当前位置: 首页 > news >正文

做美妆网站名称向日葵seo

做美妆网站名称,向日葵seo,wordpress主题慢,益阳 网站制作维护一般都是用labeleme进行标注 标注格式都是json 然后根据不同的格式进行数据标注转换: 1.逐个json转xml: 当我们在使用数据集训练计算机视觉模型时,常常会遇到有的数据集只给了单个的json annotation文件,而模型所需要的annotation是基于每…

一般都是用labeleme进行标注 标注格式都是json

然后根据不同的格式进行数据标注转换:

1.逐个json转xml:

当我们在使用数据集训练计算机视觉模型时,常常会遇到有的数据集只给了单个的json annotation文件,而模型所需要的annotation是基于每个图片的xml annotation文件

# translate coco_json to xml
import os
import time
import json
import pandas as pd
from tqdm import tqdm
from pycocotools.coco import COCOdef trans_id(category_id):names = []namesid = []for i in range(0, len(cats)):names.append(cats[i]['name'])namesid.append(cats[i]['id'])# print('id:{1}\t {0}'.format(names[i], namesid[i]))index = namesid.index(category_id)return indexroot = r''  # 你下载的 COCO 数据集所在目录
dataType = '2019'
anno = r'' # annotation json 文件所在位置
xml_dir = r'' # 导出的xml文件所在的位置coco = COCO(anno)  # 读文件
cats = coco.loadCats(coco.getCatIds())  # 这里loadCats就是coco提供的接口,获取类别# Create anno dir
dttm = time.strftime("%Y%m%d%H%M%S", time.localtime())
# if os.path.exists(xml_dir):
#     os.rename(xml_dir, xml_dir + dttm)
# os.mkdir(xml_dir)with open(anno, 'r') as load_f:f = json.load(load_f)imgs = f['images']  # json文件的img_id和图片对应关系 imgs列表表示多少张图cat = f['categories']
df_cate = pd.DataFrame(f['categories'])  # json中的类别
df_cate_sort = df_cate.sort_values(["id"], ascending=True)  # 按照类别id排序
categories = list(df_cate_sort['name'])  # 获取所有类别名称
print('categories = ', categories)
df_anno = pd.DataFrame(f['annotations'])  # json中的annotationfor i in tqdm(range(len(imgs))):  # 大循环是images所有图片xml_content = []file_name = imgs[i]['file_name']  # 通过img_id找到图片的信息height = imgs[i]['height']img_id = imgs[i]['id']width = imgs[i]['width']# xml文件添加属性xml_content.append("<annotation>")xml_content.append("	<folder>VOC2007</folder>")xml_content.append("	<filename>" + file_name.split('/')[1].split('.')[0] + '.jpg' + "</filename>")xml_content.append("	<size>")xml_content.append("		<width>" + str(width) + "</width>")xml_content.append("		<height>" + str(height) + "</height>")xml_content.append("	</size>")xml_content.append("	<segmented>0</segmented>")# 通过img_id找到annotationsannos = df_anno[df_anno["image_id"].isin([img_id])]  # (2,8)表示一张图有两个框for index, row in annos.iterrows():  # 一张图的所有annotation信息bbox = row["bbox"]category_id = row["category_id"]# cate_name = categories[trans_id(category_id)]cate_name = cat[category_id-1]['name']# add new objectxml_content.append("<object>")xml_content.append("<name>" + cate_name + "</name>")xml_content.append("<pose>Unspecified</pose>")xml_content.append("<truncated>0</truncated>")xml_content.append("<difficult>0</difficult>")xml_content.append("<bndbox>")xml_content.append("<xmin>" + str(int(bbox[0])) + "</xmin>")xml_content.append("<ymin>" + str(int(bbox[1])) + "</ymin>")xml_content.append("<xmax>" + str(int(bbox[0] + bbox[2])) + "</xmax>")xml_content.append("<ymax>" + str(int(bbox[1] + bbox[3])) + "</ymax>")xml_content.append("</bndbox>")xml_content.append("</object>")xml_content.append("</annotation>")x = xml_contentxml_content = [x[i] for i in range(0, len(x)) if x[i] != "\n"]### list存入文件xml_path = os.path.join(xml_dir, file_name.replace('.jpg', '.xml'))with open(xml_path, 'w+', encoding="utf8") as f:f.write('\n'.join(xml_content))xml_content[:] = []

