批量将PPM格式图片转化为JPG格式

将PPM格式图片转化为JPG格式

做图像识别的时候数据集常常是ppm格式的，虽然不影响建模训练，但是我们电脑往往不支持ppm格式的图像展示。
比如到做交通标志识别的时候用到的BelgiumTS交通数据集或者德国GTSRB数据集
下载后得到都是ppm格式的图像。

格式转化代码

from PIL import Image
import os

input_train_path = r"E:\test\BelgiumTSC_Training\Training"
output_train_path = r"E:\BelgiumTSC_JPG\Train_data"
input_test_path = r"E:\test\BelgiumTSC_Testing\Testing"
output_test_path = r"E:\BelgiumTSC_JPG\Test_data"


def batch_image(in_dir, out_dir):
    if not os.path.exists(out_dir):
        print(out_dir, 'is not existed.')
        os.mkdir(out_dir)

    if not os.path.exists(in_dir):
        print(in_dir, 'is not existed.')
        return -1

    directories = [d for d in os.listdir(in_dir) if os.path.isdir(os.path.join(in_dir, d))]
    for d in directories:
        # 每一类的路径
        label_directory = os.path.join(in_dir, d)
        new_directory = os.path.join(out_dir, d)
        out_folder = os.path.exists(out_dir + d)
        if not out_folder:
            os.mkdir(new_directory)
        file_names = [os.path.join(label_directory, f) for f in os.listdir(label_directory) if f.endswith(".ppm")]
        # file_names is every photo which is end with ".ppm"

        count = 0
        for files in file_names:
            file_path, extfilename = os.path.split(files)
            filename, extname = os.path.splitext(extfilename)
            out_file = filename + '.jpg'
            # print(filepath,',',filename, ',', out_file)
            im = Image.open(files)
            new_path = os.path.join(new_directory, out_file)
            print(count, ',', new_path)
            count = count + 1
            im.save(new_path)


if __name__ == '__main__':
    batch_image(input_test_path, output_test_path)
    batch_image(input_train_path, output_train_path)

转化后会保留原有的两级目录，方便建模训练。