网站域名查询网网站推广的方法搜索引擎

0 注意

图片命名纯数字命名，防止各种各样的报错，类别不要有空格。

1 验证的时候开启save_json选项

import warnings
warnings.filterwarnings('ignore')
import os
import numpy as np
from ultralytics import YOLOif __name__ == '__main__':model_path = f'runs/best.pt'model = YOLO(model_path) # 选择训练好的权重路径result = model.val(data='datasets/data.yaml',split='val', # split可以选择train、val、test 根据自己的数据集情况来选择.imgsz=640,batch=16,# iou=0.7,# rect=False,save_json=True, # 一定要开启此选项project='runs/val',)

运行命令

python val.py

2 数据集的格式转换成COCO格式

import os
import cv2
import json
from tqdm import tqdm
from sklearn.model_selection import train_test_split
import argparse# visdrone2019
classes = ['pedestrain', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor'] #自己的类别parser = argparse.ArgumentParser()
parser.add_argument('--image_path', default='',type=str, help="path of images")
parser.add_argument('--label_path', default='',type=str, help="path of labels .txt")
parser.add_argument('--save_path', default='data.json', type=str, help="if not split the dataset, give a path to a json file")
arg = parser.parse_args()def yolo2coco(arg):print("Loading data from ", arg.image_path, arg.label_path)assert os.path.exists(arg.image_path)assert os.path.exists(arg.label_path)originImagesDir = arg.image_path                                   originLabelsDir = arg.label_path# images dir nameindexes = os.listdir(originImagesDir)dataset = {'categories': [], 'annotations': [], 'images': []}for i, cls in enumerate(classes, 0):dataset['categories'].append({'id': i, 'name': cls, 'supercategory': 'mark'})# 标注的idann_id_cnt = 0for k, index in enumerate(tqdm(indexes)):# 支持 png jpg 格式的图片.txtFile = f'{index[:index.rfind(".")]}.txt'stem = index[:index.rfind(".")]# 读取图像的宽和高try:im = cv2.imread(os.path.join(originImagesDir, index))height, width, _ = im.shapeexcept Exception as e:print(f'{os.path.join(originImagesDir, index)} read error.\nerror:{e}')# 添加图像的信息if not os.path.exists(os.path.join(originLabelsDir, txtFile)):# 如没标签，跳过，只保留图片信息.continuedataset['images'].append({'file_name': index,'id': stem,'width': width,'height': height})with open(os.path.join(originLabelsDir, txtFile), 'r') as fr:labelList = fr.readlines()for label in labelList:label = label.strip().split()x = float(label[1])y = float(label[2])w = float(label[3])h = float(label[4])# convert x,y,w,h to x1,y1,x2,y2H, W, _ = im.shapex1 = (x - w / 2) * Wy1 = (y - h / 2) * Hx2 = (x + w / 2) * Wy2 = (y + h / 2) * H# 标签序号从0开始计算, coco2017数据集标号混乱，不管它了。cls_id = int(label[0])   width = max(0, x2 - x1)height = max(0, y2 - y1)dataset['annotations'].append({'area': width * height,'bbox': [x1, y1, width, height],'category_id': cls_id,'id': ann_id_cnt,'image_id': stem,'iscrowd': 0,# mask, 矩形是从左上角点按顺时针的四个顶点'segmentation': [[x1, y1, x2, y1, x2, y2, x1, y2]]})ann_id_cnt += 1# 保存结果with open(arg.save_path, 'w') as f:json.dump(dataset, f)print('Save annotation to {}'.format(arg.save_path))if __name__ == "__main__":yolo2coco(arg)

运行命令

pip install tidecv

python yolo2coco.py --image_path /hy-tmp/yolov11/datasets/images/val --label_path /hy-tmp/yolov11/datasets/labels/val --save_path /hy-tmp/yolov11/datasets/val_coco.json

4 使用get_COCO.py获取指标

import warnings
warnings.filterwarnings('ignore')
import argparse
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
from tidecv import TIDE, datasetsdef parse_opt():parser = argparse.ArgumentParser()parser.add_argument('--anno_json', type=str, default='', help='label coco json path')parser.add_argument('--pred_json', type=str, default='', help='pred coco json path')return parser.parse_known_args()[0]if __name__ == '__main__':opt = parse_opt()anno_json = opt.anno_jsonpred_json = opt.pred_jsonanno = COCO(anno_json)  # init annotations apiif 'info' not in anno.dataset:anno.dataset['info'] = {}  # 添加空的info字段# print(anno.dataset.keys())pred = anno.loadRes(pred_json)  # init predictions apieval = COCOeval(anno, pred, 'bbox')eval.evaluate()eval.accumulate()eval.summarize()tide = TIDE()tide.evaluate_range(datasets.COCO(anno_json), datasets.COCOResult(pred_json), mode=TIDE.BOX)tide.summarize()tide.plot(out_dir='result')

运行命令

python get_COCO_metrice.py --anno_json /hy-tmp/yolov11/datasets/val_coco.json --pred_json /hy-tmp/yolov11/runs/val/test/predictions.json