2.逐个xml转txt:

# xml_to_yolo_txt.py
# 此代码和VOC_KITTI文件夹同目录
import os
import xml.etree.ElementTree as ET
# 这里的类名为我们xml里面的类名,顺序a按照Readme文件,或者也可以不考虑顺序
# 其中thermal类别比rgb类别多了dog和deer,生成txt注意区分  # 我统一都写成thermal的类别了
class_names = ['person','bike','car','motor', 'bus', 'train','truck','light','hydrant', 'sign','dog','deer','skateboard','stroller', 'scooter', 'other vehicle']
# class_names = ['person','bike','car','motor', 'bus', 'train','truck','light','hydrant', 'sign',
#                'skateboard','stroller','scooter','other vehicle' ]
# xml文件路径
path = 'G:/红外数据集-FLIR2/FLIR2_yolo_xml/images_rgb_val/data/'
# 转换一个xml文件为txt
def single_xml_to_txt(xml_file):tree = ET.parse(os.path.join(path, xml_file))root = tree.getroot()# 保存的txt文件路径txt_file = os.path.join('G:/红外数据集-FLIR2/FLIR2_yolo_txt/images_rgb_val/data/', xml_file.split('.')[0]+'.txt')with open(txt_file, 'w') as txt_file:for member in root.findall('object'):#filename = root.find('filename').textpicture_width = int(root.find('size')[0].text)picture_height = int(root.find('size')[1].text)class_name = member[0].text# 类名对应的indexclass_num = class_names.index(class_name)box_x_min = int(member[4][0].text) # 左上角横坐标box_y_min = int(member[4][1].text) # 左上角纵坐标box_x_max = int(member[4][2].text) # 右下角横坐标box_y_max = int(member[4][3].text) # 右下角纵坐标# 转成相对位置和宽高x_center = float(box_x_min + box_x_max) / (2 * picture_width)y_center = float(box_y_min + box_y_max) / (2 * picture_height)width = float(box_x_max - box_x_min) /  picture_widthheight = float(box_y_max - box_y_min) /  picture_height# print(class_num, x_center, y_center, width, height)txt_file.write(str(class_num) + ' ' + str(x_center) + ' ' + str(y_center) + ' ' + str(width) + ' ' + str(height) + '\n')
# 转换文件夹下的所有xml文件为txt
def dir_xml_to_txt(path):files = os.listdir(path)for xml_file in files:single_xml_to_txt(xml_file)
dir_xml_to_txt(path)

3. 逐个json转txt  (生成coco数据集/yolo数据集格式)

(1.) 这里首先对xx.jpg,xx.json统一成coco格式,生成instances_train2017/instances_val2017

定义lables.txt是:(注意_background_是-1)

_background_
person
car
bicycle
UAV
motorcycle
xxx

目录结构: 

|-- images
|     |---  1.jpg
|     |---  1.json
|     |---  2.jpg
|     |---  2.json
|     |---  .......
|-- labelmejson2coco.py
|-- labels.txt

