提取mat标注文件中的关键点数量并输出到csv和txt文件（shanghaiTech数据集）

    关于shanghaiTech的介绍，可以看我之前的写的博客（https://blog.csdn.net/johnhamtom/article/details/104481186?spm=1001.2014.3001.5501）
    这里采用的文件结构如下图所示，其中images存放图片，ground_truth存放对应的标注文件：

    参考CSRNet的官方源码(https://github.com/leeyeehoo/CSRNet-pytorch)中的make_dataset.py可以得知，读取mat标注文件并获取其点坐标的代码如下：

mat = io.loadmat(img_path.replace('.jpg','.mat').replace('images','ground_truth').replace('IMG_','GT_IMG_'))
gt = mat["image_info"][0,0][0,0][0] #gt为用列表存储的点坐标对

    知道如何获取mat文件的点坐标后，直接批量读取mat文件，并在读取的时候记录关键点数量和图片名称即可，一些说明写在了注释中，代码如下：

import scipy.io as io
import glob
from image import *
import pandas as pd


# 设置根目录地址
root = r'.\Shanghai'
# 根据根目录地址合成图片地址
part_A_train = os.path.join(root, 'part_A_final', 'train_data', 'train_data', 'images')
part_A_val = os.path.join(root, 'part_A_final', 'train_data', 'val_data', 'images')
part_A_test = os.path.join(root, 'part_A_final', 'test_data', 'images')

part_B_train = os.path.join(root, 'part_B_final', 'train_data', 'train_data', 'images')
part_B_val = os.path.join(root, 'part_B_final', 'train_data', 'val_data', 'images')
part_B_test = os.path.join(root, 'part_B_final', 'test_data', 'images')

path_sets = [part_A_train, part_A_val, part_A_test, part_B_train, part_B_val, part_B_test]
save_path = ['part_A_train', 'part_A_val', 'part_A_test', 'part_B_train', 'part_B_val', 'part_B_test']

index_path_sets = 0

for name in save_path:
    # 读取图片路径
    img_paths = []
    for img_path in glob.glob(os.path.join(path_sets[index_path_sets], '*.jpg')):
        img_paths.append(img_path)

    index_path_sets = index_path_sets + 1

    df = pd.DataFrame(columns=['ImgName', 'Num'])  # 将标注框数量储存在CSV中

    #文件名
    filename = name +"_num"

    i=0

    with open(r".\Shanghai\annotations/" + filename + ".txt" , "w") as f:
        for img_path in img_paths:
            mat = io.loadmat(img_path.replace('.jpg','.mat').replace('images','ground_truth').replace('IMG_','GT_IMG_'))
            gt = mat["image_info"][0, 0][0, 0][0]
            # len(gt) 即为标注点数量
            # os.path.basename(img_path) 提取出图片文件名
            new = [os.path.basename(img_path), len(gt)]
            df.loc[i] = new
            print(new)
            i=i+1
            f.write(os.path.basename(img_path) + " " + str(len(gt)))
            f.write("\n")

    df.to_csv(r".\Shanghai\annotations/" + filename + ".csv", index=False)  # CSV文件路径

    结果如下所示：