YOLOv9训练自己的数据集

1. YOLOv9原理介绍

论文： 2402.13616.pdf (arxiv.org)

代码：GitHub - WongKinYiu/yolov9: Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
摘要： 如今的深度学习方法重点关注如何设计最合适的目标函数，从而使得模型的预测结果能够最接近真实情况。同时，必须设计一个适当的架构，可以帮助获取足够的信息进行预测。然而，现有方法忽略了一个事实，即当输入数据经过逐层特征提取和空间变换时，大量信息将会丢失。因此，YOLOv9 深入研究了数据通过深度网络传输时数据丢失的重要问题，即信息瓶颈和可逆函数。作者提出了可编程梯度信息（programmable gradient information，PGI）的概念，来应对深度网络实现多个目标所需要的各种变化。PGI 可以为目标任务计算目标函数提供完整的输入信息，从而获得可靠的梯度信息来更新网络权值。此外，研究者基于梯度路径规划设计了一种新的轻量级网络架构，即通用高效层聚合网络（Generalized Efficient Layer Aggregation Network，GELAN）。该架构证实了 PGI 可以在轻量级模型上取得优异的结果。研究者在基于 MS COCO 数据集的目标检测任务上验证所提出的 GELAN 和 PGI。结果表明，与其他 SOTA 方法相比，GELAN 仅使用传统卷积算子即可实现更好的参数利用率。对于 PGI 而言，它的适用性很强，可用于从轻型到大型的各种模型。我们可以用它来获取完整的信息，从而使从头开始训练的模型能够比使用大型数据集预训练的 SOTA 模型获得更好的结果。对比结果如图1所示。

1.1 YOLOv9各个模型介绍

1.2 PGI

1.3 GELAN

2. VisDrone2019-DET数据集介绍

VisDrone2019-DET是由天津大学机器学习和数据挖掘实验室AISKYEYE团队收集。该数据集是由无人机在不同地点，不同高度拍摄的广域航拍图像，训练集包括 6471张图片，验证集包括548张图片，分辨率约为2000*1500像素，包括10个类别（pedestrian, person, car, van, bus, truck, motor, bicycle, awning-tricycle, and tricycle）

2.1 数据集转换

'''
Author: 刘鸿燕 13752614153@163.com
Date: 2022-05-09 14:05:05
LastEditors: 刘鸿燕 13752614153@163.com
LastEditTime: 2022-05-09 15:38:09
FilePath: \VisDrone2019\data_process\visDrone2019_txt2txt_yolo.py
Description: 这是默认设置,请设置`customMade`, 打开koroFileHeader查看配置 进行设置: https://github.com/OBKoro1/koro1FileHeader/wiki/%E9%85%8D%E7%BD%AE
'''
import os
from pathlib import Path
from PIL import Image
from tqdm import tqdm

def visdrone2yolo(dir):
    def convert_box(size, box):
        #Convert VisDrone box to YOLO CxCywh box,坐标进行了归一化
        dw = 1. / size[0]
        dh = 1. / size[1]
        return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh

    # (dir / 'labels').mkdir(parents=True, exist_ok=True)  # make labels directory
    (dir / 'Annotations_YOLO').mkdir(parents=True, exist_ok=True)  # make labels directory
    pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}')
    for f in pbar:
        img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size
        lines = []
        with open(f, 'r') as file:  # read annotation.txt
            for row in [x.split(',') for x in file.read().strip().splitlines()]:
                if row[4] == '0':  # VisDrone 'ignored regions' class 0
                    continue
                cls = int(row[5]) - 1
                box = convert_box(img_size, tuple(map(int, row[:4])))
                lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n")
                with open(str(f).replace(os.sep + 'annotations' + os.sep, os.sep + 'Annotations_YOLO' + os.sep), 'w') as fl:
                    fl.writelines(lines)  # write label.txt


dir = Path(r'E:\data\VisDrone2019-DET')  # dataset文件夹下Visdrone2019文件夹路径
# Convert
for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev':
    visdrone2yolo(dir / d)  # convert VisDrone annotations to YOLO labels

2.2 较为通用的方法

数据集划分
通过split_train_val.py得到trainval.txt、val.txt、test.txt

# coding:utf-8
 
import os
import random
import argparse
 
parser = argparse.ArgumentParser()
#xml文件的地址，根据自己的数据进行修改 xml一般存放在Annotations下
parser.add_argument('--xml_path', default='Annotations', type=str, help='input xml label path')
#数据集的划分，地址选择自己数据下的ImageSets/Main
parser.add_argument('--txt_path', default='ImageSets/Main', type=str, help='output txt label path')
opt = parser.parse_args()
 
trainval_percent = 0.9
train_percent = 0.8
xmlfilepath = opt.xml_path
txtsavepath = opt.txt_path
total_xml = os.listdir(xmlfilepath)
if not os.path.exists(txtsavepath):
    os.makedirs(txtsavepath)
 
num = len(total_xml)
list_index = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list_index, tv)
train = random.sample(trainval, tr)
 
file_trainval = open(txtsavepath + '/trainval.txt', 'w')
file_test = open(txtsavepath + '/test.txt', 'w')
file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')
 
for i in list_index:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        file_trainval.write(name)
        if i in train:
            file_train.write(name)
        else:
            file_val.write(name)
    else:
        file_test.write(name)
 
file_trainval.close()
file_train.close()
file_val.close()
file_test.close()

