Python core.multiclass_nms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 multiclass_nms [as 别名]
def get_det_bboxes(self,
                       rois,
                       cls_score,
                       bbox_pred,
                       img_shape,
                       scale_factor,
                       rescale=False,
                       cfg=None):
        if isinstance(cls_score, list):
            cls_score = sum(cls_score) / float(len(cls_score))
        scores = F.softmax(cls_score, dim=1) if cls_score is not None else None

        if bbox_pred is not None:
            bboxes = delta2bbox(rois[:, 1:], bbox_pred, self.target_means,
                                self.target_stds, img_shape)
        else:
            bboxes = rois[:, 1:]
            # TODO: add clip here

        if rescale:
            bboxes /= scale_factor

        if cfg is None:
            return bboxes, scores
        else:
            det_bboxes, det_labels = multiclass_nms(bboxes, scores,
                                                    cfg.score_thr, cfg.nms,
                                                    cfg.max_per_img)

            return det_bboxes, det_labels 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import multiclass_nms [as 别名]
def aug_test(self, imgs, img_metas, rescale=False):
        # recompute feats to save memory
        feats = self.extract_feats(imgs)

        aug_bboxes = []
        aug_scores = []
        for x, img_meta in zip(feats, img_metas):
            # only one image in the batch
            # TODO more flexible
            outs = self.bbox_head(x)
            bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
            det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
            aug_bboxes.append(det_bboxes)
            aug_scores.append(det_scores)

        # after merging, bboxes will be rescaled to the original image size
        merged_bboxes, merged_scores = self.merge_aug_results(
            aug_bboxes, aug_scores, img_metas)
        det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
                                                self.test_cfg.score_thr,
                                                self.test_cfg.nms,
                                                self.test_cfg.max_per_img)

        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)
        return bbox_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import multiclass_nms [as 别名]
def aug_test(self, imgs, img_metas, rescale=False):
        # recompute feats to save memory
        feats = self.extract_feats(imgs)

        aug_bboxes = []
        aug_scores = []
        for x, img_meta in zip(feats, img_metas):
            # only one image in the batch
            outs = self.bbox_head(x)
            bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
            det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
            aug_bboxes.append(det_bboxes)
            aug_scores.append(det_scores)

        # after merging, bboxes will be rescaled to the original image size
        merged_bboxes, merged_scores = self.merge_aug_results(
            aug_bboxes, aug_scores, img_metas)
        det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
                                                self.test_cfg.score_thr,
                                                self.test_cfg.nms,
                                                self.test_cfg.max_per_img)

        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)
        return bbox_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import multiclass_nms [as 别名]
def _get_bboxes_single(self,
                           cls_scores,
                           bbox_preds,
                           featmap_sizes,
                           point_list,
                           img_shape,
                           scale_factor,
                           cfg,
                           rescale=False):
        cfg = self.test_cfg if cfg is None else cfg
        assert len(cls_scores) == len(bbox_preds) == len(point_list)
        det_bboxes = []
        det_scores = []
        for cls_score, bbox_pred, featmap_size, stride, base_len, (y, x) \
                in zip(cls_scores, bbox_preds, featmap_sizes, self.strides,
                       self.base_edge_list, point_list):
            assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
            scores = cls_score.permute(1, 2, 0).reshape(
                -1, self.cls_out_channels).sigmoid()
            bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4).exp()
            nms_pre = cfg.get('nms_pre', -1)
            if (nms_pre > 0) and (scores.shape[0] > nms_pre):
                max_scores, _ = scores.max(dim=1)
                _, topk_inds = max_scores.topk(nms_pre)
                bbox_pred = bbox_pred[topk_inds, :]
                scores = scores[topk_inds, :]
                y = y[topk_inds]
                x = x[topk_inds]
            x1 = (stride * x - base_len * bbox_pred[:, 0]).\
                clamp(min=0, max=img_shape[1] - 1)
            y1 = (stride * y - base_len * bbox_pred[:, 1]).\
                clamp(min=0, max=img_shape[0] - 1)
            x2 = (stride * x + base_len * bbox_pred[:, 2]).\
                clamp(min=0, max=img_shape[1] - 1)
            y2 = (stride * y + base_len * bbox_pred[:, 3]).\
                clamp(min=0, max=img_shape[0] - 1)
            bboxes = torch.stack([x1, y1, x2, y2], -1)
            det_bboxes.append(bboxes)
            det_scores.append(scores)
        det_bboxes = torch.cat(det_bboxes)
        if rescale:
            det_bboxes /= det_bboxes.new_tensor(scale_factor)
        det_scores = torch.cat(det_scores)
        padding = det_scores.new_zeros(det_scores.shape[0], 1)
        # remind that we set FG labels to [0, num_class-1] since mmdet v2.0
        # BG cat_id: num_class
        det_scores = torch.cat([det_scores, padding], dim=1)
        det_bboxes, det_labels = multiclass_nms(det_bboxes, det_scores,
                                                cfg.score_thr, cfg.nms,
                                                cfg.max_per_img)
        return det_bboxes, det_labels 

