easycv/models/detection/dense_heads/base_dense_head.py [33:212]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - def get_bboxes(self, cls_scores, bbox_preds, score_factors=None, img_metas=None, cfg=None, rescale=False, with_nms=True, **kwargs): """Transform network outputs of a batch into bbox results. Note: When score_factors is not None, the cls_scores are usually multiplied by it then obtain the real score used in NMS, such as CenterNess in FCOS, IoU branch in ATSS. Args: cls_scores (list[Tensor]): Classification scores for all scale levels, each is a 4D-tensor, has shape (batch_size, num_priors * num_classes, H, W). bbox_preds (list[Tensor]): Box energies / deltas for all scale levels, each is a 4D-tensor, has shape (batch_size, num_priors * 4, H, W). score_factors (list[Tensor], Optional): Score factor for all scale level, each is a 4D-tensor, has shape (batch_size, num_priors * 1, H, W). Default None. img_metas (list[dict], Optional): Image meta info. Default None. cfg (mmcv.Config, Optional): Test / postprocessing configuration, if None, test_cfg would be used. Default None. rescale (bool): If True, return boxes in original image space. Default False. with_nms (bool): If True, do nms before return boxes. Default True. Returns: list[list[Tensor, Tensor]]: Each item in result_list is 2-tuple. The first item is an (n, 5) tensor, where the first 4 columns are bounding box positions (tl_x, tl_y, br_x, br_y) and the 5-th column is a score between 0 and 1. The second item is a (n,) tensor where each item is the predicted class label of the corresponding box. """ assert len(cls_scores) == len(bbox_preds) if score_factors is None: # e.g. Retina, FreeAnchor, Foveabox, etc. with_score_factors = False else: # e.g. FCOS, PAA, ATSS, AutoAssign, etc. with_score_factors = True assert len(cls_scores) == len(score_factors) num_levels = len(cls_scores) featmap_sizes = [cls_scores[i].shape[-2:] for i in range(num_levels)] mlvl_priors = self.prior_generator.grid_priors( featmap_sizes, dtype=cls_scores[0].dtype, device=cls_scores[0].device) result_list = [] for img_id in range(len(img_metas)): img_meta = img_metas[img_id] cls_score_list = select_single_mlvl(cls_scores, img_id) bbox_pred_list = select_single_mlvl(bbox_preds, img_id) if with_score_factors: score_factor_list = select_single_mlvl(score_factors, img_id) else: score_factor_list = [None for _ in range(num_levels)] results = self._get_bboxes_single(cls_score_list, bbox_pred_list, score_factor_list, mlvl_priors, img_meta, cfg, rescale, with_nms, **kwargs) result_list.append(results) return result_list def _get_bboxes_single(self, cls_score_list, bbox_pred_list, score_factor_list, mlvl_priors, img_meta, cfg, rescale=False, with_nms=True, **kwargs): """Transform outputs of a single image into bbox predictions. Args: cls_score_list (list[Tensor]): Box scores from all scale levels of a single image, each item has shape (num_priors * num_classes, H, W). bbox_pred_list (list[Tensor]): Box energies / deltas from all scale levels of a single image, each item has shape (num_priors * 4, H, W). score_factor_list (list[Tensor]): Score factor from all scale levels of a single image, each item has shape (num_priors * 1, H, W). mlvl_priors (list[Tensor]): Each element in the list is the priors of a single level in feature pyramid. In all anchor-based methods, it has shape (num_priors, 4). In all anchor-free methods, it has shape (num_priors, 2) when `with_stride=True`, otherwise it still has shape (num_priors, 4). img_meta (dict): Image meta info. cfg (mmcv.Config): Test / postprocessing configuration, if None, test_cfg would be used. rescale (bool): If True, return boxes in original image space. Default: False. with_nms (bool): If True, do nms before return boxes. Default: True. Returns: tuple[Tensor]: Results of detected bboxes and labels. If with_nms is False and mlvl_score_factor is None, return mlvl_bboxes and mlvl_scores, else return mlvl_bboxes, mlvl_scores and mlvl_score_factor. Usually with_nms is