faster-rcnn 之 bbox_transform_inv(boxes, deltas)

jasonzzj

于 2017-07-20 15:09:20 发布

阅读量3.1k

点赞数

分类专栏：深度学习 Python

本文链接：https://blog.youkuaiyun.com/jasonzzj/article/details/75529824

版权

Python 同时被 2 个专栏收录

23 篇文章

订阅专栏

深度学习

14 篇文章

订阅专栏

def bbox_transform_inv(boxes, deltas):
  if boxes.shape[0] == 0:
    return np.zeros((0, deltas.shape[1]), dtype=deltas.dtype)

  boxes = boxes.astype(deltas.dtype, copy=False)
  widths = boxes[:, 2] - boxes[:, 0] + 1.0
  heights = boxes[:, 3] - boxes[:, 1] + 1.0
  ctr_x = boxes[:, 0] + 0.5 * widths
  ctr_y = boxes[:, 1] + 0.5 * heights

  dx = deltas[:, 0::4]
  dy = deltas[:, 1::4]
  dw = deltas[:, 2::4]
  dh = deltas[:, 3::4]

  pred_ctr_x = dx * widths[:, np.newaxis] + ctr_x[:, np.newaxis]
  pred_ctr_y = dy * heights[:, np.newaxis] + ctr_y[:, np.newaxis]
  pred_w = np.exp(dw) * widths[:, np.newaxis]
  pred_h = np.exp(dh) * heights[:, np.newaxis]

  pred_boxes = np.zeros(deltas.shape, dtype=deltas.dtype)
  # x1
  pred_boxes[:, 0::4] = pred_ctr_x - 0.5 * pred_w
  # y1
  pred_boxes[:, 1::4] = pred_ctr_y - 0.5 * pred_h
  # x2
  pred_boxes[:, 2::4] = pred_ctr_x + 0.5 * pred_w
  # y2
  pred_boxes[:, 3::4] = pred_ctr_y + 0.5 * pred_h

  return pred_boxes