feat: 引入yolo标注结果，增加手动标注工具

[submodule "public/data/0.pdfs/a-complete-collection-of-bronzes-unearthed-in-china"]

	path = public/data/0.pdfs/a-complete-collection-of-bronzes-unearthed-in-china

	url = https://mirrors.sustech.edu.cn/git/12011404/a-complete-collection-of-bronzes-unearthed-in-china.git

[submodule "users/ycm/图中图提取/labelGo-Yolov5AutoLabelImg"]

	path = users/ycm/图中图提取/labelGo-Yolov5AutoLabelImg

	url = https://github.com/cnyvfang/labelGo-Yolov5AutoLabelImg.git

import json

import math

from typing import Tuple

import cv2

import numpy as np

from matplotlib import pyplot as plt

    cv_img = cv2.cvtColor(cv_img, cv2.COLOR_RGB2BGR)

    return cv_img

def cv_imwrite(filename, src, format=".png"):

    cv2.imencode(format ,src)[1].tofile(filename)

def cv_imshow(img):

    # plt.style.use("default")

    tmp = Image.fromarray(img).convert('L')

    return tmp

def cv_rect2slice(rect:Tuple[int, int, int, int]):

    x, y, w, h = rect

    return (y, y+h, x, x+w)

def slice2xyxy(slice:Tuple[int, int, int, int]):

    # python 的 numpy array，横着升高的是列，竖着向下的是行。而CV中是https://roboflow.com/formats/yolov5-pytorch-txt

    y1, y2, x1, x2 = slice

    return (x1, y1, x2, y2)

def xyxy2yolo_xywh(image_size:Tuple[int, int], box:Tuple[int, int, int, int]):

    # size是图片的大小 (width, height)

    # 比如， 

    # box = 'xmin': 1580.0, 'ymin': 758.667, 'xmax': 1638.6667, 'ymax': 818.6667

    # converts to yolo format

    # 拆解

    global_width, global_height = image_size

    x_min, y_min, x_max, y_max = box

    # 计算

    center_x = (x_min + x_max)/2.0  

    center_y = (y_min + y_max)/2.0  

    box_width = x_max - x_min  # xmax-xmin

    box_height = y_max - y_min  # ymax-ymin

    # 中心化

    center_x /= global_width

    box_width /= global_width

    center_y /= global_height

    box_height /= global_height

    return (center_x , center_y, box_width, box_height)

def yolo_xywh2cv_rect(image_size:Tuple[int, int], yolo_box:Tuple[float, float, float, float]):

    # 拆解

    global_width, global_height = image_size

    center_x , center_y, box_width, box_height = yolo_box

    # 计算

    center_x, box_width = center_x*global_width, box_width*global_width

    center_y, box_height = center_y*global_height, box_height*global_height

    x = center_x-box_width/2

    y = center_y-box_height/2

    process = lambda x, limit: min(max(int(round(x)), 0), limit)

    return (process(x, global_width), process(y, global_height), 

            process(box_width, global_width), process(box_height, global_height))

from deep_translator import (GoogleTranslator,

                             ChatGptTranslator,

                             MicrosoftTranslator,

Subproject commit b873a7d5482d152ded714120fcc7e34e7a038fb7

# 5. 按q退出程序。

# 可以调节的参数介绍：见下面 var_dict 的定义

from typing import Tuple

from typing import List, Tuple

from commons import *

from pathlib import Path

import json

# img = cv_imread(img_path)   

# cv_imshow(img)

classes_txt_path = output_folder/'classes.txt'

if not classes_txt_path.exists():

    with open(classes_txt_path, 'w') as f:

        f.write("image\n")

# 2. 处理函数

parameter_path = this_directory/'标注器保存的参数.json'

max_area_possible = 2900*4000

current_img, valid_rects = None, None

def save_rois(image, rects):

    path = f"{var_dict['number']['value']}-*.png"

def make_yolo(txt_path:str, array_shape:Tuple[int, int, int], cv_rects:List[Tuple[int, int, int, int]], label_type=0):