False is used for aug test. If with_nms is True, then return the following format - det_bboxes (Tensor): Predicted bboxes with shape \ [num_bboxes, 5], where the first 4 columns are bounding \ box positions (tl_x, tl_y, br_x, br_y) and the 5-th \ column are scores between 0 and 1. - det_labels (Tensor): Predicted labels of the corresponding \ box with shape [num_bboxes]. """ if score_factor_list[0] is None: # e.g. Retina, FreeAnchor, etc. with_score_factors = False else: # e.g. FCOS, PAA, ATSS, etc. with_score_factors = True cfg = self.test_cfg if cfg is None else cfg img_shape = img_meta['img_shape'] nms_pre = cfg.get('nms_pre', -1) mlvl_bboxes = [] mlvl_scores = [] mlvl_labels = [] if with_score_factors: mlvl_score_factors = [] else: mlvl_score_factors = None for level_idx, (cls_score, bbox_pred, score_factor, priors) in \ enumerate(zip(cls_score_list, bbox_pred_list, score_factor_list, mlvl_priors)): assert cls_score.size()[-2:] == bbox_pred.size()[-2:] bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4) if with_score_factors: score_factor = score_factor.permute(1, 2, 0).reshape(-1).sigmoid() cls_score = cls_score.permute(1, 2, 0).reshape(-1, self.cls_out_channels) if self.use_sigmoid_cls: scores = cls_score.sigmoid() else: # remind that we set FG labels to [0, num_class-1] # since mmdet v2.0 # BG cat_id: num_class scores = cls_score.softmax(-1)[:, :-1] # After https://github.com/open-mmlab/mmdetection/pull/6268/, # this operation keeps fewer bboxes under the same `nms_pre`. # There is no difference in performance for most models. If you # find a slight drop in performance, you can set a larger # `nms_pre` than before. results = filter_scores_and_topk( scores, cfg.score_thr, nms_pre, dict(bbox_pred=bbox_pred, priors=priors)) scores, labels, keep_idxs, filtered_results = results bbox_pred = filtered_results['bbox_pred'] priors = filtered_results['priors'] if with_score_factors: score_factor = score_factor[keep_idxs] - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - easycv/models/detection/detectors/fcos/fcos_head.py [581:754]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - def get_bboxes(self, cls_scores, bbox_preds, score_factors=None, img_metas=None, cfg=None, rescale=False, with_nms=True, **kwargs): """Transform network outputs of a batch into bbox results. Note: When score_factors is not None, the cls_scores are usually multiplied by it then obtain the real score used in NMS, such as CenterNess in FCOS, IoU branch in ATSS. Args: cls_scores (list[Tensor]): Classification scores for all scale levels, each is a 4D-tensor, has shape (batch_size, num_priors * num_classes, H, W). bbox_preds (list[Tensor]): Box energies / deltas for all scale levels, each is a 4D-tensor, has shape (batch_size, num_priors * 4, H, W). score_factors (list[Tensor], Optional): Score factor for all scale level, each is a 4D-tensor, has shape (batch_size, num_priors * 1, H, W). Default None. img_metas (list[dict], Optional): Image meta info. Default None. cfg (mmcv.Config, Optional): Test / postprocessing configuration, if None, test_cfg would be used. Default None. rescale (bool): If True, return boxes in original image space. Default False. with_nms (bool): If True, do nms before return boxes. Default True. Returns: list[list[Tensor, Tensor]]: Each item in result_list is 2-tuple. The first item is an (n, 5) tensor, where the first 4 columns are bounding box positions (tl_x, tl_y, br_x, br_y) and the 5-th column is a score between 0 and 1. The second item is a (n,) tensor where each item is the predicted class label of the corresponding box. """ assert len(cls_scores) == len(bbox_preds) if score_factors is None: # e.g. Retina, FreeAnchor, Foveabox, etc. with_score_factors = False else: # e.g. FCOS, PAA, ATSS, AutoAssign, etc. with_score_factors = True assert len(cls_scores) == len(score_factors) num_levels = len(cls_scores) featmap_sizes = [cls_scores[i].shape[-2:] for i in range(num_levels)] mlvl_priors = self.prior_generator.grid_priors( featmap_sizes, dtype=cls_scores[0].dtype, device=cls_scores[0].device) result_list = [] for img_id in range(len(img_metas)): img_meta = img_metas[img_id] cls_score_list = select_single_mlvl(cls_scores, img_id) bbox_pred_list = select_single_mlvl(bbox_preds, img_id) if with_score_factors: score_factor_list = select_single_mlvl(score_factors, img_id) else: score_factor_list = [None for _ in range(num_levels)] results = self._get_bboxes_single(cls_score_list, bbox_pred_list, score_factor_list, mlvl_priors, img_meta, cfg, rescale, with_nms, **kwargs) result_list.append(results) return result_list def _get_bboxes_single(self, cls_score_list, bbox_pred_list, score_factor_list, mlvl_priors, img_meta, cfg, rescale=False, with_nms=True, **kwargs): """Transform outputs of a single image into bbox predictions. Args: cls_score_list (list[Tensor]): Box scores from all scale levels of a single image, each item has shape (num_priors * num_classes, H, W). bbox_pred_list (list[Tensor]): Box energies / deltas from all scale levels of a single image, each item has shape (num_priors * 4, H, W). score_factor_list (list[Tensor]): Score factor from all scale levels of a single image, each item has shape (num_priors * 1, H, W). mlvl_priors (list[Tensor]): Each element in the list is the priors of a single level in feature pyramid. In all anchor-based methods, it has shape (num_priors, 4). In all anchor-free methods, it has shape (num_priors, 2) when `with_stride=True`, otherwise it still has shape (num_priors, 4). img_meta (dict): Image meta info. cfg (mmcv.Config): Test / postprocessing configuration, if None, test_cfg would be used. rescale (bool): If True, return boxes in original image space. Default: False. with_nms (bool): If True, do nms before return boxes. Default: True. Returns: tuple[Tensor]: Results of detected bboxes and labels. If with_nms is False and mlvl_score_factor is None, return mlvl_bboxes and mlvl_scores, else return mlvl_bboxes, mlvl_scores and mlvl_score_factor. Usually with_nms is False is used for aug test. If with_nms is True, then return the following format - det_bboxes (Tensor): Predicted bboxes with shape \ [num_bboxes, 5], where the first 4 columns are bounding \ box positions (tl_x, tl_y, br_x, br_y) and the 5-th \ column are scores between 0 and 1. - det_labels (Tensor): Predicted labels of the corresponding \ box with shape [num_bboxes]. """ if score_factor_list[0] is None: # e.g. Retina, FreeAnchor, etc. with_score_factors = False else: # e.g. FCOS, PAA, ATSS, etc. with_score_factors = True cfg = self.test_cfg if cfg is None else cfg img_shape = img_meta['img_shape'] nms_pre = cfg.get('nms_pre', -1) mlvl_bboxes = [] mlvl_scores = [] mlvl_labels = [] if with_score_factors: mlvl_score_factors = [] else: mlvl_score_factors = None for level_idx, (cls_score, bbox_pred, score_factor, priors) in \ enumerate(zip(cls_score_list, bbox_pred_list, score_factor_list, mlvl_priors)): assert cls_score.size()[-2:] == bbox_pred.size()[-2:] bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4) if with_score_factors: score_factor = score_factor.permute(1, 2, 0).reshape(-1).sigmoid() cls_score = cls_score.permute(1, 2, 0).reshape(-1, self.cls_out_channels) if self.use_sigmoid_cls: scores = cls_score.sigmoid() else: # remind that we set FG labels to [0, num_class-1] # since mmdet v2.0 # BG cat_id: num_class scores = cls_score.softmax(-1)[:, :-1] # After https://github.com/open-mmlab/mmdetection/pull/6268/, # this operation keeps fewer bboxes under the same `nms_pre`. # There is no difference in performance for most models. If you # find a slight drop in performance, you can set a larger # `nms_pre` than before. results = filter_scores_and_topk( scores, cfg.score_thr, nms_pre, dict(bbox_pred=bbox_pred, priors=priors)) scores, labels, keep_idxs, filtered_results = results bbox_pred = filtered_results['bbox_pred'] priors = filtered_results['priors'] if with_score_factors: score_factor = score_factor[keep_idxs] - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -