训练自己的yolox

标注用  labelme
标注完成以后放在一个文件夹里面

创建一个文件夹  比葫芦画瓢和我这样放

import os
import numpy as np
import codecs
import json
from glob import glob
import cv2
import shutil
from sklearn.model_selection import train_test_split

# 1.标签路径
labelme_path =r"F:\1\2/"  # 原始labelme标注数据路径
saved_path = "./VOC2007/"  # 保存路径
isUseTest = True  # 是否创建test集
print (labelme_path)

# 2.创建要求文件夹
if not os.path.exists(saved_path + "Annotations"):  # xmls_path
    os.makedirs(saved_path + "Annotations")
if not os.path.exists(saved_path + "JPEGImages/"):  # images_path
    os.makedirs(saved_path + "JPEGImages/")
if not os.path.exists(saved_path + "ImageSets/Main/"):  # train_val_txt_path
    os.makedirs(saved_path + "ImageSets/Main/")

# 3.获取待处理文件
files = glob(labelme_path + "*.json")
files = [i.replace("\\", "/").split("/")[-1].split(".json")[0] for i in files]
# print(files)

# 4.读取标注信息并写入 xml
for json_file_ in files:
    json_filename = labelme_path + json_file_ + ".json"
    json_file = json.load(open(json_filename, "r", encoding="utf-8"))
    height, width, channels = cv2.imread(labelme_path + json_file_ + ".jpg").shape
    with codecs.open(saved_path + "Annotations/" + json_file_ + ".xml", "w", "utf-8") as xml:
        xml.write('<annotation>\n')
        xml.write('\t<folder>' + 'VOC_data' + '</folder>\n')
        xml.write('\t<filename>' + json_file_ + ".jpg" + '</filename>\n')
        xml.write('\t<source>\n')
        xml.write('\t\t<database>VOC Data</database>\n')
        xml.write('\t\t<image>flickr</image>\n')
        xml.write('\t\t<flickrid>NULL</flickrid>\n')
        xml.write('\t</source>\n')
        xml.write('\t<size>\n')
        xml.write('\t\t<width>' + str(width) + '</width>\n')
        xml.write('\t\t<height>' + str(height) + '</height>\n')
        xml.write('\t\t<depth>' + str(channels) + '</depth>\n')
        xml.write('\t</size>\n')
        xml.write('\t\t<segmented>0</segmented>\n')
        for multi in json_file["shapes"]:
            points = np.array(multi["points"])
            labelName = multi["label"]
            xmin = min(points[:, 0])
            xmax = max(points[:, 0])
            ymin = min(points[:, 1])
            ymax = max(points[:, 1])
            label = multi["label"]
            if xmax <= xmin:
                pass
            elif ymax <= ymin:
                pass
            else:
                xml.write('\t<object>\n')
                xml.write('\t\t<name>' + labelName + '</name>\n')
                xml.write('\t\t<pose>Unspecified</pose>\n')
                xml.write('\t\t<truncated>1</truncated>\n')
                xml.write('\t\t<difficult>0</difficult>\n')
                xml.write('\t\t<bndbox>\n')
                xml.write('\t\t\t<xmin>' + str(int(xmin)) + '</xmin>\n')
                xml.write('\t\t\t<ymin>' + str(int(ymin)) + '</ymin>\n')
                xml.write('\t\t\t<xmax>' + str(int(xmax)) + '</xmax>\n')
                xml.write('\t\t\t<ymax>' + str(int(ymax)) + '</ymax>\n')
                xml.write('\t\t</bndbox>\n')
                xml.write('\t</object>\n')
                # print(json_filename, xmin, ymin, xmax, ymax, label)
        xml.write('</annotation>')

# 5.将图片复制到 VOC2007/JPEGImages/目录下
image_files = glob(labelme_path + "*.jpg")
print("copy image files to VOC007/JPEGImages/")
for image in image_files:
    shutil.copy(image, saved_path + "JPEGImages/")