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

        Args:
            imgs (list[torch.Tensor]): List of multiple images
            img_metas (list[dict]): List of image information.
            rescale (bool, optional): Whether to rescale the results.
                Defaults to False.

        Returns:
            list[ndarray]: bbox results of each class
        """
        # recompute feats to save memory
        feats = self.extract_feats(imgs)

        aug_bboxes = []
        aug_scores = []
        for x, img_meta in zip(feats, img_metas):
            # only one image in the batch
            outs = self.bbox_head(x)
            bbox_inputs = outs + (img_metas, self.test_cfg, False, False)
            det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
            aug_bboxes.append(det_bboxes)
            aug_scores.append(det_scores)

        # after merging, bboxes will be rescaled to the original image size
        merged_bboxes, merged_scores = self.merge_aug_results(
            aug_bboxes, aug_scores, img_metas)
        det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
                                                self.test_cfg.score_thr,
                                                self.test_cfg.nms,
                                                self.test_cfg.max_per_img)

        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)
        return bbox_results 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import multiclass_nms [as 别名]
def get_bboxes_single(self,
                          cls_scores,
                          bbox_preds,
                          centernesses,
                          mlvl_points,
                          img_shape,
                          scale_factor,
                          cfg,
                          rescale=False):
        assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
        mlvl_bboxes = []
        mlvl_scores = []
        mlvl_centerness = []
        for cls_score, bbox_pred, centerness, points in zip(
                cls_scores, bbox_preds, centernesses, mlvl_points):
            assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
            scores = cls_score.permute(1, 2, 0).reshape(
                -1, self.cls_out_channels).sigmoid()
            centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()

            bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
            nms_pre = cfg.get('nms_pre', -1)
            if nms_pre > 0 and scores.shape[0] > nms_pre:
                max_scores, _ = (scores * centerness[:, None]).max(dim=1)
                _, topk_inds = max_scores.topk(nms_pre)
                points = points[topk_inds, :]
                bbox_pred = bbox_pred[topk_inds, :]
                scores = scores[topk_inds, :]
                centerness = centerness[topk_inds]
            bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
            mlvl_bboxes.append(bboxes)
            mlvl_scores.append(scores)
            mlvl_centerness.append(centerness)
        mlvl_bboxes = torch.cat(mlvl_bboxes)
        if rescale:
            mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
        mlvl_scores = torch.cat(mlvl_scores)
        padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
        mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
        mlvl_centerness = torch.cat(mlvl_centerness)
        det_bboxes, det_labels = multiclass_nms(
            mlvl_bboxes,
            mlvl_scores,
            cfg.score_thr,
            cfg.nms,
            cfg.max_per_img,
            score_factors=mlvl_centerness)
        return det_bboxes, det_labels 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import multiclass_nms [as 别名]
def get_bboxes_single(self,
                          cls_scores,
                          bbox_preds,
                          featmap_sizes,
                          point_list,
                          img_shape,
                          scale_factor,
                          cfg,
                          rescale=False):
        assert len(cls_scores) == len(bbox_preds) == len(point_list)
        det_bboxes = []
        det_scores = []
        for cls_score, bbox_pred, featmap_size, stride, base_len, (y, x) \
                in zip(cls_scores, bbox_preds, featmap_sizes, self.strides,
                       self.base_edge_list, point_list):
            assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
            scores = cls_score.permute(1, 2, 0).reshape(
                -1, self.cls_out_channels).sigmoid()
            bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4).exp()
            nms_pre = cfg.get('nms_pre', -1)
            if (nms_pre > 0) and (scores.shape[0] > nms_pre):
                max_scores, _ = scores.max(dim=1)
                _, topk_inds = max_scores.topk(nms_pre)
                bbox_pred = bbox_pred[topk_inds, :]
                scores = scores[topk_inds, :]
                y = y[topk_inds]
                x = x[topk_inds]
            x1 = (stride * x - base_len * bbox_pred[:, 0]).\
                clamp(min=0, max=img_shape[1] - 1)
            y1 = (stride * y - base_len * bbox_pred[:, 1]).\
                clamp(min=0, max=img_shape[0] - 1)
            x2 = (stride * x + base_len * bbox_pred[:, 2]).\
                clamp(min=0, max=img_shape[1] - 1)
            y2 = (stride * y + base_len * bbox_pred[:, 3]).\
                clamp(min=0, max=img_shape[0] - 1)
            bboxes = torch.stack([x1, y1, x2, y2], -1)
            det_bboxes.append(bboxes)
            det_scores.append(scores)
        det_bboxes = torch.cat(det_bboxes)
        if rescale:
            det_bboxes /= det_bboxes.new_tensor(scale_factor)
        det_scores = torch.cat(det_scores)
        padding = det_scores.new_zeros(det_scores.shape[0], 1)
        det_scores = torch.cat([padding, det_scores], dim=1)
        det_bboxes, det_labels = multiclass_nms(det_bboxes, det_scores,
                                                cfg.score_thr, cfg.nms,
                                                cfg.max_per_img)
        return det_bboxes, det_labels 

