ncnn/python/ncnn/utils/functional.py

# Tencent is pleased to support the open source community by making ncnn available.
#
# Copyright (C) 2020 THL A29 Limited, a Tencent company. All rights reserved.
#
# Licensed under the BSD 3-Clause License (the "License"); you may not use this file except
# in compliance with the License. You may obtain a copy of the License at
#
# https://opensource.org/licenses/BSD-3-Clause
#
# 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.

import numpy as np


def xywh2xyxy(x):
    # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
    y = np.zeros_like(x)
    y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
    y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
    y[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right x
    y[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right y
    return y


def xyxy2xywh(x):
    # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
    y = np.zeros_like(x)
    y[:, 0] = (x[:, 0] + x[:, 2]) / 2  # x center
    y[:, 1] = (x[:, 1] + x[:, 3]) / 2  # y center
    y[:, 2] = x[:, 2] - x[:, 0]  # width
    y[:, 3] = x[:, 3] - x[:, 1]  # height
    return y


def make_grid(nx=20, ny=20):
    xv1, yv1 = np.meshgrid(np.arange(nx), np.arange(ny))
    z1 = np.stack((xv1, yv1), 2).reshape((1, ny, nx, 2)).astype(np.float32)
    return z1


def sigmoid(x):
    return 1 / (1 + np.exp(-x))


def softmax(x):
    max_value = np.max(x, axis=-1)
    x -= max_value.reshape((x.shape[0], 1))
    x = np.exp(x)
    sum_value = np.sum(x, axis=-1)
    x /= sum_value.reshape((x.shape[0], 1))
    return x


def iou_of(boxes0, boxes1, eps=1e-5):
    """Return intersection-over-union (Jaccard index) of boxes.

    Args:
        boxes0 (N, 4): ground truth boxes.
        boxes1 (N or 1, 4): predicted boxes.
        eps: a small number to avoid 0 as denominator.
    Returns:
        iou (N): IoU values.
    """
    overlap_left_top = np.maximum(boxes0[..., :2], boxes1[..., :2])
    overlap_right_bottom = np.minimum(boxes0[..., 2:], boxes1[..., 2:])

    overlap_area = area_of(overlap_left_top, overlap_right_bottom)
    area0 = area_of(boxes0[..., :2], boxes0[..., 2:])
    area1 = area_of(boxes1[..., :2], boxes1[..., 2:])
    return overlap_area / (area0 + area1 - overlap_area + eps)


def area_of(left_top, right_bottom):
    """Compute the areas of rectangles given two corners.

    Args:
        left_top (N, 2): left top corner.
        right_bottom (N, 2): right bottom corner.

    Returns:
        area (N): return the area.
    """
    hw = np.clip(right_bottom - left_top, 0.0, None)
    return hw[..., 0] * hw[..., 1]


def nms(boxes, scores, iou_threshold, top_k=-1, candidate_size=200):
    """

    Args:
        box_scores (N, 5): boxes in corner-form(x1, y1, x2, y2) and probabilities.
        iou_threshold: intersection over union threshold.
        top_k: keep top_k results. If k <= 0, keep all the results.
        candidate_size: only consider the candidates with the highest scores.
    Returns:
         picked: a list of indexes of the kept boxes
    """

    picked = []
    indexes = np.argsort(scores)
    indexes = indexes[-candidate_size:]
    while len(indexes) > 0:
        current = indexes[-1]
        picked.append(current)
        if 0 < top_k == len(picked) or len(indexes) == 1:
            break

        current_box = boxes[current, :]
        indexes = indexes[:-1]
        rest_boxes = boxes[indexes, :]
        iou = iou_of(
            rest_boxes,
            np.expand_dims(current_box, axis=0),
        )
        indexes = indexes[iou <= iou_threshold]

    return picked