How can I print out dice_coef or define other metric in the code?

1

I am using the following code and I got the iou_score, but I want to evaluate it by:

Precision & Recall

image
such as this one:

FP, FN, TP, TN = numeric_score(prediction, groundtruth)
N = FP + FN + TP + TN
accuracy = np.divide(TP + TN, N)
return accuracy * 100.0`

how can I add them in , or just print the Dice?

def iou_score(output, target):
    smooth = 1e-5

    if torch.is_tensor(output):
        output = torch.sigmoid(output).data.cpu().numpy()
    if torch.is_tensor(target):
        target = target.data.cpu().numpy()
    output_ = output > 0.5
    target_ = target > 0.5
    intersection = (output_ & target_).sum()
    union = (output_ | target_).sum()

    return (intersection + smooth) / (union + smooth)


def dice_coef(output, target):
    smooth = 1e-5

    output = torch.sigmoid(output).view(-1).data.cpu().numpy()
    target = target.view(-1).data.cpu().numpy()
    intersection = (output * target).sum()

    return (2. * intersection + smooth) / \
        (output.sum() + target.sum() + smooth)


 iou = iou_score(output, target)
            avg_meter.update(iou, input.size(0))

            output = torch.sigmoid(output).cpu().numpy()

            for i in range(len(output)):
                for c in range(config['num_classes']):
                    cv2.imwrite(os.path.join('outputs', config['name'], str(c), meta['img_id'][i] + '.jpg'),
                                (output[i, c] * 255).astype('uint8'))

    print('IoU: %.4f' % avg_meter.avg)

    torch.cuda.empty_cache()

https://github.com/4uiiurz1/pytorch-nested-unet
With reagrds, any help would be so grateful!