(2)labelmejson2coco.py文件,整理成coco数据集格式

# 命令行执行: python labelme2coco.py --input_dir images --output_dir coco --labels labels.txt
# 输出文件夹必须为空文件夹import argparse
import collections
import datetime
import glob
import json
import os
import os.path as osp
import sys
import uuid
import imgviz
import numpy as np
import labelme
import cv2
from sklearn.model_selection import train_test_splittry:import pycocotools.mask
except ImportError:print("Please install pycocotools:\n\n    pip install pycocotools\n")sys.exit(1)def to_coco(args, label_files, train):# 创建 总标签datanow = datetime.datetime.now()data = dict(info=dict(description=None,url=None,version=None,year=now.year,contributor=None,date_created=now.strftime("%Y-%m-%d %H:%M:%S.%f"),),licenses=[dict(url=None, id=0, name=None, )],images=[# license, url, file_name, height, width, date_captured, id],type="instances",annotations=[# segmentation, area, iscrowd, image_id, bbox, category_id, id],categories=[# supercategory, id, name],)# 创建一个 {类名 : id} 的字典,并保存到 总标签data 字典中。class_name_to_id = {}for i, line in enumerate(open(args.labels).readlines()):class_id = i - 1  # starts with -1class_name = line.strip()  # strip() 方法用于移除字符串头尾指定的字符(默认为空格或换行符)或字符序列。if class_id == -1:assert class_name == "_background_"  # _background_:0, class1:1, ,,continueclass_name_to_id[class_name] = class_iddata["categories"].append(dict(supercategory=None, id=class_id, name=class_name, ))if train:out_ann_file = osp.join(args.output_dir, "annotations", "instances_train2017.json")else:out_ann_file = osp.join(args.output_dir, "annotations", "instances_val2017.json")for image_id, filename in enumerate(label_files):label_file = labelme.LabelFile(filename=filename)base = osp.splitext(osp.basename(filename))[0]  # 文件名不带后缀if train:out_img_file = osp.join(args.output_dir, "train2017", base + ".jpg")else:out_img_file = osp.join(args.output_dir, "val2017", base + ".jpg")print("| ", out_img_file)# ************************** 对图片的处理开始 *******************************************# 将标签文件对应的图片进行保存到对应的 文件夹。train保存到 train2017/ test保存到 val2017/img = labelme.utils.img_data_to_arr(label_file.imageData)  # .json文件中包含图像,用函数提出来# 对数据进行增强,图像数据本身不会随图像的变换而变换。所以直接在json文件里面使用图像的ID作为键,将图像和标注数据进行匹配和关联。如果裁剪就用下面代码# image_path = os.path.join(filename).replace('.json', '.jpg')# img = cv2.imread(image_path)imgviz.io.imsave(out_img_file, img)  # 将图像保存到输出路径# ************************** 对图片的处理结束 *******************************************# ************** ************ 对标签的处理开始 *******************************************# 读取原始的JSON文件  # 如果裁剪下面这两行就取消掉with open(filename, 'r') as f:data_json = json.load(f)data["images"].append(dict(license=0,url=None,file_name=osp.relpath(out_img_file, osp.dirname(out_ann_file)),#   out_img_file = "/coco/train2017/1.jpg"#   out_ann_file = "/coco/annotations/annotations_train2017.json"#   osp.dirname(out_ann_file) = "/coco/annotations"#   file_name = ..\train2017\1.jpg   out_ann_file文件所在目录下 找 out_img_file 的相对路径height=img.shape[0],   # 如果裁剪就用img调用width=img.shape[1],# height=data_json['imageHeight'],# width=data_json['imageWidth'],date_captured=None,id=image_id,))masks = {}  # for areasegmentations = collections.defaultdict(list)  # for segmentationfor shape in label_file.shapes:points = shape["points"]label = shape["label"]group_id = shape.get("group_id")shape_type = shape.get("shape_type", "polygon")mask = labelme.utils.shape_to_mask(img.shape[:2], points, shape_type)if group_id is None:group_id = uuid.uuid1()instance = (label, group_id)if instance in masks:masks[instance] = masks[instance] | maskelse:masks[instance] = maskif shape_type == "rectangle":(x1, y1), (x2, y2) = pointsx1, x2 = sorted([x1, x2])y1, y2 = sorted([y1, y2])points = [x1, y1, x2, y1, x2, y2, x1, y2]else:points = np.asarray(points).flatten().tolist()segmentations[instance].append(points)segmentations = dict(segmentations)for instance, mask in masks.items():cls_name, group_id = instanceif cls_name not in class_name_to_id:continuecls_id = class_name_to_id[cls_name]mask = np.asfortranarray(mask.astype(np.uint8))mask = pycocotools.mask.encode(mask)area = float(pycocotools.mask.area(mask))bbox = pycocotools.mask.toBbox(mask).flatten().tolist()data["annotations"].append(dict(id=len(data["annotations"]),image_id=image_id,category_id=cls_id,segmentation=segmentations[instance],area=area,bbox=bbox,iscrowd=0,))# ************************** 对标签的处理结束 *******************************************# ************************** 可视化的处理开始 *******************************************if not args.noviz:labels, captions, masks = zip(*[(class_name_to_id[cnm], cnm, msk)for (cnm, gid), msk in masks.items()if cnm in class_name_to_id])viz = imgviz.instances2rgb(image=img,labels=labels,masks=masks,captions=captions,font_size=15,line_width=2,)out_viz_file = osp.join(args.output_dir, "visualization", base + ".jpg")imgviz.io.imsave(out_viz_file, viz)# ************************** 可视化的处理结束 *******************************************with open(out_ann_file, "w") as f:  # 将每个标签文件汇总成data后,保存总标签data文件json.dump(data, f)# 主程序执行
def main():parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)parser.add_argument("--input_dir", help="input annotated directory", default=r"E:/老师和教研室相关/揭榜挂帅挑战杯/海陆/")parser.add_argument("--output_dir", help="output dataset directory", default=r"E:/老师和教研室相关/揭榜挂帅挑战杯/海陆/coco")parser.add_argument("--labels", help="labels file", default='E:/老师和教研室相关/揭榜挂帅挑战杯/海陆/0labels.txt')parser.add_argument("--noviz", help="no visualization", action="store_true")args = parser.parse_args()if osp.exists(args.output_dir):print("Output directory already exists:", args.output_dir)sys.exit(1)os.makedirs(args.output_dir)print("| Creating dataset dir:", args.output_dir)if not args.noviz:os.makedirs(osp.join(args.output_dir, "visualization"))# 创建保存的文件夹if not os.path.exists(osp.join(args.output_dir, "annotations")):os.makedirs(osp.join(args.output_dir, "annotations"))if not os.path.exists(osp.join(args.output_dir, "train2017")):os.makedirs(osp.join(args.output_dir, "train2017"))if not os.path.exists(osp.join(args.output_dir, "val2017")):os.makedirs(osp.join(args.output_dir, "val2017"))# 获取目录下所有的.jpg文件列表# feature_files = glob.glob(osp.join(args.input_dir, "*.jpg"))feature_files = glob.glob(osp.join(args.input_dir, "*.png"))print('| Image number: ', len(feature_files))# 获取目录下所有的joson文件列表label_files = glob.glob(osp.join(args.input_dir, "*.json"))print('| Json number: ', len(label_files))# feature_files:待划分的样本特征集合    label_files:待划分的样本标签集合    test_size:测试集所占比例# x_train:划分出的训练集特征      x_test:划分出的测试集特征     y_train:划分出的训练集标签    y_test:划分出的测试集标签x_train, x_test, y_train, y_test = train_test_split(feature_files, label_files, test_size=0.3, random_state=1)print("| Train number:", len(y_train), '\t Value number:', len(y_test))# 把训练集标签转化为COCO的格式,并将标签对应的图片保存到目录 /train2017/print("—" * 50)print("| Train images:")to_coco(args, y_train, train=True)# 把测试集标签转化为COCO的格式,并将标签对应的图片保存到目录 /val2017/print("—" * 50)print("| Test images:")to_coco(args, y_test, train=False)if __name__ == "__main__":print("—" * 50)main()print("—" * 50)

