PPYOLOE目标检测训练框架使用说明_pp-yoloe源代码

数据集准备

1. 数据集标注参考博客【使用labelimg制作数据集】：使用labelimg制作数据集-CSDN博客

1. 标注数据注意事项，图片名称为纯数字，例如1289.jpg ;不要出现其他字符，否则下面代码转换会报错。

1. 标注好的数据集格式为VOC格式，AI Studio 中PPYOLOE用到的数据格式为coco数据格式，需要将标注好的数据进行格式转换。执行python voc2coco.py 即可！转换代码如下：

voc2coco.py

 
import os
import random
import shutil
import sys
import json
import glob
import xml.etree.ElementTree as ET
 
 
"""
代码来源：https://github.com/Stephenfang51/VOC_to_COCO
You only need to set the following three parts
1.val_files_num : num of validation samples from your all samples
2.test_files_num = num of test samples from your all samples
3.voc_annotations : path to your VOC dataset Annotations(最好写成绝对路径)
 
"""
val_files_num = 0
test_files_num = 0
voc_annotations = r'C:/Users/liq/Desktop/VOC/Annotations/'  #remember to modify the path
 
split = voc_annotations.split('/')
coco_name = split[-3]
del split[-3]
del split[-2]
del split[-1]
del split[0]
# print(split)
main_path = ''
for i in split:
    main_path += '/' + i
 
main_path = main_path + '/'
 
# print(main_path)
 
coco_path = os.path.join(main_path, coco_name+'_COCO/')
coco_images = os.path.join(main_path, coco_name+'_COCO/images')
coco_json_annotations = os.path.join(main_path, coco_name+'_COCO/annotations/')
xml_val = os.path.join(main_path, 'xml', 'xml_val/')
xml_test = os.path.join(main_path, 'xml/', 'xml_test/')
xml_train = os.path.join(main_path, 'xml/', 'xml_train/')
 
voc_images = os.path.join(main_path, coco_name, 'JPEGImages/')
 
 
 
 
#from https://www.php.cn/python-tutorials-424348.html
def mkdir(path):
    path=path.strip()
    path=path.rstrip("\\")
    isExists=os.path.exists(path)
    if not isExists:
        os.makedirs(path)
        print(path+' ----- folder created')
        return True
    else:
        print(path+' ----- folder existed')
        return False
#foler to make, please enter full path
 
 
 
 
mkdir(coco_path)
mkdir(coco_images)
mkdir(coco_json_annotations)
mkdir(xml_val)
mkdir(xml_test)
mkdir(xml_train)
 
 
#voc images copy to coco images
for i in os.listdir(voc_images):
    img_path = os.path.join(voc_images + i)
    shutil.copy(img_path, coco_images)
 
    # voc images copy to coco images
for i in os.listdir(voc_annotations):
    img_path = os.path.join(voc_annotations + i)
    shutil.copy(img_path, xml_train)
 
print("\n\n %s files copied to %s" % (val_files_num, xml_val))
 
for i in range(val_files_num):
    if len(os.listdir(xml_train)) > 0:
 
        random_file = random.choice(os.listdir(xml_train))
        #         print("%d) %s"%(i+1,random_file))
        source_file = "%s/%s" % (xml_train, random_file)
 
        if random_file not in os.listdir(xml_val):
            shutil.move(source_file, xml_val)
        else:
            random_file = random.choice(os.listdir(xml_train))
            source_file = "%s/%s" % (xml_train, random_file)
            shutil.move(source_file, xml_val)
    else:
        print('The folders are empty, please make sure there are enough %d file to move' % (val_files_num))
        break
 
for i in range(test_files_num):
    if len(os.listdir(xml_train)) > 0:
 
        random_file = random.choice(os.listdir(xml_train))
        #         print("%d) %s"%(i+1,random_file))
        source_file = "%s/%s" % (xml_train, random_file)
 
        if random_file not in os.listdir(xml_test):
            shutil.move(source_file, xml_test)
        else:
            random_file = random.choice(os.listdir(xml_train))
            source_file = "%s/%s" % (xml_train, random_file)
            shutil.move(source_file, xml_test)
    else:
        print('The folders are empty, please make sure there are enough %d file to move' % (val_files_num))
        break
 
print("\n\n" + "*" * 27 + "[ Done ! Go check your file ]" + "*" * 28)
 
# !/usr/bin/python
 
# pip install lxml
 
 
START_BOUNDING_BOX_ID = 1
PRE_DEFINE_CATEGORIES = None
 
 
# If necessary, pre-define category and its id
#  PRE_DEFINE_CATEGORIES = {"aeroplane": 1, "bicycle": 2, "bird": 3, "boat": 4,
#  "bottle":5, "bus": 6, "car": 7, "cat": 8, "chair": 9,
#  "cow": 10, "diningtable": 11, "dog": 12, "horse": 13,
#  "motorbike": 14, "person": 15, "pottedplant": 16,
#  "sheep": 17, "sofa": 18, "train": 19, "tvmonitor": 20}
 
"""
main code below are from
https://github.com/Tony607/voc2coco
"""
 
 
def get(root, name):
    vars = root.findall(name)
    return vars
 
 
def get_and_check(root, name, length):
    vars = root.findall(name)
    if len(vars) == 0:
        raise ValueError("Can not find %s in %s." % (name, root.tag))
    if length > 0 and len(vars) != length:
        raise ValueError(
            "The size of %s is supposed to be %d, but is %d."
            % (name, length, len(vars))
        )
    if length == 1:
        vars = vars[0]
    return vars
 
 
def get_filename_as_int(filename):
    try:
        filename = filename.replace("\\", "/")
        filename = os.path.splitext(os.path.basename(filename))[0]
        return int(filename)
    except:
        raise ValueError("Filename %s is supposed to be an integer." % (filename))
 
 
def get_categories(xml_files):
    """Generate category name to id mapping from a list of xml files.
    Arguments:
        xml_files {list} -- A list of xml file paths.
    Returns:
        dict -- category name to id mapping.
    """
    classes_names = []
    for xml_file in xml_files:
        tree = ET.parse(xml_file)
        root = tree.getroot()
        for member in root.findall("object"):
            classes_names.append(member[0].text)
    classes_names = list(set(classes_names))
    classes_names.sort()
    return {name: i for i, name in enumerate(classes_names)}
 
 
def convert(xml_files, json_file):
    json_dict = {"images": [], "type": "instances", "annotations": [], "categories": []}
    if PRE_DEFINE_CATEGORIES is not None:
        categories = PRE_DEFINE_CATEGORIES
    else:
        categories = get_categories(xml_files)
    bnd_id = START_BOUNDING_BOX_ID
    for xml_file in xml_files:
        tree = ET.parse(xml_file)
        root = tree.getroot()
        path = get(root, "path")
        if len(path) == 1:
            filename = os.path.basename(path[0].text)
        elif len(path) == 0:
            filename = get_and_check(root, "filename", 1).text
        else:
            raise ValueError("%d paths found in %s" % (len(path), xml_file))
        ## The filename must be a number
        image_id = get_filename_as_int(filename)
        size = get_and_check(root, "size", 1)
        width = int(get_and_check(size, "width", 1).text)
        height = int(get_and_check(size, "height", 1).text)
        image = {
            "file_name": filename,
            "height": height,
            "width": width,
            "id": image_id,
        }
        json_dict["images"].append(image)
        ## Currently we do not support segmentation.
        #  segmented = get_and_check(root, 'segmented', 1).text
        #  assert segmented == '0'
        for obj in get(root, "object"):
            category = get_and_check(obj, "name", 1).text
            if category not in categories:
                new_id = len(categories)
                categories[category] = new_id
            category_id = categories[category]
            bndbox = get_and_check(obj, "bndbox", 1)
            xmin = int(get_and_check(bndbox, "xmin", 1).text) - 1
            ymin = int(get_and_check(bndbox, "ymin", 1).text) - 1
            xmax = int(get_and_check(bndbox, "xmax", 1).text)
            ymax = int(get_and_check(bndbox, "ymax", 1).text)
            assert xmax > xmin
            assert ymax > ymin
            o_width = abs(xmax - xmin)
            o_height = abs(ymax - ymin)
            ann = {
                "area": o_width * o_height,
                "iscrowd": 0,
                "image_id": image_id,
                "bbox": [xmin, ymin, o_width, o_height],
                "category_id": category_id,
                "id": bnd_id,
                "ignore": 0,
                "segmentation": [],
            }
            json_dict["annotations"].append(ann)
            bnd_id = bnd_id + 1
 