    # 保存YOLO风格标注框

    # 格式参考说明：https://roboflow.com/formats https://roboflow.com/formats/yolov8-pytorch-txt

    # yolo v8: class_id center_x center_y width height

    res = list(map(lambda rect: 

        " ".join([str(label_type)]+

                 [str(f) for f in 

                  xyxy2yolo_xywh((array_shape[1], array_shape[0]), slice2xyxy(cv_rect2slice(rect)))]), 

                   cv_rects))

    with open(txt_path, 'w') as f:

        f.write("\n".join(res)+"\n")

yolo_txt_path = lambda number: output_folder / f'第{number}页-{number}.txt'

inner_png_path = lambda number, subimage_num: output_folder / f"第{number}页-{number}-内图{subimage_num}.png"

def is_annotated(number:int):

    return yolo_txt_path(number).exists()

def remove_annotated(number:int):

    # 删除旧的标注结果

    # path = f"{number}-*.png"

    path = inner_png_path(number, "*").relative_to(output_folder).as_posix()

    for f in output_folder.glob(path):

        f.unlink()

    if len(rects)==0:

        with open(output_folder/f"{var_dict['number']['value']}-stub.png", 'w') as f:

            f.write("该页没有文物图片。\n")

    yolo_txt_path(number).unlink()

def make_sub_image_from_yolo(txt_path:str, number:int, image:np.ndarray):

    pass

current_img, valid_rects = None, None

def save_rois(image:np.ndarray, rects:List[Tuple[int, int, int, int]]):

    current_num = int(var_dict['number']['value'])

    yolo_path = yolo_txt_path(current_num)

    if is_annotated(current_num):

        print(f'警告：{current_num}号图片有已知标注成果，正在使用新的标注结果覆盖。')

        remove_annotated(current_num)

    make_yolo(yolo_path.as_posix(), image.shape, rects)

    # 保存小图片    

    for i, rect in enumerate(rects):

        roi = image[rect[1]:rect[1]+rect[3], rect[0]:rect[0]+rect[2]]

        cv2.imwrite((output_folder/f"{var_dict['number']['value']}-{i}.png").as_posix(), roi)

    print(f"enter: 确认标注，已保存标注结果到{output_folder/path}！")

        y1, y2, x1, x2 = cv_rect2slice(rect)

        roi = image[y1:y2, x1:x2]

        # cv2.imwrite((output_folder/f"{current_num}-{i}.png").as_posix(), roi)

        cv_imwrite(inner_png_path(current_num, i).as_posix(), roi)

    print(f"enter: 确认标注，已保存标注结果到{yolo_path}！")

import time

last_prompt_time = time.time()

        break

    key = cv2.waitKey(10) % 255

    if key == ord('s'):

        print(f"当前参数已保存到{parameter_path}")

        dump_json_file(var_dict, parameter_path)

    #https://blog.csdn.net/listener51/article/details/89353247

    # elif key==get_keycode('KEYCODE_ENTER'):

        print("down: 下一张图片。")

        cv2.setTrackbarPos('number', window_name, min(pages, var_dict['number']['value']+1))

    elif key==ord('j') or key==ord('k'):

        new_page = var_dict['number']['value']+1

        new_page = -1

        for new_page in range(var_dict['number']['value']+1, pages+1):

            path = f"{new_page}-*.png"

            if len(list(output_folder.glob(path)))==0:

            if not is_annotated(new_page):

                break

        cv2.setTrackbarPos('number', window_name, new_page)

    elif key == ord('q'):

%% Cell type:code id: tags:

``` python

from commons import *

```

%% Cell type:code id: tags:

``` python

image_size = 200, 100

cv_rect = (20, 30, 30, 20)

slice = cv_rect2slice(cv_rect)

slice

```

%% Cell type:code id: tags:

``` python

xyxy = slice2xyxy(slice)

xyxy

```

%% Cell type:code id: tags:

``` python

yolo = xyxy2yolo_xywh(image_size, xyxy)

yolo

```

%% Cell type:code id: tags:

``` python

cv_rect = yolo_xywh2cv_rect(image_size, cv_rect)

```