def evaluate()

in ViT4MNIST/mnist_vit.py [0:0]

• 18 lines of code
• 2 McCabe index (conditional complexity)

def evaluate(model, data_loader, loss_history):
    model.eval()

    total_samples = len(data_loader.dataset)
    correct_samples = 0
    total_loss = 0

    with torch.no_grad():
        for data, target in data_loader:
            output = F.log_softmax(model(data), dim=1)
            loss = F.nll_loss(output, target, reduction='sum')
            _, pred = torch.max(output, dim=1)

            total_loss += loss.item()
            correct_samples += pred.eq(target).sum()

    avg_loss = total_loss / total_samples
    loss_history.append(avg_loss)
    print('\nAverage test loss: ' + '{:.4f}'.format(avg_loss) +
          '  Accuracy:' + '{:5}'.format(correct_samples) + '/' +
          '{:5}'.format(total_samples) + ' (' +
          '{:4.2f}'.format(100.0 * correct_samples / total_samples) + '%)\n')