paddle.fluid.layers.detection. locality_aware_nms ( bboxes, scores, score_threshold, nms_top_k, keep_top_k, nms_threshold=0.3, normalized=True, nms_eta=1.0, background_label=- 1, name=None ) [source]

Local Aware NMS

Local Aware NMS is to do locality-aware non maximum suppression (LANMS) on boxes and scores.

Firstly, this operator merge box and score according their IOU (intersection over union). In the NMS step, this operator greedily selects a subset of detection bounding boxes that have high scores larger than score_threshold, if providing this threshold, then selects the largest nms_top_k confidences scores if nms_top_k is larger than -1. Then this operator pruns away boxes that have high IOU overlap with already selected boxes by adaptive threshold NMS based on parameters of nms_threshold and nms_eta.

Aftern NMS step, at most keep_top_k number of total bboxes are to be kept per image if keep_top_k is larger than -1.

  • bboxes (Variable) – A 3-D Tensor with shape [N, M, 4 or 8 16 24 32] represents the predicted locations of M bounding bboxes, N is the batch size. Each bounding box has four coordinate values and the layout is [xmin, ymin, xmax, ymax], when box size equals to 4. The data type is float32 or float64.

  • scores (Variable) – A 3-D Tensor with shape [N, C, M] represents the predicted confidence predictions. N is the batch size, C is the class number, M is number of bounding boxes. Now only support 1 class. For each category there are total M scores which corresponding M bounding boxes. Please note, M is equal to the 2nd dimension of BBoxes. The data type is float32 or float64.

  • background_label (int) – The index of background label, the background label will be ignored. If set to -1, then all categories will be considered. Default: -1

  • score_threshold (float) – Threshold to filter out bounding boxes with low confidence score. If not provided, consider all boxes.

  • nms_top_k (int) – Maximum number of detections to be kept according to the confidences after the filtering detections based on score_threshold.

  • keep_top_k (int) – Number of total bboxes to be kept per image after NMS step. -1 means keeping all bboxes after NMS step.

  • nms_threshold (float) – The threshold to be used in NMS. Default: 0.3

  • nms_eta (float) – The threshold to be used in NMS. Default: 1.0

  • normalized (bool) – Whether detections are normalized. Default: True

  • name (str) – Name of the locality aware nms op, please refer to Name . Default: None.


A 2-D LoDTensor with shape [No, 6] represents the detections.

Each row has 6 values: [label, confidence, xmin, ymin, xmax, ymax] or A 2-D LoDTensor with shape [No, 10] represents the detections. Each row has 10 values: [label, confidence, x1, y1, x2, y2, x3, y3, x4, y4]. No is the total number of detections. If there is no detected boxes for all images, lod will be set to {1} and Out only contains one value which is -1. (After version 1.3, when no boxes detected, the lod is changed from {0} to {1}). The data type is float32 or float64.

Return type



import paddle.fluid as fluid
boxes = fluid.data(name='bboxes', shape=[None, 81, 8],
scores = fluid.data(name='scores', shape=[None, 1, 81],
out = fluid.layers.locality_aware_nms(bboxes=boxes,