YOLO-V4 Pytorch版本训练自建数据集和预测

# makeTxt.py 制作训练集和测试集列表的脚本。

# 需要将脚本中的所有路径进行更改，手动改就好，改成自己数据集存储的地方，我建议大家使用绝对路径（不要出现中文）。

import os

import random

trainval_percent = 0.2  # 可自行进行调节

train_percent = 1

xmlfilepath = '../annotations'

txtsavepath = '../images'

total_xml = os.listdir(xmlfilepath)

num = len(total_xml)

list = range(num)

tv = int(num * trainval_percent)

tr = int(tv * train_percent)

trainval = random.sample(list, tv)

train = random.sample(trainval, tr)

# ftrainval = open('ImageSets/Main/trainval.txt', 'w')

ftest = open('../ImageSets/test.txt', 'w')

ftrain = open('../ImageSets/train.txt', 'w')

# fval = open('ImageSets/Main/val.txt', 'w')

for i in list:

    name = total_xml[i][:-4] + '\n'

    if i in trainval:

        # ftrainval.write(name)

        if i in train:

            ftest.write(name)

        # else:

        # fval.write(name)

    else:

        ftrain.write(name)

# ftrainval.close()

ftrain.close()

# fval.close()

ftest.close()

#!/usr/bin/env python

# -*- coding:utf-8 -*-

# voc_label.py 生成YOLO可以读取的数据集格式，最后会在labels文件夹下面生成每个图片的标签文件，txt结尾。

import xml.etree.ElementTree as ET

import pickle

import os

from os import listdir, getcwd

from os.path import join

sets = ['train', 'test']

classes = ['a', 'b', 'c']  # 自己训练的类别

def convert(size, box):

    dw = 1. / size[0]

    dh = 1. / size[1]

    x = (box[0] + box[1]) / 2.0

    y = (box[2] + box[3]) / 2.0

    w = box[1] - box[0]

    h = box[3] - box[2]

    x = x * dw

    w = w * dw

    y = y * dh

    h = h * dh

    return (x, y, w, h)

def convert_annotation(image_id):

    in_file = open('../annotations/%s.xml' % (image_id))

    out_file = open('../labels/%s.txt' % (image_id), 'w')

    tree = ET.parse(in_file)

    root = tree.getroot()

    size = root.find('size')

    w = int(size.find('width').text)

    h = int(size.find('height').text)

    for obj in root.iter('object'):

        difficult = obj.find('difficult').text

        cls = obj.find('name').text

        if cls not in classes or int(difficult) == 1:

            continue

        cls_id = classes.index(cls)

        xmlbox = obj.find('bndbox')

        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),

             float(xmlbox.find('ymax').text))

        print(root.find('filename').text)

        bb = convert((w, h), b)

        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

wd = getcwd()

for image_set in sets:

    if not os.path.exists('../labels/'):

        os.makedirs('../labels/')

    image_ids = open('../ImageSets/%s.txt' % (image_set)).read().strip().split()

    list_file = open('../%s.txt' % (image_set), 'w')

    for image_id in image_ids:

        list_file.write('../images/%s.jpg\n' % (image_id))

        convert_annotation(image_id)

    list_file.close()