深度学习图片数据标签切割转换

深度学习图片数据标签切割转换，相对坐标

我们图片分类的标签可能有多个类，一张图片中有大目标和小目标，我们要切割出大目标，然后小目标的坐标也变成相对于大目标的坐标。因为我们为了方便，一次性打标了，一次性的标注了图片中的大目标和小目标，所以小目标的标注坐标是相对于整张图片的，但现在我们要做两次检测，所以切出来的大目标中含有的小目标我们需要做个坐标转换，把小目标的坐标转换成相对于大目标的。

代码如下：

import glob, math, os

import numpy as np
import cv2
from PIL import Image

if __name__ == '__main__':
    yolo_dataset_path = 'D://baozi/baozilabel/'   #要切割的图片的数据路径
    roi_save_path = 'D://baozi//roi1//'           #保存切割后的图片数据的路径

    # 把所有的txt数据都转化成需要的数据
    img_label_infos = dict()
    img_path_list = glob.glob(yolo_dataset_path + "//*.jpg")
    print(len(img_path_list))
    print(img_path_list[0])
    for img_path_item in img_path_list:
        label_one_infos = []
        label_two_infos = []
        txt_path = img_path_item[:-3] + 'txt'
        # 判断是否存在这个txt
        if os.path.exists(txt_path):
            img = cv2.imread(img_path_item)
            width = img.shape[1]
            heigth = img.shape[0]
            with open(txt_path) as f:
                lines_infos = f.readlines()
            for line_item in lines_infos:
                line_item_split = line_item.split()
                if line_item_split[0] == '1':
                    line_item_split_float = np.array(line_item_split).astype(np.float)
                    small_width = int(line_item_split_float[3] * width)
                    small_height = int(line_item_split_float[4] * heigth)
                    top_x = int(line_item_split_float[1] * width - small_width / 2)
                    top_y = int(line_item_split_float[2] * heigth - small_height / 2)
                    bottom_x = int(line_item_split_float[1] * width + small_width / 2)
                    bottom_y = int(line_item_split_float[2] * heigth + small_height / 2)
                    center_x = int(line_item_split_float[1] * width)
                    center_y = int(line_item_split_float[2] * heigth)
                    label_one_infos.append([top_x, top_y, small_width, small_height, bottom_x, bottom_y,center_x,center_y])

                    # 这里进行保存roi图片，命名规则:图片名_top_x_top_y_small_width_small_height
                    roi_img = img[top_y:(top_y + small_height), top_x:(top_x + small_width)]
                    save_name = os.path.join(roi_save_path,
                                             os.path.basename(img_path_item)[:-4] + "_{}_{}_{}_{}.jpg".format(top_x,
                                                                                                              top_y,
                                                                                                              small_width,
                                                                                                              small_height))
                    cv2.imwrite(save_name, roi_img)
                    pass

                elif line_item_split[0] == '0':
                    line_item_split_float = np.array(line_item_split).astype(np.float)
                    small_width = int(line_item_split_float[3] * width)
                    small_height = int(line_item_split_float[4] * heigth)
                    top_x = int(line_item_split_float[1] * width - small_width / 2)
                    top_y = int(line_item_split_float[2] * heigth - small_height / 2)
                    bottom_x = int(line_item_split_float[1] * width + small_width / 2)
                    bottom_y = int(line_item_split_float[2] * heigth + small_height / 2)
                    center_x = int(line_item_split_float[1] * width)
                    center_y = int(line_item_split_float[2] * heigth)
                    label_two_infos.append(
                        [top_x, top_y, small_width, small_height, bottom_x, bottom_y, center_x, center_y])

            img_label_infos[img_path_item] = [label_one_infos.copy(), label_two_infos.copy()]
    for img_path, label_infos in img_label_infos.items():
        for plate_label_info_item in label_infos[0]:
            label_txt_path = os.path.join(roi_save_path, os.path.basename(img_path)[:-4] + "_{}_{}_{}_{}.txt".format(
                plate_label_info_item[0], plate_label_info_item[1], plate_label_info_item[2],
                plate_label_info_item[3], ))
            with open(label_txt_path, 'w') as f:
                for small_label_info_item in label_infos[1]:
                    # 判读是否在碗碟里面
                    if small_label_info_item[6]>plate_label_info_item[0]and small_label_info_item[6]<plate_label_info_item[4] and small_label_info_item[7]>plate_label_info_item[1]and small_label_info_item[7]<plate_label_info_item[5]:
                        center_x=float((small_label_info_item[0]-plate_label_info_item[0])+small_label_info_item[2]/2)/plate_label_info_item[2]
                        center_y=float((small_label_info_item[1]-plate_label_info_item[1]+small_label_info_item[3]/2))/plate_label_info_item[3]
                        small_width_scale=float(small_label_info_item[2])/plate_label_info_item[2]
                        small_height_scale=float(small_label_info_item[3])/plate_label_info_item[3]
                        f.writelines("{} {} {} {} {}\n".format(0,center_x,center_y,small_width_scale,small_height_scale))

        pass

创作分享不易，如果您觉得这篇blog对你有帮助，请留下一个免费的点赞，谢谢！