    for cate, cid in categories.items():
        cat = {"supercategory": "none", "id": cid, "name": cate}
        json_dict["categories"].append(cat)
 
    os.makedirs(os.path.dirname(json_file), exist_ok=True)
    json_fp = open(json_file, "w")
    json_str = json.dumps(json_dict)
    json_fp.write(json_str)
    json_fp.close()
 
 
xml_val_files = glob.glob(os.path.join(xml_val, "*.xml"))
xml_test_files = glob.glob(os.path.join(xml_test, "*.xml"))
xml_train_files = glob.glob(os.path.join(xml_train, "*.xml"))
 
convert(xml_val_files, coco_json_annotations + 'val2017.json')
convert(xml_test_files, coco_json_annotations+'test2017.json')
convert(xml_train_files, coco_json_annotations + 'train2017.json')

或者使用voc2coco2.py

# !/usr/bin/python
# -*- coding: utf-8 -*-
'''
@Project ：always 
@File    ：voc2coco2.py
@Author  ：Lis
@Date    ：2023/7/28 18:23 
@Desc    : 
'''
import xml.etree.ElementTree as ET
import os
import json
 
coco = dict()
coco['images'] = []
coco['type'] = 'instances'
coco['annotations'] = []
coco['categories'] = []
 
category_set = dict()
image_set = set()
 
category_item_id = -1
image_id = 20180000000
annotation_id = 0
 
 
def addCatItem(name):
    global category_item_id
    category_item = dict()
    category_item['supercategory'] = 'none'
    category_item_id += 1
    category_item['id'] = category_item_id
    category_item['name'] = name
    coco['categories'].append(category_item)
    category_set[name] = category_item_id
    return category_item_id
 
 
def addImgItem(file_name, size):
    global image_id
    if file_name is None:
        raise Exception('Could not find filename tag in xml file.')
    if size['width'] is None:
        raise Exception('Could not find width tag in xml file.')
    if size['height'] is None:
        raise Exception('Could not find height tag in xml file.')
    image_id += 1
    image_item = dict()
    image_item['id'] = image_id
    image_item['file_name'] = file_name
    image_item['width'] = size['width']
    image_item['height'] = size['height']
    coco['images'].append(image_item)
    image_set.add(file_name)
    return image_id
 
 
def addAnnoItem(object_name, image_id, category_id, bbox):
    global annotation_id
    annotation_item = dict()
    annotation_item['segmentation'] = []
    seg = []
    # bbox[] is x,y,w,h
    # left_top
    seg.append(bbox[0])
    seg.append(bbox[1])
    # left_bottom
    seg.append(bbox[0])
    seg.append(bbox[1] + bbox[3])
    # right_bottom
    seg.append(bbox[0] + bbox[2])
    seg.append(bbox[1] + bbox[3])
    # right_top
    seg.append(bbox[0] + bbox[2])
    seg.append(bbox[1])
 
    annotation_item['segmentation'].append(seg)
 
    annotation_item['area'] = bbox[2] * bbox[3]
    annotation_item['iscrowd'] = 0
    annotation_item['ignore'] = 0
    annotation_item['image_id'] = image_id
    annotation_item['bbox'] = bbox
    annotation_item['category_id'] = category_id
    annotation_id += 1
    annotation_item['id'] = annotation_id
    coco['annotations'].append(annotation_item)
 
 
def parseXmlFiles(xml_path):
    for f in os.listdir(xml_path):
        if not f.endswith('.xml'):
            continue
 
        bndbox = dict()
        size = dict()
        current_image_id = None
        current_category_id = None
        file_name = None
        size['width'] = None
        size['height'] = None
        size['depth'] = None
 
        xml_file = os.path.join(xml_path, f)
        print(xml_file)
 
        tree = ET.parse(xml_file)
        root = tree.getroot()
        if root.tag != 'annotation':
            raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))
 