coco数据集格式如下:

|-- annotations
| 	|---  instances_train2017.json
|       |---  instances_val2017.json
|-- train2017
| 	|---  2.jpg
| 	|---  5.jpg
| 	|---  .......
|-- val2017
| 	|---  1.jpg
| 	|---  3.jpg
| 	|---  .......
|-- visualization
| 	|---  1.jpg
| 	|---  2.jpg
| 	|---  .......

 (3) cocojson2yolotxt 是对统一的coco格式利用instances_train2017/instances_val2017形成yolo的txt格式
 

这里得 classes.txt  没有_background_  只有自己设定的类别
#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
import argparseparser = argparse.ArgumentParser()
#这里根据自己的json文件位置,换成自己的就行
parser.add_argument('--json_path', default='F:/CutLER-main/output/imagenet_train_fixsize480_tau0.2_N3.json',type=str, help="input: coco format(json)")
#这里设置.txt文件保存位置
parser.add_argument('--save_path', default='F:/CutLER-main/output/yolo_my_mask/labels/', type=str, help="specify where to save the output dir of labels")
arg = parser.parse_args()def convert(size, box):dw = 1. / (size[0])dh = 1. / (size[1])x = box[0] + box[2] / 2.0y = box[1] + box[3] / 2.0w = 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__':json_file =   arg.json_path # COCO Object Instance 类型的标注ana_txt_save_path = arg.save_path  # 保存的路径data = json.load(open(json_file, 'r'))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(ana_txt_save_path, 'classes.txt'), 'w') as f:# 写入classes.txtfor i, category in enumerate(data['categories']):f.write(f"{category['name']}\n")id_map[category['id']] = i# 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(ana_txt_save_path, 'train2017.txt'), 'w')for img in tqdm(data['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 data['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('./images/train2017/%s.jpg\n' %(head))list_file.close()

