letterbox实现

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)):
    # Resize and pad image while meeting stride-multiple constraints
    shape = im.shape[:2]  # current shape [height, width]

    # Scale ratio (new / old)
    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
    
    # Compute padding
    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  # wh padding 
    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:  # resize
        im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
    im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
    return im
    

src = cv2.imread("1.jpg") 
dst = letterbox(src, (768,768))
cv2.imwrite("letterbox.jpg",dst)