Python ops.nms方法代码示例

# 需要导入模块: from mmdet import ops [as 别名]
# 或者: from mmdet.ops import nms [as 别名]
def merge_aug_proposals(aug_proposals, img_metas, rpn_test_cfg):
    """Merge augmented proposals (multiscale, flip, etc.)

    Args:
        aug_proposals (list[Tensor]): proposals from different testing
            schemes, shape (n, 5). Note that they are not rescaled to the
            original image size.

        img_metas (list[dict]): list of image info dict where each dict has:
            'img_shape', 'scale_factor', 'flip', and my also contain
            'filename', 'ori_shape', 'pad_shape', and 'img_norm_cfg'.
            For details on the values of these keys see
            `mmdet/datasets/pipelines/formatting.py:Collect`.

        rpn_test_cfg (dict): rpn test config.

    Returns:
        Tensor: shape (n, 4), proposals corresponding to original image scale.
    """
    recovered_proposals = []
    for proposals, img_info in zip(aug_proposals, img_metas):
        img_shape = img_info['img_shape']
        scale_factor = img_info['scale_factor']
        flip = img_info['flip']
        flip_direction = img_info['flip_direction']
        _proposals = proposals.clone()
        _proposals[:, :4] = bbox_mapping_back(_proposals[:, :4], img_shape,
                                              scale_factor, flip,
                                              flip_direction)
        recovered_proposals.append(_proposals)
    aug_proposals = torch.cat(recovered_proposals, dim=0)
    merged_proposals, _ = nms(aug_proposals, rpn_test_cfg.nms_thr)
    scores = merged_proposals[:, 4]
    _, order = scores.sort(0, descending=True)
    num = min(rpn_test_cfg.max_num, merged_proposals.shape[0])
    order = order[:num]
    merged_proposals = merged_proposals[order, :]
    return merged_proposals 

# 需要导入模块: from mmdet import ops [as 别名]
# 或者: from mmdet.ops import nms [as 别名]
def merge_rotate_aug_proposals(aug_proposals, img_metas, rpn_test_cfg):
    """Merge augmented proposals (multiscale, flip, etc.)

    Args:
        aug_proposals (list[Tensor]): proposals from different testing
            schemes, shape (n, 5). Note that they are not rescaled to the
            original image size.
        img_metas (list[dict]): image info including "shape_scale" and "flip".
        rpn_test_cfg (dict): rpn test config.

    Returns:
        Tensor: shape (n, 4), proposals corresponding to original image scale.
    """
    recovered_proposals = []
    for proposals, img_info in zip(aug_proposals, img_metas):
        img_shape = img_info['img_shape']
        scale_factor = img_info['scale_factor']
        flip = img_info['flip']
        _proposals = proposals.clone()
        _proposals[:, :4] = bbox_mapping_back(_proposals[:, :4], img_shape,
                                              scale_factor, flip)
        # rotation mapping
        angle = img_info['angle']
        if angle != 0:
            # TODO: check the angle
            _proposals[:, :4] = bbox_rotate_mapping(_proposals[:, :4], img_shape, -angle)
        recovered_proposals.append(_proposals)
    aug_proposals = torch.cat(recovered_proposals, dim=0)
    merged_proposals, _ = nms(aug_proposals, rpn_test_cfg.nms_thr)
    scores = merged_proposals[:, 4]
    _, order = scores.sort(0, descending=True)
    num = min(rpn_test_cfg.max_num, merged_proposals.shape[0])
    order = order[:num]
    merged_proposals = merged_proposals[order, :]
    return merged_proposals 

# 需要导入模块: from mmdet import ops [as 别名]
# 或者: from mmdet.ops import nms [as 别名]
def merge_aug_proposals(aug_proposals, img_metas, rpn_test_cfg):
    """Merge augmented proposals (multiscale, flip, etc.)

    Args:
        aug_proposals (list[Tensor]): proposals from different testing
            schemes, shape (n, 5). Note that they are not rescaled to the
            original image size.
        img_metas (list[dict]): image info including "shape_scale" and "flip".
        rpn_test_cfg (dict): rpn test config.

    Returns:
        Tensor: shape (n, 4), proposals corresponding to original image scale.
    """
    recovered_proposals = []
    for proposals, img_info in zip(aug_proposals, img_metas):
        img_shape = img_info['img_shape']
        scale_factor = img_info['scale_factor']
        flip = img_info['flip']
        _proposals = proposals.clone()
        _proposals[:, :4] = bbox_mapping_back(_proposals[:, :4], img_shape,
                                              scale_factor, flip)
        recovered_proposals.append(_proposals)
    aug_proposals = torch.cat(recovered_proposals, dim=0)
    merged_proposals, _ = nms(aug_proposals, rpn_test_cfg.nms_thr)
    scores = merged_proposals[:, 4]
    _, order = scores.sort(0, descending=True)
    num = min(rpn_test_cfg.max_num, merged_proposals.shape[0])
    order = order[:num]
    merged_proposals = merged_proposals[order, :]
    return merged_proposals 