 (4)  cocojson2yolotxt_seg  是对统一的coco格式利用instances_train2017/instances_val2017形成yolo-segment的txt格式,用于实例分割的,最好一般都用这个来转换

import os
import json
import shutildef write_yolo_txt_file(txt_file_path, label_seg_x_y_list):if not os.path.exists(txt_file_path):with open(txt_file_path, "w") as file:for element in label_seg_x_y_list:file.write(str(element) + " ")file.write('\n')else:with open(txt_file_path, "a") as file:for element in label_seg_x_y_list:file.write(str(element) + " ")file.write('\n')def read_json(in_json_path, img_dir, target_dir):with open(in_json_path, "r", encoding='utf-8') as f:# json.load数据到变量json_datajson_data = json.load(f)# print(len(json_data['annotations']))# print(len(json_data['images']))# print(len(json_data['categories']))for annotation in json_data['annotations']:  # 遍历标注数据信息# print(annotation)category_id = annotation['category_id']image_id = annotation['image_id']for image in json_data['images']:  # 遍历图片相关信息if image['id'] == image_id:width = image['width']  # 图片宽height = image['height']  # 图片高img_file_name = image['file_name']  # 图片名称img_file_name = img_file_name.split('/')[-1]filename = os.path.splitext(os.path.basename(img_file_name))[0]# img_file_name=img_file_name[:-4]# txt_file_name = img_file_name.split('.')[0] + '.txt'txt_file_name = filename + '.txt' # 要保存的对应txt文件名break# print(width,height,img_file_name,txt_file_name)segmentation = annotation['segmentation']  # 图像分割点信息[[x1,y1,x2,y2,...,xn,yn]]seg_x_y_list = [i / width if num % 2 == 0 else i / height for num, i inenumerate(segmentation[0])]  # 归一化图像分割点信息label_seg_x_y_list = seg_x_y_list[:]label_seg_x_y_list.insert(0, category_id)  # 图像类别与分割点信息[label,x1,y1,x2,y2,...,xn,yn]# print(label_seg_x_y_list)# 写txt文件txt_file_path = target_dir + txt_file_name# print(txt_file_path)write_yolo_txt_file(txt_file_path, label_seg_x_y_list)# # 选出txt对应img文件# img_file_path = img_dir + img_file_name# # print(img_file_path)# shutil.copy(img_file_path, target_dir)if __name__ == "__main__":img_dir = 'E:/老师和教研室相关/揭榜挂帅挑战杯/海陆/yolo/images/train2017/'target_dir = 'E:/老师和教研室相关/揭榜挂帅挑战杯/海陆/yolo/labels/train2017/'if not os.path.exists(target_dir):os.mkdir(target_dir)in_json_path = 'E:/老师和教研室相关/揭榜挂帅挑战杯/海陆/coco/annotations/instances_train2017.json'read_json(in_json_path, img_dir, target_dir)

