52e09ed9ba6ce987e08334a73a1656792ef7b564,code/deep/DaNN/main.py,,test,#,72

Before Change

    correct = 0
    criterion = nn.CrossEntropyLoss()
    for batch_id, (data, target) in enumerate(data_tar):
        if CUDA:
            model = model.cuda()
            data, target = data.cuda(), target.cuda()
        model.eval()
        data, target = Variable(data.view(-1, 28 * 28), volatile=True), Variable(target)
        ypred, _, _ = model(data, data)
        loss = criterion(ypred, target)

After Change

    total_loss_test = 0
    correct = 0
    criterion = nn.CrossEntropyLoss()
    with torch.no_grad():
        for batch_id, (data, target) in enumerate(data_tar):
            data, target = data.view(-1,28 * 28).to(DEVICE),target.to(DEVICE)
            model.eval()
            ypred, _, _ = model(data, data)
            loss = criterion(ypred, target)
            pred = ypred.data.max(1)[1]  // get the index of the max log-probability
            correct += pred.eq(target.data.view_as(pred)).cpu().sum()
            total_loss_test += loss.data
        accuracy = correct * 100. / len(data_tar.dataset)
        res = "Test: total loss: {:.6f}, correct: [{}/{}], testing accuracy: {:.4f}%".format(
            total_loss_test, correct, len(data_tar.dataset), accuracy
        )
    tqdm.write(res)
    RESULT_TEST.append([e, total_loss_test, accuracy])
    log_test.write(res + "\n")

Instances