# 需要导入模块: from mmdet import core [as 别名]
# 或者: from mmdet.core import multiclass_nms [as 别名]
def get_bboxes_single(self,
                          cls_scores,
                          bbox_preds,
                          featmap_sizes,
                          point_list,
                          img_shape,
                          scale_factor,
                          cfg,
                          rescale=False, debug=False):
        assert len(cls_scores) == len(bbox_preds) == len(point_list)
        det_bboxes = []
        det_scores = []
        for cls_score, bbox_pred, featmap_size, stride, base_len, (y, x) in zip(
                cls_scores, bbox_preds, featmap_sizes, self.strides, self.base_edge_list, point_list):

            assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
            scores = cls_score.permute(1, 2, 0).reshape(
                -1, self.cls_out_channels).sigmoid()
            bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4).exp()
            nms_pre = cfg.get('nms_pre', -1)
            if nms_pre > 0 and scores.shape[0] > nms_pre:
                max_scores, _ = scores.max(dim=1)
                _, topk_inds = max_scores.topk(nms_pre)
                bbox_pred = bbox_pred[topk_inds, :]
                scores = scores[topk_inds, :]
                y = y[topk_inds]
                x = x[topk_inds]
            x1 = (stride * x - base_len * bbox_pred[:, 0]).clamp(min=0, max=img_shape[1] - 1)
            y1 = (stride * y - base_len * bbox_pred[:, 1]).clamp(min=0, max=img_shape[0] - 1)
            x2 = (stride * x + base_len * bbox_pred[:, 2]).clamp(min=0, max=img_shape[1] - 1)
            y2 = (stride * y + base_len * bbox_pred[:, 3]).clamp(min=0, max=img_shape[0] - 1)
            bboxes = torch.stack([x1, y1, x2, y2], -1)
            det_bboxes.append(bboxes)
            det_scores.append(scores)
        det_bboxes = torch.cat(det_bboxes)
        if rescale:
            det_bboxes /= det_bboxes.new_tensor(scale_factor)
        det_scores = torch.cat(det_scores)
        padding = det_scores.new_zeros(det_scores.shape[0], 1)
        det_scores = torch.cat([padding, det_scores], dim=1)
        if debug:
            det_bboxes, det_labels = multiclass_nms(
                det_bboxes,
                det_scores,
                cfg['score_thr'],
                cfg['nms'],
                cfg['max_per_img'])
        else:
            det_bboxes, det_labels = multiclass_nms(
                det_bboxes,
                det_scores,
                cfg.score_thr,
                cfg.nms,
                cfg.max_per_img)
        return det_bboxes, det_labels