Python core.bbox2result方法代码示例

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def async_simple_test(self,
                                x,
                                proposal_list,
                                img_metas,
                                proposals=None,
                                rescale=False):
        """Async test without augmentation."""
        assert self.with_bbox, 'Bbox head must be implemented.'

        det_bboxes, det_labels = await self.async_test_bboxes(
            x, img_metas, proposal_list, self.test_cfg, rescale=rescale)
        bbox_results = bbox2result(det_bboxes, det_labels,
                                   self.bbox_head.num_classes)
        if not self.with_mask:
            return bbox_results
        else:
            segm_results = await self.async_test_mask(
                x,
                img_metas,
                det_bboxes,
                det_labels,
                rescale=rescale,
                mask_test_cfg=self.test_cfg.get('mask'))
            return bbox_results, segm_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def simple_test(self,
                    x,
                    proposal_list,
                    img_metas,
                    proposals=None,
                    rescale=False):
        """Test without augmentation."""
        assert self.with_bbox, 'Bbox head must be implemented.'

        det_bboxes, det_labels = self.simple_test_bboxes(
            x, img_metas, proposal_list, self.test_cfg, rescale=rescale)
        bbox_results = bbox2result(det_bboxes, det_labels,
                                   self.bbox_head.num_classes)

        if not self.with_mask:
            return bbox_results
        else:
            segm_results = self.simple_test_mask(
                x, img_metas, det_bboxes, det_labels, rescale=rescale)
            return bbox_results, segm_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def simple_test(self, img, img_meta, proposals=None, rescale=False):
        """Test without augmentation."""
        assert self.with_bbox, "Bbox head must be implemented."

        x = self.extract_feat(img)

        proposal_list = self.simple_test_rpn(
            x, img_meta, self.test_cfg.rpn) if proposals is None else proposals

        det_bboxes, det_labels = self.simple_test_bboxes(
            x, img_meta, proposal_list, self.test_cfg.rcnn, rescale=rescale)
        bbox_results = bbox2result(det_bboxes, det_labels,
                                   self.bbox_head.num_classes)

        if not self.with_mask:
            return bbox_results
        else:
            segm_results = self.simple_test_mask(
                x, img_meta, det_bboxes, det_labels, rescale=rescale)
            return bbox_results, segm_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def simple_test(self, img, img_meta, proposals=None, rescale=False):
        """Test without augmentation."""
        assert self.with_bbox, "Bbox head must be implemented."

        x = self.extract_feat(img)

        proposal_list = self.simple_test_rpn(
            x, img_meta, self.test_cfg.rpn) if proposals is None else proposals

        det_bboxes, det_labels = self.simple_test_bboxes_hkrm(
            x, img_meta, proposal_list, self.test_cfg.rcnn, rescale=rescale, use_hkrm=True)
        bbox_results = bbox2result(det_bboxes, det_labels,
                                   self.bbox_head_hkrm.num_classes)

        if not self.with_mask:
            return bbox_results
        else:
            segm_results = self.simple_test_mask(
                x, img_meta, det_bboxes, det_labels, rescale=rescale)
            return bbox_results, segm_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def simple_test(self, img, img_meta, proposals=None, rescale=False):
        """Test without augmentation."""
        assert self.with_bbox, "Bbox head must be implemented."
        if self.use_consistent_supervision:
            x, y = self.extract_feat(img)
        else:
            x = self.extract_feat(img)

        proposal_list = self.simple_test_rpn(
            x, img_meta, self.test_cfg.rpn) if proposals is None else proposals

        det_bboxes, det_labels = self.simple_test_bboxes(
            x, img_meta, proposal_list, self.test_cfg.rcnn, rescale=rescale)
        bbox_results = bbox2result(det_bboxes, det_labels,
                                   self.bbox_head.num_classes)

        if not self.with_mask:
            return bbox_results
        else:
            segm_results = self.simple_test_mask(
                x, img_meta, det_bboxes, det_labels, rescale=rescale)
            return bbox_results, segm_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def simple_test(self,
                    x,
                    proposal_list,
                    img_metas,
                    proposals=None,
                    rescale=False):
        """Test without augmentation."""
        assert self.with_bbox, 'Bbox head must be implemented.'

