[英]is there any other good metrics for segmentation task in deep learning apart from IOU?
I would like to ask if there are other good metrics for segmentation tasks in deep learning except for IOU (intersection over union)?请问深度学习中除了IOU(intersection over union)还有其他好的分割任务指标吗?
Because some times i got NaN results from IOU, Just wondering maybe there are some other metrics that can help to observe the performance of the model.因为有时我从 IOU 得到 NaN 结果,只是想知道也许还有其他一些指标可以帮助观察模型的性能。
def IoU(
targets: np.array,
outputs: np.array,
) -> np.array:
intersection = np.sum(
outputs * targets,
axis=(0, 1)
)
union = np.sum(
outputs + targets,
axis=(0, 1)
) - intersection
return np.mean(intersection / union)
Try this method for IOU试试这个方法的借据
intersection = np.logical_and(target, prediction)
union = np.logical_or(target, prediction)
iou_score = np.sum(intersection) / np.sum(union)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.