当前位置: 首页>>代码示例>>Python>>正文


Python core.bbox_mapping_back方法代码示例

本文整理汇总了Python中mmdet.core.bbox_mapping_back方法的典型用法代码示例。如果您正苦于以下问题:Python core.bbox_mapping_back方法的具体用法?Python core.bbox_mapping_back怎么用?Python core.bbox_mapping_back使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在mmdet.core的用法示例。


在下文中一共展示了core.bbox_mapping_back方法的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: merge_aug_results

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox_mapping_back [as 别名]
def merge_aug_results(self, aug_bboxes, aug_scores, img_metas):
        """Merge augmented detection bboxes and scores.

        Args:
            aug_bboxes (list[Tensor]): shape (n, 4*#class)
            aug_scores (list[Tensor] or None): shape (n, #class)
            img_shapes (list[Tensor]): shape (3, ).

        Returns:
            tuple: (bboxes, scores)
        """
        recovered_bboxes = []
        for bboxes, img_info in zip(aug_bboxes, img_metas):
            img_shape = img_info[0]['img_shape']
            scale_factor = img_info[0]['scale_factor']
            flip = img_info[0]['flip']
            bboxes = bbox_mapping_back(bboxes, img_shape, scale_factor, flip)
            recovered_bboxes.append(bboxes)
        bboxes = torch.cat(recovered_bboxes, dim=0)
        if aug_scores is None:
            return bboxes
        else:
            scores = torch.cat(aug_scores, dim=0)
            return bboxes, scores 
开发者ID:microsoft,项目名称:RepPoints,代码行数:26,代码来源:reppoints_detector.py

示例2: merge_aug_results

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox_mapping_back [as 别名]
def merge_aug_results(self, aug_bboxes, aug_scores, img_metas):
        """Merge augmented detection bboxes and scores.

        Args:
            aug_bboxes (list[Tensor]): shape (n, 4*#class)
            aug_scores (list[Tensor] or None): shape (n, #class)
            img_shapes (list[Tensor]): shape (3, ).

        Returns:
            tuple: (bboxes, scores)
        """
        recovered_bboxes = []
        for bboxes, img_info in zip(aug_bboxes, img_metas):
            img_shape = img_info[0]['img_shape']
            scale_factor = img_info[0]['scale_factor']
            flip = img_info[0]['flip']
            flip_direction = img_info[0]['flip_direction']
            bboxes = bbox_mapping_back(bboxes, img_shape, scale_factor, flip,
                                       flip_direction)
            recovered_bboxes.append(bboxes)
        bboxes = torch.cat(recovered_bboxes, dim=0)
        if aug_scores is None:
            return bboxes
        else:
            scores = torch.cat(aug_scores, dim=0)
            return bboxes, scores 
开发者ID:open-mmlab,项目名称:mmdetection,代码行数:28,代码来源:reppoints_detector.py


注:本文中的mmdet.core.bbox_mapping_back方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。