f})\t'
                  'Acc@1 {top1.val:.3f} ({top1.avg:.3f})'.format(
                   epoch, idx + 1, len(train_loader), batch_time=batch_time,
                   data_time=data_time, loss=losses, top1=top1))
            sys.stdout.flush()

    return losses.avg, top1.avg


def validate(val_loader, model, criterion, opt):