yolov3识别大分辨率图片切割问题（已解决）

做图像识别的过程，发现yolov3只针对416*416的识别效果较好，而训练大分辨率的图片效果比较差，可以将图像切割训练，再进行操作，以下是大分辨率图片切割的方法

 

---

# -*- coding:utf-8 -*-


from PIL import Image

'''
   @author:xunalove
    修改文件位置
    修改图片id

'''
def cut(id,vx,vy):
    #打开图片图片1.jpg
    name1 = "D:/python/tire defects/source/xraytire/XrayImages/slidingwindow/"+ id + ".jpg"
   # name2 = "/Users/DSOcmy/PycharmProjects/untitled/test/"+ id +"_cut_"
    name2 = "D:/python/tire defects/source/xraytire/XrayImages/slidingwindow/" + id + "."
    im =Image.open(name1)
    w = im.size[0]
    h = im.size[1]
    print(w, h)
    #偏移量
    dx = 300
    dy = 300
    n = 1

    #左上角切割
    x1 = 0
    y1 = 0
    x2 = vx
    y2 = vy
    #纵向
    while x2 <= h:
        while y2 <= w:
            name3 = name2 + '%06d' % (n) +