4441480fde64e42a9c4af205bf2ab8003511172e,test.py,,NN,#Any#Any#Any#Any#Any#Any#,9

Before Change

        trainloader.dataset.transform = transform_bak
    
    end = time.time()
    for batch_idx, (inputs, targets, indexes) in enumerate(testloader):
        inputs, targets = inputs.cuda(), targets.cuda()
        inputs, targets = Variable(inputs, volatile=True), Variable(targets)
        batchSize = inputs.size(0)
        features = net(inputs)
        net_time.update(time.time() - end)
        end = time.time()

        dist = torch.mm(features.data, trainFeatures)

        yd, yi = dist.topk(1, dim=1, largest=True, sorted=True)
        candidates = trainLabels.view(1,-1).expand(batchSize, -1)
        retrieval = torch.gather(candidates, 1, yi)

        retrieval = retrieval.narrow(1, 0, 1).clone().view(-1)
        yd = yd.narrow(1, 0, 1)

        total += targets.size(0)
        correct += retrieval.eq(targets.data).cpu().sum()
        
        cls_time.update(time.time() - end)
        end = time.time()

        print("Test [{}/{}]\t"
              "Net Time {net_time.val:.3f} ({net_time.avg:.3f})\t"
              "Cls Time {cls_time.val:.3f} ({cls_time.avg:.3f})\t"
              "Top1: {:.2f}".format(
              total, testsize, correct*100./total, net_time=net_time, cls_time=cls_time))

    return correct/total

def kNN(epoch, net, lemniscate, trainloader, testloader, K, sigma, recompute_memory=0):
    net.eval()

After Change

        trainloader.dataset.transform = transform_bak
    
    end = time.time()
    with torch.no_grad():
        for batch_idx, (inputs, targets, indexes) in enumerate(testloader):
            inputs, targets = inputs.to(device), targets.to(device)
            batchSize = inputs.size(0)
            features = net(inputs)
            net_time.update(time.time() - end)
            end = time.time()

            dist = torch.mm(features, trainFeatures)

            yd, yi = dist.topk(1, dim=1, largest=True, sorted=True)
            candidates = trainLabels.view(1,-1).expand(batchSize, -1)
            retrieval = torch.gather(candidates, 1, yi)

            retrieval = retrieval.narrow(1, 0, 1).clone().view(-1)
            yd = yd.narrow(1, 0, 1)

            total += targets.size(0)
            correct += retrieval.eq(targets.data).cpu().sum().item()
            
            cls_time.update(time.time() - end)
            end = time.time()

            print("Test [{}/{}]\t"
                  "Net Time {net_time.val:.3f} ({net_time.avg:.3f})\t"
                  "Cls Time {cls_time.val:.3f} ({cls_time.avg:.3f})\t"
                  "Top1: {:.2f}".format(
                  total, testsize, correct*100./total, net_time=net_time, cls_time=cls_time))

    return correct/total

def kNN(epoch, net, lemniscate, trainloader, testloader, K, sigma, recompute_memory=0):
    device = "cuda" if torch.cuda.is_available() else "cpu"

Instances