# 6.split files for txt
txtsavepath = saved_path + "ImageSets/Main/"
ftrainval = open(txtsavepath + '/trainval.txt', 'w')
ftest = open(txtsavepath + '/test.txt', 'w')
ftrain = open(txtsavepath + '/train.txt', 'w')
fval = open(txtsavepath + '/val.txt', 'w')
total_files = glob("data/VOCdevkit/VOC2007/Annotations/*.xml")
total_files = [i.replace("\\", "/").split("\\")[-1].split(".xml")[0] for i in total_files]
trainval_files = []
test_files = []
print(total_files)
print(trainval_files)
if isUseTest:
    trainval_files, test_files = train_test_split(total_files, test_size=0.3, random_state=55)
else:
    trainval_files = total_files
for file in trainval_files:
    ftrainval.write(file + "\n")
# split
train_files, val_files = train_test_split(trainval_files, test_size=0.3, random_state=55)
# train
for file in train_files:
    ftrain.write(file + "\n")
# val
for file in val_files:
    fval.write(file + "\n")
for file in test_files:
    # print(file)
    ftest.write(file + "\n")
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

修改

运行   发现错误 ValueError：当 n_samples=0、test_size=0.3 和 train_size=None 时，生成的训练集将为空。调整任何上述参数。

 简单查了下

这种错误一般有   路径不对

json  和  图片不在一个文件夹里面

sklearn  版本不对  或者 train_test_split 的参数写的不对（感觉和这没有关系，我的sklearn 1.0.2
）

发现原因

 

 我们没有这个文件夹

所以改成下面这样

 已经成功了

检查一下

在训练的时候老出现路径错误

把4个txt  删掉   跑下面这个脚本

import os
import random

random.seed(0)

xmlfilepath = r'./VOC2007/Annotations'
saveBasePath = r"./VOC2007/ImageSets/Main"

trainval_percent = 0.8
train_percent = 1

temp_xml = os.listdir(xmlfilepath)
total_xml = []
for xml in temp_xml:
    if xml.endswith(".xml"):
        total_xml.append(xml)

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)

print("train and val size", tv)
print("traub suze", tr)
ftrainval = open(os.path.join(saveBasePath, 'trainval.txt'), 'w')
ftest = open(os.path.join(saveBasePath, 'test.txt'), 'w')
ftrain = open(os.path.join(saveBasePath, 'train.txt'), 'w')
fval = open(os.path.join(saveBasePath, 'val.txt'), 'w')

for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftrain.write(name)
        else:
            fval.write(name)
    else:
        ftest.write(name)

ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

效果

4个TXT  里面都有东西  voc  2007 数据集制作完成。

修改类别

修改为自己的类别名

写成我这样   把原来的删掉   

data_dir=写绝对路径

 

 windows    下work=1

 先跑

python setup.py install
训练命令

 python tools/train.py -f exps/example/yolox_voc/yolox_voc_s.py -d 1 -b 1 --fp16 -c w/yolox_s.pth
 

等着就行了

帮助：

断了  用下面这个命令接着训练

 python tools/train.py -f exps/example/yolox_voc/yolox_voc_s.py -d 1 -b 1 --fp16 -c F:\YOLOX-main\YOLOX_outputs\yolox_voc_s\latest_ckpt.pth --resume
 

修改  json的类别  比如  之前是  老头  改成  laoto

# -*- encoding: utf-8 -*-
import os
import json


def Edit_label(json_dir, new_label='zangdian'):
    json_files = os.listdir(json_dir)
    json_dict = {}
    for json_file in json_files:

        #  只获取json文件
        if json_file[-4:] != 'json':
            continue
        jsonfile = json_dir + '/' + json_file
        with open(jsonfile, 'r', encoding='utf-8') as jf:
            info = json.load(jf)

            # 找到位置进行修改
            for i, label in enumerate(info['shapes']):
                info['shapes'][i]['label'] = new_label

            # 使用新字典替换修改后的字典
            json_dict = info

        # 将替换后的内容写入原文件
        with open(jsonfile, 'w') as fw:
            json.dump(json_dict, fw)


if __name__ == '__main__':
    #  文件夹目录
    json_dir = r'F:\w2'
    new_label = 'zangdian'
    Edit_label(json_dir, new_label)
    print('OK!')

 

就好了