通过voc2yolo转化成yolo格式

# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os
from os import getcwd
 
sets = ['train', 'val', 'test']
classes = ["crazing","inclusion","patches","pitted_surface","rolled-in_scale","scratches"]   # 改成自己的类别
abs_path = os.getcwd()
print(abs_path)
 
def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    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), encoding='UTF-8')
    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
        #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))
        b1, b2, b3, b4 = b
        # 标注越界修正
        if b2 > w:
            b2 = w
        if b4 > h:
            b4 = h
        b = (b1, b2, b3, b4)
        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/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open('%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write(abs_path + '/images/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

3. YOLOv9 训练自己的数据集

3.1 修改VisDrone.yaml

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset by Tianjin University
# Example usage: python train.py --data VisDrone.yaml
# parent
# ├── yolov5
# └── datasets
#     └── VisDrone  ← downloads here (2.3 GB)


# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: E:\data\VisDrone2019-DET\VisDrone2019\images  # dataset root dir
train: train  # train images (relative to 'path')  6471 images
val: val  # val images (relative to 'path')  548 images
test:   # test images (optional)  1610 images

# Classes
names:
  0: pedestrian
  1: people
  2: bicycle
  3: car
  4: van
  5: truck
  6: tricycle
  7: awning-tricycle
  8: bus
  9: motor

3.2 修改train_dual.py

def parse_opt(known=False):
    parser = argparse.ArgumentParser()
    # parser.add_argument('--weights', type=str, default=ROOT / 'yolo.pt', help='initial weights path')
    # parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
    parser.add_argument('--weights', type=str, default='', help='initial weights path')
    parser.add_argument('--cfg', type=str, default='models/detect/yolov9.yaml', help='model.yaml path')
    parser.add_argument('--data', type=str, default=ROOT / 'data/VisDrone.yaml', help='dataset.yaml path')
    parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch-high.yaml', help='hyperparameters path')
    parser.add_argument('--epochs', type=int, default=240, help='total training epochs')
    parser.add_argument('--batch-size', type=int, default=4, help='total batch size for all GPUs, -1 for autobatch')
    parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
    parser.add_argument('--rect', action='store_true', help='rectangular training')
    parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
    parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
    parser.add_argument('--noval', action='store_true', help='only validate final epoch')
    parser.add_argument('--noautoanchor', action='store_true', help='disable AutoAnchor')
    parser.add_argument('--noplots', action='store_true', help='save no plot files')
    parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
    parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
    parser.add_argument('--cache', type=str, nargs='?', const='ram', help='image --cache ram/disk')
    parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
    parser.add_argument('--device', default='0', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
    parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
    parser.add_argument('--optimizer', type=str, choices=['SGD', 'Adam', 'AdamW', 'LION'], default='SGD', help='optimizer')
    parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
    parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)')
    parser.add_argument('--project', default=ROOT / 'VisDrone', help='save to project/name')
    parser.add_argument('--name', default='yolov9', help='save to project/name')
    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--quad', action='store_true', help='quad dataloader')
    parser.add_argument('--cos-lr', action='store_true', help='cosine LR scheduler')
    parser.add_argument('--flat-cos-lr', action='store_true', help='flat cosine LR scheduler')
    parser.add_argument('--fixed-lr', action='store_true', help='fixed LR scheduler')
    parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
    parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)')
    parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone=10, first3=0 1 2')
    parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)')
    parser.add_argument('--seed', type=int, default=0, help='Global training seed')
    parser.add_argument('--local_rank', type=int, default=-1, help='Automatic DDP Multi-GPU argument, do not modify')
    parser.add_argument('--min-items', type=int, default=0, help='Experimental')
    parser.add_argument('--close-mosaic', type=int, default=0, help='Experimental')

    # Logger arguments
    parser.add_argument('--entity', default=None, help='Entity')
    parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='Upload data, "val" option')
    parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval')
    parser.add_argument('--artifact_alias', type=str, default='latest', help='Version of dataset artifact to use')

    return parser.parse_known_args()[0] if known else parser.parse_args()

3.3 开启训练

python train_dual.py