python - Train YOLOv3 for multiple classes, adapt from single class case

Question

I would like to do a train using YOLOv3 for multiple classes. I found a code for single class. And I tried to do for multiple classes, and I failed. So this is the code:

import glob
import os
import re

txt_file_paths = glob.glob(r"data/obj/*.txt")
for i, file_path in enumerate(txt_file_paths):
    # get image size
    with open(file_path, "r") as f_o:
        lines = f_o.readlines()

        text_converted = []
        for line in lines:
            print(line)
            numbers = re.findall("[0-9.]+", line)
            print(numbers)
            if numbers:

                # Define coordinates
                text = "{} {} {} {} {}".format(0, numbers[1], numbers[2], numbers[3], numbers[4])
                text_converted.append(text)
                print(i, file_path)
                print(text)
        # Write file
        with open(file_path, 'w') as fp:
            for item in text_converted:
                fp.writelines("%s
" % item)

Can anyone help to adapt to multiple classes?

Answer 1

等待大神解答