GIoU

最新推荐文章于 2023-11-29 10:50:55 发布

sunny冰青

最新推荐文章于 2023-11-29 10:50:55 发布

阅读量236

点赞数

分类专栏：算法

本文链接：https://blog.csdn.net/u012751110/article/details/103600852

版权

本文深入探讨GIoU损失函数，包括其定义、参数作用，如原始损失、权重系数和贡献比例调节等。

摘要由CSDN通过智能技术生成

    def bbox_giou(self, boxes1, boxes2):

        boxes1 = tf.concat([boxes1[..., :2] - boxes1[..., 2:] * 0.5,
                            boxes1[..., :2] + boxes1[..., 2:] * 0.5], axis=-1)
        boxes2 = tf.concat([boxes2[..., :2] - boxes2[..., 2:] * 0.5,
                            boxes2[..., :2] + boxes2[..., 2:] * 0.5], axis=-1)

        boxes1 = tf.concat([tf.minimum(boxes1[..., :2], boxes1[..., 2:]),
                            tf.maximum(boxes1[..., :2], boxes1[..., 2:])], axis=-1)
        boxes2 = tf.concat([tf.minimum(boxes2[..., :2], boxes2[..., 2:]),
                            tf.maximum(boxes2[..., :2], boxes2[..., 2:])], axis=-1)

        boxes1_area = (boxes1[..., 2] - boxes1[..., 0]) * (boxes1[..., 3] - boxes1[..., 1])
        boxes2_area = (boxes2[..., 2] - boxes2[..., 0]) * (boxes2[..., 3] - boxes2[..., 1])

        left_up = tf.maximum(boxes1[..., :2], boxes2[..., :2])
        right_down &#