bbox_transform.py
# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------
import numpy as np
#函數作用:返回anchor相對於GT的(dx,dy,dw,dh)四個迴歸值,shape(len(anchors),4)
def bbox_transform(ex_rois, gt_rois):
#計算每一個anchor的width與height
ex_widths = ex_rois[:, 2] - ex_rois[:, 0] + 1.0
ex_heights = ex_rois[:, 3] - ex_rois[:, 1] + 1.0
#計算每一個anchor中心點x,y座標
ex_ctr_x = ex_rois[:, 0] + 0.5 * ex_widths
ex_ctr_y = ex_rois[:, 1] + 0.5 * ex_heights
#注意:當前的GT不是最一開始傳進來的所有GT,而是與對應anchor最匹配的GT,可能有重複信息
#計算每一個GT的width與height
gt_widths = gt_rois[:, 2] - gt_rois[:, 0] + 1.0
gt_heights = gt_rois[:, 3] - gt_rois[:, 1] + 1.0
#計算每一個GT的中心點x,y座標
gt_ctr_x = gt_rois[:, 0] + 0.5 * gt_widths
gt_ctr_y = gt_rois[:, 1] + 0.5 * gt_heights
#要對bbox進行迴歸需要4個量,dx、dy、dw、dh,分別爲橫縱平移量、寬高縮放量
#此迴歸與fast-rcnn迴歸不同,fast要做的是在cnn卷積完之後的特徵向量進行迴歸,dx、dy、dw、dh都是對應與特徵向量
#此時由於是對原圖像可視野中的anchor進行迴歸,更直觀
#定義 Tx=Pwdx(P)+Px Ty=Phdy(P)+Py Tw=Pwexp(dw(P)) Th=Phexp(dh(P))
#P爲anchor,T爲target,最後要使得T~G,G爲ground-True
#迴歸量dx(P),dy(P),dw(P),dh(P),即dx、dy、dw、dh
targets_dx = (gt_ctr_x - ex_ctr_x) / ex_widths
targets_dy = (gt_ctr_y - ex_ctr_y) / ex_heights
targets_dw = np.log(gt_widths / ex_widths)
targets_dh = np.log(gt_heights / ex_heights)
#targets_dx, targets_dy, targets_dw, targets_dh都爲(anchors.shape[0],)大小
#所以targets爲(anchors.shape[0],4)
targets = np.vstack(
(targets_dx, targets_dy, targets_dw, targets_dh)).transpose()
return targets
#boxes爲anchor信息,deltas爲'rpn_bbox_pred'層信息
#函數作用:得到改善後的anchor的信息(x1,y1,x2,y2)
def bbox_transform_inv(boxes, deltas):
#boxes.shape[0]=K*A=Height*Width*A
if boxes.shape[0] == 0:
return np.zeros((0, deltas.shape[1]), dtype=deltas.dtype)
boxes = boxes.astype(deltas.dtype, copy=False)
#得到Height*Width*A個anchor的寬,高,中心點的x,y座標
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
#deltas本來就只有4列,依次存(dx,dy,dw,dh),每一行表示一個anchor
#0::4表示先取第一個元素,以後每4個取一個,所以取的index爲(0,4,8,12,16...),但是deltas本來就只有4列,所以只能取到一個值
dx = deltas[:, 0::4]
dy = deltas[:, 1::4]
dw = deltas[:, 2::4]
dh = deltas[:, 3::4]
#預測後的中心點,與w與h
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]
#預測後的(x1,y1,x2,y2)存入 pred_boxes
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
#函數作用:使得boxes位於圖片內
def clip_boxes(boxes, im_shape):
"""
Clip boxes to image boundaries.
"""
#im_shape[0]爲圖片高,im_shape[1]爲圖片寬
#使得boxes位於圖片內
# x1 >= 0
boxes[:, 0::4] = np.maximum(np.minimum(boxes[:, 0::4], im_shape[1] - 1), 0)
# y1 >= 0
boxes[:, 1::4] = np.maximum(np.minimum(boxes[:, 1::4], im_shape[0] - 1), 0)
# x2 < im_shape[1]
boxes[:, 2::4] = np.maximum(np.minimum(boxes[:, 2::4], im_shape[1] - 1), 0)
# y2 < im_shape[0]
boxes[:, 3::4] = np.maximum(np.minimum(boxes[:, 3::4], im_shape[0] - 1), 0)
return boxes
轉自https://blog.csdn.net/l297969586/article/details/78026221