4.逐个txt转json

注意这里面lcassesname 要txt里面的目标类别对应,判断对应的标签名称,写入json文件中

import os
import json
import base64
import cv2def read_txt_file(txt_file):with open(txt_file, 'r') as f:lines = f.readlines()data = []for line in lines:line = line.strip().split()class_name = line[0]bbox = [coord for coord in line[1:]]data.append({'class_name': class_name, 'bbox': bbox})return datadef convert_to_labelme(data, image_path, image_size):labelme_data = {'version': '4.5.6','flags': {},'shapes': [],'imagePath': json_image_path,'imageData': None,'imageHeight': image_size[0],'imageWidth': image_size[1]}for obj in data:dx = obj['bbox'][0]dy = obj['bbox'][1]dw = obj['bbox'][2]dh = obj['bbox'][3]w = eval(dw) * image_size[1]h = eval(dh) * image_size[0]center_x = eval(dx) * image_size[1]center_y = eval(dy) * image_size[0]x1 = center_x - w/2y1 = center_y - h/2x2 = center_x + w/2y2 = center_y + h/2if obj['class_name'] == '0': #判断对应的标签名称,写入json文件中label = str('People')elif obj['class_name'] == '1': #判断对应的标签名称,写入json文件中label = str('Car')elif obj['class_name'] == '2': #判断对应的标签名称,写入json文件中label = str('Bus')elif obj['class_name'] == '3': #判断对应的标签名称,写入json文件中label = str('Lamp')elif obj['class_name'] == '4': #判断对应的标签名称,写入json文件中label = str('Motorcycle')elif obj['class_name'] == '5': #判断对应的标签名称,写入json文件中label = str('Truck')shape_data = {'label': label,'points': [[x1, y1], [x2, y2]],'group_id': None,'shape_type': 'rectangle','flags': {}}labelme_data['shapes'].append(shape_data)return labelme_datadef save_labelme_json(labelme_data, image_path, output_file):with open(image_path, 'rb') as f:image_data = f.read()labelme_data['imageData'] = base64.b64encode(image_data).decode('utf-8')with open(output_file, 'w') as f:json.dump(labelme_data, f, indent=4)# 设置文件夹路径和输出文件夹路径
txt_folder = r"G:/datasets/yolo_M3FD_Detection/labels" # 存放txt文件的文件夹路径
output_folder = r"G:/datasets/yolo_M3FD_Detection/jsons/"
img_folder = r"G:/datasets/yolo_M3FD_Detection/ir/"# 创建输出文件夹
if not os.path.exists(output_folder):os.makedirs(output_folder)# 遍历txt文件夹中的所有文件
for filename in os.listdir(txt_folder):if filename.endswith('.txt'):# 生成对应的输出文件名output_filename = os.path.splitext(filename)[0] + '.json'# 读取txt文件txt_file = os.path.join(txt_folder, filename)data = read_txt_file(txt_file)# 设置图片路径和尺寸# image_filename = os.path.splitext(filename)[0] + '.jpg'  # 图片文件名与txt文件名相同,后缀为.jpgimage_filename = os.path.splitext(filename)[0] + '.png'  # 图片文件名与txt文件名相同,后缀为.jpg# image_path = os.path.join(img_folder, image_filename)image_path = os.path.join(image_filename)  # 直接文件名 方便后面json转换# image_size = (1280, 720)  # 根据实际情况修改json_image_path = image_path.split('\\')[-1]print("image_path:", image_path)image_path_folder = os.path.join(img_folder, image_filename)image_size = cv2.imread(image_path_folder).shape# 转化为LabelMe格式labelme_data = convert_to_labelme(data, image_path, image_size)# 保存为LabelMe JSON文件output_file = os.path.join(output_folder, output_filename)save_labelme_json(labelme_data, image_path_folder, output_file)

