数据集中的图片一般为长方形，当模型输入为正方形时直接将长方形图片resize为正方形会使得图片失真，采用letterbox通过填充边界(通常是灰色填充)的方式来保持原始图片的长宽比例，同时又满足模型正方形输入的需要。
import cv2
def letterbox(im, new_shape=(640, 640), color=(114, 114, 114)):
shape = im.shape[:2]
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
dw, dh = (new_shape[1] - new_unpad[0])/2, (new_shape[0] - new_unpad[1])/2
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
if shape[::-1] != new_unpad:
im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)
return im
src = cv2.imread("1.jpg")
dst = letterbox(src, (768,768))
cv2.imwrite("letterbox.jpg",dst)
Original: https://blog.csdn.net/taifyang/article/details/127820108
Author: 给算法爸爸上香
Title: letterbox实现
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/657157/
转载文章受原作者版权保护。转载请注明原作者出处！