detection.py

#   Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
All layers just related to the detection neural network.
"""

from ..layer_helper import LayerHelper

__all__ = ['detection_output', ]


def detection_output(scores,
                     loc,
                     prior_box,
                     prior_box_var,
                     background_label=0,
                     nms_threshold=0.3,
                     nms_top_k=400,
                     keep_top_k=200,
                     score_threshold=0.01,
                     nms_eta=1.0):
    """
    **Detection Output Layer**

    This layer applies the NMS to the output of network and computes the 
    predict bounding box location. The output's shape of this layer could
    be zero if there is no valid bounding box.

    Args:
        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. For each category
            there are total M scores which corresponding M bounding boxes.
        loc(Variable): A 3-D Tensor with shape [N, M, 4] represents the
            predicted locations of M bounding bboxes. N is the batch size,
            and each bounding box has four coordinate values and the layout
            is [xmin, ymin, xmax, ymax].
        prior_box(Variable): A 2-D Tensor with shape [M, 4] holds M boxes,
            each box is represented as [xmin, ymin, xmax, ymax],
            [xmin, ymin] is the left top coordinate of the anchor box,
            if the input is image feature map, they are close to the origin
            of the coordinate system. [xmax, ymax] is the right bottom
            coordinate of the anchor box.
        prior_box_var(Variable): A 2-D Tensor with shape [M, 4] holds M group
            of variance.
        background_label(float): The index of background label,
            the background label will be ignored. If set to -1, then all
            categories will be considered.
        nms_threshold(float): The threshold to be used in NMS.
        nms_top_k(int): Maximum number of detections to be kept according
            to the confidences aftern 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.
        score_threshold(float): Threshold to filter out bounding boxes with
            low confidence score. If not provided, consider all boxes.
        nms_eta(float): The parameter for adaptive NMS.

    Returns:
        The detected bounding boxes which are a Tensor.

    Examples:
        .. code-block:: python

        pb = layers.data(name='prior_box', shape=[10, 4],
                         append_batch_size=False, dtype='float32')
        pbv = layers.data(name='prior_box_var', shape=[10, 4],
                          append_batch_size=False, dtype='float32')
        loc = layers.data(name='target_box', shape=[21, 4],
                          append_batch_size=False, dtype='float32')
        scores = layers.data(name='scores', shape=[2, 21, 10],
                          append_batch_size=False, dtype='float32')
        nmsed_outs = fluid.layers.detection_output(scores=scores,
                                       loc=loc,
                                       prior_box=pb,
                                       prior_box_var=pbv)
    """

    helper = LayerHelper("detection_output", **locals())
    decoded_box = helper.create_tmp_variable(dtype=loc.dtype)
    helper.append_op(
        type="box_coder",
        inputs={
            'PriorBox': prior_box,
            'PriorBoxVar': prior_box_var,
            'TargetBox': loc
        },
        outputs={'OutputBox': decoded_box},
        attrs={'code_type': 'decode_center_size'})
    nmsed_outs = helper.create_tmp_variable(dtype=decoded_box.dtype)

    helper.append_op(
        type="multiclass_nms",
        inputs={'Scores': scores,
                'BBoxes': decoded_box},
        outputs={'Out': nmsed_outs},
        attrs={
            'background_label': 0,
            'nms_threshold': nms_threshold,
            'nms_top_k': nms_top_k,
            'keep_top_k': keep_top_k,
            'score_threshold': score_threshold,
            'nms_eta': 1.0
        })
    return nmsed_outs