当前位置：首页 > news >正文

实例分割 | yolov11训练自己的数据集

news 2025/9/6 1:07:22

前言

因工作要求使用的都是yolov5系列的模型，今天学习一下最先进的yolov11，记录一下环境配置及训练过程。

1.项目下载及环境安装

源码位置：yolov11
在这里插入图片描述
可以看到，这里要求python版本大于等于3.8，我这里安装python3.10.

conda create -n yolov11 python=3.10
conda activate yolov11
pip install ultralytics -i https://pypi.tuna.tsinghua.edu.cn/simple

2.标注自己的数据集

标注实例分割数据集的工具有很多，这里建议labelme和AnyLabeling任意选一个。
如图所示，标注后的数据集是json格式的：
在这里插入图片描述
我们需要将其转成yolo系列需要的txt格式。
json转txt格式转化代码：

# json2txt.py
# json2txt.py
import cv2
import os
import json
import glob
import numpy as npclass_names = ["cls1_name", "cls2_name", "cls3_name", "cls4_name", "cls5_name"]def convert_json_label_to_yolov_seg_label():json_path = "F:/Desktop/hand/labels"  # 本地json路径json_files = glob.glob(json_path + "/*.json")# print(json_files)# 指定输出文件夹output_folder = "F:/Desktop/hand/labels_txt"  # txt存放路径if not os.path.exists(output_folder):os.makedirs(output_folder)for json_file in json_files:# print(json_file)with open(json_file, 'r') as f:json_info = json.load(f)img = cv2.imread(os.path.join(json_path, json_info["imagePath"]))height, width, _ = img.shapenp_w_h = np.array([[width, height]], np.int32)txt_file = os.path.join(output_folder, os.path.basename(json_file).replace(".json", ".txt"))with open(txt_file, "w") as f:for point_json in json_info["shapes"]:txt_content = ""np_points = np.array(point_json["points"], np.int32)label = point_json["label"]index = class_names.index(label)# print(type(label))norm_points = np_points / np_w_hnorm_points_list = norm_points.tolist()txt_content += str(index) + " " + " ".join([" ".join([str(cell[0]), str(cell[1])]) for cell in norm_points_list]) + "\n"f.write(txt_content)convert_json_label_to_yolov_seg_label()

