yolov8训练coco2017 数据集，并导出onnx

安装yolov8

pip install ultralytics -i http://mirrors.aliyun.com/pypi/simple/

下载coco 数据集

test 可以不下载 使用前三个链接的文件

wget http://images.cocodataset.org/zips/train2017.zip 
wget http://images.cocodataset.org/zips/val2017.zip 
wget http://images.cocodataset.org/annotations/annotations_trainval2017.zip
 
 
wget http://images.cocodataset.org/zips/test2017.zip 
wget http://images.cocodataset.org/annotations/image_info_test2017.zip 

创建文件夹

以下过程极其重要 必须完全一致

先将下载的数据集解压

1.创建data 文件夹
2.在data文件夹下 创建 images  labels 文件夹
3.将解压的 train2017 val2017下图片全部剪切到images文件夹下
4.将解压的annotations 目录剪切到data 目录下

最终形成以下目录树
├─data
│  ├─annotations
│  ├─images
│  └─labels

创建python 文件

在data 文件夹下创建py文件,并执行

# -*- encoding: utf-8 -*-
'''
File    :   cocotoyolo.py
Time    :   2023/04/25 16:53:42
Author  :   千秋
Version :   1.0
Contact :   spirit@qq.com
'''

#COCO 格式的数据集转化为 YOLO 格式的数据集
#--json_path 输入的json文件路径
#--save_path 保存的文件夹名字，默认为当前目录下的labels。

import os
import json
from tqdm import tqdm


def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = box[0] + box[2] / 2.0
    y = box[1] + box[3] / 2.0
    w = box[2]
    h = box[3]
#round函数确定(xmin, ymin, xmax, ymax)的小数位数
    x = round(x * dw, 6)
    w = round(w * dw, 6)
    y = round(y * dh, 6)
    h = round(h * dh, 6)
    return (x, y, w, h)

if __name__ == '__main__':
    #这里根据自己的json文件位置，换成自己的就行
    root = "./"
    json_trainfile = root+'annotations/instances_train2017.json' # COCO Object Instance 类型的标注
    json_valfile = root+'annotations/instances_val2017.json' # COCO Object Instance 类型的标注
    ana_txt_save_path = root+'labels/'  # 保存的路径

    traindata = json.load(open(json_trainfile, 'r'))
    valdata = json.load(open(json_valfile, 'r'))

    # 重新映射并保存class 文件
    if not os.path.exists(ana_txt_save_path):
        os.makedirs(ana_txt_save_path)

    id_map = {} # coco数据集的id不连续！重新映射一下再输出！
    with open(os.path.join(root, 'classes.txt'), 'w') as f:
        # 写入classes.txt
        for i, category in enumerate(traindata['categories']):
            f.write(f"{category['name']}\n")
            id_map[category['id']] = i



    '''
    保存train txt
    '''
    # print(id_map)
    #这里需要根据自己的需要，更改写入图像相对路径的文件位置。
    list_file = open(os.path.join(root, 'train2017.txt'), 'w')
    for img in tqdm(traindata['images']):
        filename = img["file_name"]
        img_width = img["width"]
        img_height = img["height"]
        img_id = img["id"]
        head, tail = os.path.splitext(filename)
        ana_txt_name = head + ".txt"  # 对应的txt名字，与jpg一致
        f_txt = open(os.path.join(ana_txt_save_path, ana_txt_name), 'w')
        for ann in traindata['annotations']:
            if ann['image_id'] == img_id:
                box = convert((img_width, img_height), ann["bbox"])
                f_txt.write("%s %s %s %s %s\n" % (id_map[ann["category_id"]], box[0], box[1], box[2], box[3]))
        f_txt.close()
        #将图片的相对路径写入train2017或val2017的路径
        list_file.write('data/images/%s.jpg\n' %(head))
    list_file.close()
    '''
    保存val txt
    '''
    # print(id_map)
    #这里需要根据自己的需要，更改写入图像相对路径的文件位置。
    list_file = open(os.path.join(root, 'val2017.txt'), 'w')
    for img in tqdm(valdata['images']):
        filename = img["file_name"]
        img_width = img["width"]
        img_height = img["height"]
        img_id = img["id"]
        head, tail = os.path.splitext(filename)
        ana_txt_name = head + ".txt"  # 对应的txt名字，与jpg一致
        f_txt = open(os.path.join(ana_txt_save_path, ana_txt_name), 'w')
        for ann in valdata['annotations']:
            if ann['image_id'] == img_id:
                box = convert((img_width, img_height), ann["bbox"])
                f_txt.write("%s %s %s %s %s\n" % (id_map[ann["category_id"]], box[0], box[1], box[2], box[3]))
        f_txt.close()
        #将图片的相对路径写入train2017或val2017的路径
        list_file.write('data/images/%s.jpg\n' %(head))
    list_file.close()

创建yaml 文件

在data 文件夹下 创建my.yaml 文件

path: E:\\Backup\\Desktop\\yolov8\\data  # 修改为自己的data路径
train: train2017.txt  # train images (relative to 'path') 118287 images
val: val2017.txt  # val images (relative to 'path') 5000 images

# Classes
names:
  0: person
  1: bicycle
  2: car
  3: motorcycle
  4: airplane
  5: bus
  6: train
  7: truck
  8: boat
  9: traffic light
  10: fire hydrant
  11: stop sign
  12: parking meter
  13: bench
  14: bird
  15: cat
  16: dog
  17: horse
  18: sheep
  19: cow
  20: elephant
  21: bear
  22: zebra
  23: giraffe
  24: backpack
  25: umbrella
  26: handbag
  27: tie
  28: suitcase
  29: frisbee
  30: skis
  31: snowboard
  32: sports ball
  33: kite
  34: baseball bat
  35: baseball glove
  36: skateboard
  37: surfboard
  38: tennis racket
  39: bottle
  40: wine glass
  41: cup
  42: fork
  43: knife
  44: spoon
  45: bowl
  46: banana
  47: apple
  48: sandwich
  49: orange
  50: broccoli
  51: carrot
  52: hot dog
  53: pizza
  54: donut
  55: cake
  56: chair
  57: couch
  58: potted plant
  59: bed
  60: dining table
  61: toilet
  62: tv
  63: laptop
  64: mouse
  65: remote
  66: keyboard
  67: cell phone
  68: microwave
  69: oven
  70: toaster
  71: sink
  72: refrigerator
  73: book
  74: clock
  75: vase
  76: scissors
  77: teddy bear
  78: hair drier
  79: toothbrush

创建训练文件

在data 文件夹同级创建train.py 文件，运行train.py 即完成训练 并导出onnx 模型,注意训练batch 一定要是16的倍数 才能保证输入batch 为1

from ultralytics import YOLO
if __name__=='__main__':
    # Create a new YOLO model from scratch
    model = YOLO('yolov8s.yaml')

    # Load a pretrained YOLO model (recommended for training)
    model = YOLO('yolov8s.pt')

    # Train the model using the 'coco128.yaml' dataset for 3 epochs
    results = model.train(data='data/my.yaml', epochs=30,batch=16,workers=1,imgsz=320)

    # Evaluate the model's performance on the validation set
    results = model.val()

    # Export the model to ONNX format
    success = model.export(format='onnx', opset=12,imgsz=320)