        # elem is <folder>, <filename>, <size>, <object>
        for elem in root:
            current_parent = elem.tag
            current_sub = None
            object_name = None
 
            if elem.tag == 'folder':
                continue
 
            if elem.tag == 'filename':
                file_name = elem.text
                if file_name in category_set:
                    raise Exception('file_name duplicated')
 
            # add img item only after parse <size> tag
            elif current_image_id is None and file_name is not None and size['width'] is not None:
                if file_name not in image_set:
                    current_image_id = addImgItem(file_name, size)
                    print('add image with {} and {}'.format(file_name, size))
                else:
                    raise Exception('duplicated image: {}'.format(file_name))
                    # subelem is <width>, <height>, <depth>, <name>, <bndbox>
            for subelem in elem:
                bndbox['xmin'] = None
                bndbox['xmax'] = None
                bndbox['ymin'] = None
                bndbox['ymax'] = None
 
                current_sub = subelem.tag
                if current_parent == 'object' and subelem.tag == 'name':
                    object_name = subelem.text
                    if object_name not in category_set:
                        current_category_id = addCatItem(object_name)
                    else:
                        current_category_id = category_set[object_name]
 
                elif current_parent == 'size':
                    if size[subelem.tag] is not None:
                        raise Exception('xml structure broken at size tag.')
                    size[subelem.tag] = int(subelem.text)
 
                # option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>
                for option in subelem:
                    if current_sub == 'bndbox':
                        if bndbox[option.tag] is not None:
                            raise Exception('xml structure corrupted at bndbox tag.')
                        bndbox[option.tag] = int(option.text)
 
                # only after parse the <object> tag
                if bndbox['xmin'] is not None:
                    if object_name is None:
                        raise Exception('xml structure broken at bndbox tag')
                    if current_image_id is None:
                        raise Exception('xml structure broken at bndbox tag')
                    if current_category_id is None:
                        raise Exception('xml structure broken at bndbox tag')
                    bbox = []
                    # x
                    bbox.append(bndbox['xmin'])
                    # y
                    bbox.append(bndbox['ymin'])
                    # w
                    bbox.append(bndbox['xmax'] - bndbox['xmin'])
                    # h
                    bbox.append(bndbox['ymax'] - bndbox['ymin'])
                    print('add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id,
                                                                   bbox))
                    addAnnoItem(object_name, current_image_id, current_category_id, bbox)
 
 
if __name__ == '__main__':
	# 只需要改动这两个参数就行了
    xml_path = r'C:\Users\Administrator\Desktop\皮革数据检测格式数据集\anno'  # 这是xml文件所在的地址
    json_file = r'C:\Users\Administrator\Desktop\皮革数据检测格式数据集\annotations.json'  # 这是你要生成的json文件
    parseXmlFiles(xml_path)
    json.dump(coco, open(json_file, 'w'))

Fork PPYOLOE项目并启动运行

PPYOLOE目标检测训练框架

PPYOLOE目标检测训练框架 - 飞桨AI Studio星河社区

按照main.ipynb流程依次执行即可！

1. 导入所需要的第三方库

1. 安装paddlex

1. 创建数据集目录 将标注的图像数据上传到 MyDataset/JPEGImages 目录下；将coco格式数据标签annotations.json放到MyDataset目录下。

1. 按比例切分数据集

1. git PaddleDetection代码

1. 进入PaddleDetection目录

1. 根据需求修改配置文件，比如检测的目标类别数 进入/home/aistudio/config_file/目录下，修改visdrone_detection.yml中num_classes参数

1. 开始训练

1. 训练完成后评估模型

1. 挑一张验证集的图片展示预测效果（可以到生成的目录下，打开查看）

1. 导出模型，即可使用FastDeploy进行快速推理