转换后是这样的：
在这里插入图片描述
分割数据集，我们需要将转化成txt的数据集分割成训练集、验证集和测试集，这是分割代码：

# txt_split.py
# 将图片和标注数据按比例切分为 训练集和测试集
import shutil
import random
import os# 原始路径
image_original_path = "hhh/images/"
label_original_path = "hhh/labels_txt/"cur_path = os.getcwd()
#cur_path = 'D:/image_denoising_test/denoise/'
# 训练集路径
train_image_path = os.path.join(cur_path, "datasets/images/train/")
train_label_path = os.path.join(cur_path, "datasets/labels/train/")# 验证集路径
val_image_path = os.path.join(cur_path, "datasets/images/val/")
val_label_path = os.path.join(cur_path, "datasets/labels/val/")# 测试集路径
test_image_path = os.path.join(cur_path, "datasets/images/test/")
test_label_path = os.path.join(cur_path, "datasets/labels/test/")# 训练集目录
list_train = os.path.join(cur_path, "datasets/train.txt")
list_val = os.path.join(cur_path, "datasets/val.txt")
list_test = os.path.join(cur_path, "datasets/test.txt")train_percent = 0.8
val_percent = 0.1
test_percent = 0.1def del_file(path):for i in os.listdir(path):file_data = path + "\\" + ios.remove(file_data)def mkdir():if not os.path.exists(train_image_path):os.makedirs(train_image_path)else:del_file(train_image_path)if not os.path.exists(train_label_path):os.makedirs(train_label_path)else:del_file(train_label_path)if not os.path.exists(val_image_path):os.makedirs(val_image_path)else:del_file(val_image_path)if not os.path.exists(val_label_path):os.makedirs(val_label_path)else:del_file(val_label_path)if not os.path.exists(test_image_path):os.makedirs(test_image_path)else:del_file(test_image_path)if not os.path.exists(test_label_path):os.makedirs(test_label_path)else:del_file(test_label_path)def clearfile():if os.path.exists(list_train):os.remove(list_train)if os.path.exists(list_val):os.remove(list_val)if os.path.exists(list_test):os.remove(list_test)def main():mkdir()clearfile()file_train = open(list_train, 'w')file_val = open(list_val, 'w')file_test = open(list_test, 'w')total_txt = os.listdir(label_original_path)num_txt = len(total_txt)list_all_txt = range(num_txt)num_train = int(num_txt * train_percent)num_val = int(num_txt * val_percent)num_test = num_txt - num_train - num_valtrain = random.sample(list_all_txt, num_train)# train从list_all_txt取出num_train个元素# 所以list_all_txt列表只剩下了这些元素val_test = [i for i in list_all_txt if not i in train]# 再从val_test取出num_val个元素，val_test剩下的元素就是testval = random.sample(val_test, num_val)print("训练集数目：{}, 验证集数目：{}, 测试集数目：{}".format(len(train), len(val), len(val_test) - len(val)))for i in list_all_txt:name = total_txt[i][:-4]srcImage = image_original_path + name + '.jpg'srcLabel = label_original_path + name + ".txt"if i in train:dst_train_Image = train_image_path + name + '.jpg'dst_train_Label = train_label_path + name + '.txt'shutil.copyfile(srcImage, dst_train_Image)shutil.copyfile(srcLabel, dst_train_Label)file_train.write(dst_train_Image + '\n')elif i in val:dst_val_Image = val_image_path + name + '.jpg'dst_val_Label = val_label_path + name + '.txt'shutil.copyfile(srcImage, dst_val_Image)shutil.copyfile(srcLabel, dst_val_Label)file_val.write(dst_val_Image + '\n')else:dst_test_Image = test_image_path + name + '.jpg'dst_test_Label = test_label_path + name + '.txt'shutil.copyfile(srcImage, dst_test_Image)shutil.copyfile(srcLabel, dst_test_Label)file_test.write(dst_test_Image + '\n')file_train.close()file_val.close()file_test.close()if __name__ == "__main__":main()

3.编写训练代码并训练

我这里习惯使用代码训练，还有命令训练，如果感兴趣的朋友可以去官网了解。

# train.py
from ultralytics import YOLOif __name__ == '__main__':model = YOLO(r'ultralytics/cfg/models/11/yolo11-seg.yaml')  model.train(data=r'config.yaml',imgsz=640,epochs=800,single_cls=True,  batch=16,workers=10,device='0',)

配置文件：

# config.yaml
path: ../datasets/images  # 数据集所在路径
train: train  # 数据集路径下的train.txt
val: val  # 数据集路径下的val.txt
test: test  # 数据集路径下的test.txt# Classes
names:0: class1_name1: class2_name2: class3_name3: class4_name4: class5_name

这里的path改成你的数据集位置，如果txt_split.py在项目根目录下运行则不需要修改路径，只需要修改类别即可。
修改之后，只需要python train.py运行即可。

测试代码：

# test.py
from ultralytics import YOLO
# 加载训练好的模型，改为自己的路径
model = YOLO('runs/train/exp22/weights/best.pt')  #修改为训练好的路径
source = '11.jpg' #修改为自己的图片路径及文件名
# 运行推理，并附加参数
model.predict(source, save=True, imgsz=640)

转成onnx模型并运行:

yolo export model=runs/segment/train11/weights/best.pt imgsz=640 format=onnx opset=12 simplify
python examples/YOLOv8-Segmentation-ONNXRuntime-Python/main.py --model runs/segment/train5n/weights/bestv8.onnx