# 需要导入模块: from mmdet import ops [as 别名]
# 或者: from mmdet.ops import nms [as 别名]
def post_process(preds, num_classes=4787, iou_thr=0.3, score_thr=0.3):
    ret = []
    for pred in tqdm(preds):
        bboxes = np.vstack(pred)
        labels = np.concatenate([[i] * len(bb) for i, bb in enumerate(pred)])
        # nms
        _, inds = nms(bboxes, iou_thr)
        bboxes, labels = bboxes[inds], labels[inds]
        # score filtering
        inds = bboxes[:, 4] > score_thr
        bboxes, labels = bboxes[inds], labels[inds]
        #
        ret.append([bboxes[labels == i] for i in range(num_classes)])
    return ret 

# 需要导入模块: from mmdet import ops [as 别名]
# 或者: from mmdet.ops import nms [as 别名]
def merge_aug_proposals(aug_proposals, img_metas, rpn_test_cfg):
    """Merge augmented proposals (multiscale, flip, etc.)

    Args:
        aug_proposals (list[Tensor]): proposals from different testing
            schemes, shape (n, 5). Note that they are not rescaled to the
            original image size.

        img_metas (list[dict]): list of image info dict where each dict has:
            'img_shape', 'scale_factor', 'flip', and my also contain
            'filename', 'ori_shape', 'pad_shape', and 'img_norm_cfg'.
            For details on the values of these keys see
            `mmdet/datasets/pipelines/formatting.py:Collect`.

        rpn_test_cfg (dict): rpn test config.

    Returns:
        Tensor: shape (n, 4), proposals corresponding to original image scale.
    """
    recovered_proposals = []
    for proposals, img_info in zip(aug_proposals, img_metas):
        img_shape = img_info['img_shape']
        scale_factor = img_info['scale_factor']
        flip = img_info['flip']
        _proposals = proposals.clone()
        _proposals[:, :4] = bbox_mapping_back(_proposals[:, :4], img_shape,
                                              scale_factor, flip)
        recovered_proposals.append(_proposals)
    aug_proposals = torch.cat(recovered_proposals, dim=0)
    merged_proposals, _ = nms(aug_proposals, rpn_test_cfg.nms_thr)
    scores = merged_proposals[:, 4]
    _, order = scores.sort(0, descending=True)
    num = min(rpn_test_cfg.max_num, merged_proposals.shape[0])
    order = order[:num]
    merged_proposals = merged_proposals[order, :]
    return merged_proposals 

# 需要导入模块: from mmdet import ops [as 别名]
# 或者: from mmdet.ops import nms [as 别名]
def get_bboxes_single(self,
                          cls_scores,
                          bbox_preds,
                          mlvl_anchors,
                          img_shape,
                          scale_factor,
                          cfg,
                          rescale=False):
        mlvl_proposals = []
        for idx in range(len(cls_scores)):
            rpn_cls_score = cls_scores[idx]
            rpn_bbox_pred = bbox_preds[idx]
            assert rpn_cls_score.size()[-2:] == rpn_bbox_pred.size()[-2:]
            anchors = mlvl_anchors[idx]
            rpn_cls_score = rpn_cls_score.permute(1, 2, 0)
            if self.use_sigmoid_cls:
                rpn_cls_score = rpn_cls_score.reshape(-1)
                scores = rpn_cls_score.sigmoid()
            else:
                rpn_cls_score = rpn_cls_score.reshape(-1, 2)
                scores = rpn_cls_score.softmax(dim=1)[:, 1]
            rpn_bbox_pred = rpn_bbox_pred.permute(1, 2, 0).reshape(-1, 4)
            if cfg.nms_pre > 0 and scores.shape[0] > cfg.nms_pre:
                _, topk_inds = scores.topk(cfg.nms_pre)
                rpn_bbox_pred = rpn_bbox_pred[topk_inds, :]
                anchors = anchors[topk_inds, :]
                scores = scores[topk_inds]
            proposals = delta2bbox(anchors, rpn_bbox_pred, self.target_means,
                                   self.target_stds, img_shape)
            if cfg.min_bbox_size > 0:
                w = proposals[:, 2] - proposals[:, 0] + 1
                h = proposals[:, 3] - proposals[:, 1] + 1
                valid_inds = torch.nonzero((w >= cfg.min_bbox_size) &
                                           (h >= cfg.min_bbox_size)).squeeze()
                proposals = proposals[valid_inds, :]
                scores = scores[valid_inds]
            proposals = torch.cat([proposals, scores.unsqueeze(-1)], dim=-1)
            proposals, _ = nms(proposals, cfg.nms_thr)
            proposals = proposals[:cfg.nms_post, :]
            mlvl_proposals.append(proposals)
        proposals = torch.cat(mlvl_proposals, 0)
        if cfg.nms_across_levels:
            proposals, _ = nms(proposals, cfg.nms_thr)
            proposals = proposals[:cfg.max_num, :]
        else:
            scores = proposals[:, 4]
            num = min(cfg.max_num, proposals.shape[0])
            _, topk_inds = scores.topk(num)
            proposals = proposals[topk_inds, :]
        return proposals