        det_bboxes, det_labels = self.simple_test_bboxes(
            x, img_metas, proposal_list, self.test_cfg, rescale=False)
        # pack rois into bboxes
        grid_rois = bbox2roi([det_bboxes[:, :4]])
        grid_feats = self.grid_roi_extractor(
            x[:len(self.grid_roi_extractor.featmap_strides)], grid_rois)
        if grid_rois.shape[0] != 0:
            self.grid_head.test_mode = True
            grid_pred = self.grid_head(grid_feats)
            det_bboxes = self.grid_head.get_bboxes(det_bboxes,
                                                   grid_pred['fused'],
                                                   img_metas)
            if rescale:
                scale_factor = img_metas[0]['scale_factor']
                if not isinstance(scale_factor, (float, torch.Tensor)):
                    scale_factor = det_bboxes.new_tensor(scale_factor)
                det_bboxes[:, :4] /= scale_factor
        else:
            det_bboxes = torch.Tensor([])

        bbox_results = bbox2result(det_bboxes, det_labels,
                                   self.bbox_head.num_classes)

        if not self.with_mask:
            return bbox_results
        else:
            segm_results = self.simple_test_mask(
                x, img_metas, det_bboxes, det_labels, rescale=rescale)
            return bbox_results, segm_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def aug_test(self, x, proposal_list, img_metas, rescale=False):
        """Test with augmentations.

        If rescale is False, then returned bboxes and masks will fit the scale
        of imgs[0].
        """
        # recompute feats to save memory
        det_bboxes, det_labels = self.aug_test_bboxes(x, img_metas,
                                                      proposal_list,
                                                      self.test_cfg)

        if rescale:
            _det_bboxes = det_bboxes
        else:
            _det_bboxes = det_bboxes.clone()
            _det_bboxes[:, :4] *= det_bboxes.new_tensor(
                img_metas[0][0]['scale_factor'])
        bbox_results = bbox2result(_det_bboxes, det_labels,
                                   self.bbox_head.num_classes)

        # det_bboxes always keep the original scale
        if self.with_mask:
            segm_results = self.aug_test_mask(x, img_metas, det_bboxes,
                                              det_labels)
            return bbox_results, segm_results
        else:
            return bbox_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def aug_test(self, imgs, img_metas, rescale=False):
        """Test with augmentations.

        If rescale is False, then returned bboxes and masks will fit the scale
        of imgs[0].
        """
        # recompute feats to save memory
        proposal_list = self.aug_test_rpn(
            self.extract_feats(imgs), img_metas, self.test_cfg.rpn)
        det_bboxes, det_labels = self.aug_test_bboxes(
            self.extract_feats(imgs), img_metas, proposal_list,
            self.test_cfg.rcnn)

        if rescale:
            _det_bboxes = det_bboxes
        else:
            _det_bboxes = det_bboxes.clone()
            _det_bboxes[:, :4] *= img_metas[0][0]['scale_factor']
        bbox_results = bbox2result(_det_bboxes, det_labels,
                                   self.bbox_head.num_classes)

        # det_bboxes always keep the original scale
        if self.with_mask:
            segm_results = self.aug_test_mask(
                self.extract_feats(imgs), img_metas, det_bboxes, det_labels)
            return bbox_results, segm_results
        else:
            return bbox_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def simple_test(self, img, img_meta, proposals=None, rescale=False):
        """Test without augmentation."""
        assert self.with_bbox, "Bbox head must be implemented."
        assert self.with_rbbox, "RBox head must be implemented."
        x = self.extract_feat(img)

        proposal_list = self.simple_test_rpn(
            x, img_meta, self.test_cfg.rpn) if proposals is None else proposals

        det_bboxes, det_labels = self.simple_test_bboxes(
            x, img_meta, proposal_list, self.test_cfg.rcnn, rescale=rescale)
        # TODO: implement the dbbox2result
        # bbox_results = dbbox2result(det_bboxes, det_labels,
        #                            self.bbox_head.num_classes)
        bbox_results = bbox2result(det_bboxes, det_labels,
                                   self.bbox_head.num_classes)

        if not self.with_rbbox:
            return bbox_results
        else:
            det_rbboxes, det_rlabels = self.simple_test_rbboxes_v2(
                x, img_meta, det_bboxes, self.test_cfg.rrcnn, rescale=rescale)
            # import pdb
            # pdb.set_trace()
            rbbox_results = dbbox2result(det_rbboxes, det_rlabels,
                                         self.rbbox_head.num_classes)
            return bbox_results, rbbox_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def aug_test(self, imgs, img_metas, rescale=False):
        """Test with augmentations.

        If rescale is False, then returned bboxes and masks will fit the scale
        of imgs[0].
        """
        # recompute feats to save memory
        assert NotImplementedError
        # proposal_list = self.aug_test_rpn(
        #     self.extract_feats(imgs), img_metas, self.test_cfg.rpn)
        # det_bboxes, det_labels = self.aug_test_bboxes(
        #     self.extract_feats(imgs), img_metas, proposal_list,
        #     self.test_cfg.rcnn)
        #
        # if rescale:
        #     _det_bboxes = det_bboxes
        # else:
        #     _det_bboxes = det_bboxes.clone()
        #     _det_bboxes[:, :4] *= img_metas[0][0]['scale_factor']
        # bbox_results = bbox2result(_det_bboxes, det_labels,
        #                            self.bbox_head.num_classes)

        # det_bboxes always keep the original scale
        # if self.with_mask:
        #     segm_results = self.aug_test_mask(
        #         self.extract_feats(imgs), img_metas, det_bboxes, det_labels)
        #     return bbox_results, segm_results
        # else:
        #     return bbox_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def simple_test(self, img, img_meta, proposals=None, rescale=False):
        """Test without augmentation."""
        assert self.with_bbox, "Bbox head must be implemented."

        x = self.extract_feat(img)

        proposal_list = self.simple_test_rpn(
            x, img_meta, self.test_cfg.rpn) if proposals is None else proposals

        det_bboxes, det_labels = self.simple_test_bboxes(
            x, img_meta, proposal_list, self.test_cfg.rcnn, rescale=False)

        # pack rois into bboxes
        grid_rois = bbox2roi([det_bboxes[:, :4]])
        grid_feats = self.grid_roi_extractor(
            x[:len(self.grid_roi_extractor.featmap_strides)], grid_rois)
        if grid_rois.shape[0] != 0:
            self.grid_head.test_mode = True
            grid_pred = self.grid_head(grid_feats)
            det_bboxes = self.grid_head.get_bboxes(det_bboxes,
                                                   grid_pred['fused'],
                                                   img_meta)
            if rescale:
                det_bboxes[:, :4] /= img_meta[0]['scale_factor']
        else:
            det_bboxes = torch.Tensor([])

        bbox_results = bbox2result(det_bboxes, det_labels,
                                   self.bbox_head.num_classes)

        return bbox_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import bbox2result [as 别名]
def simple_test(self, img, img_meta, proposals=None, rescale=False):
        """Test without augmentation."""
        assert self.with_bbox, "Bbox head must be implemented."

        # 经过backbone和FPN特征提取层，得到若干个输出特征图组成tuple
        x = self.extract_feat(img)

        # 定义在RPNTestMixin中，用于生成RPN输出后处理得到的proposals（真实坐标）（NMS过）
        # 注意list的长度对应的是图片的数目
        #输入特征图，生成anchors，分类回归，NMS，坐标还原，生成proposals
        proposal_list = self.simple_test_rpn(
            x, img_meta, self.test_cfg.rpn) if proposals is None else proposals

        # 定义在BBoxTestMixin中
        # 输入proposals，进行RoI池化，分类回归，NMS，得到真正的检测目标和坐标的坐标偏移
        det_bboxes, det_labels = self.simple_test_bboxes(
            x, img_meta, proposal_list, self.test_cfg.rcnn, rescale=rescale)
        # 偏移还原为真实坐坐标
        bbox_results = bbox2result(det_bboxes, det_labels,
                                   self.bbox_head.num_classes)

        if not self.with_mask:
            return bbox_results
        else:
            # 分割任务加mask
            segm_results = self.simple_test_mask(
                x, img_meta, det_bboxes, det_labels, rescale=rescale)
            return bbox_results, segm_results