5.逐个txt转coco的json

相当于直接把coco的数据集instances格式弄出来

import os
import json
import cv2
import random
import time
from PIL import Image# 生成全部的Json_all 分train/val/test
coco_format_save_path='G:datasets/yolo_ir_jz/jsons/test/'   #要生成的标准coco格式标签所在文件夹
yolo_format_classes_path='G:datasets/yolo_ir_jz/classes.txt'     #类别文件,一行一个类
yolo_format_annotation_path='G:datasets/yolo_ir_jz/labels/test/'  #yolo格式标签所在文件夹
img_pathDir='G:datasets/yolo_ir_jz/images/test/'    #图片所在文件夹with open(yolo_format_classes_path,'r') as fr:                               #打开并读取类别文件lines1=fr.readlines()
# print(lines1)
categories=[]                                                                 #存储类别的列表
for j,label in enumerate(lines1):label=label.strip()categories.append({'id':j+1,'name':label,'supercategory':'None'})         #将类别信息添加到categories中
# print(categories)write_json_context=dict()                                                      #写入.json文件的大字典
write_json_context['info']= {'description': '', 'url': '', 'version': '', 'year': 2024, 'contributor': 'gc', 'date_created': '2024-09-27'}
write_json_context['licenses']=[{'id':1,'name':None,'url':None}]
write_json_context['categories']=categories
write_json_context['images']=[]
write_json_context['annotations']=[]#接下来的代码主要添加'images'和'annotations'的key值
imageFileList=os.listdir(img_pathDir)                                           #遍历该文件夹下的所有文件,并将所有文件名添加到列表中
for i,imageFile in enumerate(imageFileList):imagePath = os.path.join(img_pathDir,imageFile)                             #获取图片的绝对路径image = Image.open(imagePath)                                               #读取图片,然后获取图片的宽和高W, H = image.sizeimg_context={}                                                              #使用一个字典存储该图片信息#img_name=os.path.basename(imagePath)                                       #返回path最后的文件名。如果path以/或\结尾,那么就会返回空值img_context['file_name']=imageFileimg_context['height']=Himg_context['width']=Wimg_context['date_captured']='2024-09-27'img_context['id']=i                                                         #该图片的idimg_context['license']=1img_context['color_url']=''img_context['flickr_url']=''write_json_context['images'].append(img_context)                            #将该图片信息添加到'image'列表中txtFile=imageFile[:5]+'.txt'                                               #获取该图片获取的txt文件with open(os.path.join(yolo_format_annotation_path,txtFile),'r') as fr:lines=fr.readlines()                                                   #读取txt文件的每一行数据,lines2是一个列表,包含了一个图片的所有标注信息for j,line in enumerate(lines):bbox_dict = {}                                                          #将每一个bounding box信息存储在该字典中# line = line.strip().split()# print(line.strip().split(' '))class_id,x,y,w,h=line.strip().split(' ')                                          #获取每一个标注框的详细信息class_id,x, y, w, h = int(class_id), float(x), float(y), float(w), float(h)       #将字符串类型转为可计算的int和float类型xmin=(x-w/2)*W                                                                    #坐标转换ymin=(y-h/2)*Hxmax=(x+w/2)*Wymax=(y+h/2)*Hw=w*Wh=h*Hbbox_dict['id']=i*10000+j                                                         #bounding box的坐标信息bbox_dict['image_id']=ibbox_dict['category_id']=class_id+1                                               #注意目标类别要加一bbox_dict['iscrowd']=0height,width=abs(ymax-ymin),abs(xmax-xmin)bbox_dict['area']=height*widthbbox_dict['bbox']=[xmin,ymin,w,h]bbox_dict['segmentation']=[[xmin,ymin,xmax,ymin,xmax,ymax,xmin,ymax]]write_json_context['annotations'].append(bbox_dict)                               #将每一个由字典存储的bounding box信息添加到'annotations'列表中name = os.path.join(coco_format_save_path,"train"+ '.json')
with open(name,'w') as fw:                                                                #将字典信息写入.json文件中json.dump(write_json_context,fw,indent=2)

6.根据txt划分yolo数据集格式

训练集:验证集:测试集 (7:2:1) 比例可以自己定义
import os, shutil, random
from tqdm import tqdm"""
标注文件是yolo格式(txt文件)
训练集:验证集:测试集 (7:2:1) 
"""def split_img(img_path, label_path, split_list):try:Data = 'G:\datasets/yolo_my_enhance'# Data是你要将要创建的文件夹路径(路径一定是相对于你当前的这个脚本而言的)# os.mkdir(Data)train_img_dir = Data + '/images/train'val_img_dir = Data + '/images/val'test_img_dir = Data + '/images/test'train_label_dir = Data + '/labels/train'val_label_dir = Data + '/labels/val'test_label_dir = Data + '/labels/test'# 创建文件夹os.makedirs(train_img_dir)os.makedirs(train_label_dir)os.makedirs(val_img_dir)os.makedirs(val_label_dir)os.makedirs(test_img_dir)os.makedirs(test_label_dir)except:print('文件目录已存在')train, val, test = split_listall_img = os.listdir(img_path)all_img_path = [os.path.join(img_path, img) for img in all_img]# all_label = os.listdir(label_path)# all_label_path = [os.path.join(label_path, label) for label in all_label]train_img = random.sample(all_img_path, int(train * len(all_img_path)))train_img_copy = [os.path.join(train_img_dir, img.split('\\')[-1]) for img in train_img]train_label = [toLabelPath(img, label_path) for img in train_img]train_label_copy = [os.path.join(train_label_dir, label.split('\\')[-1]) for label in train_label]for i in tqdm(range(len(train_img)), desc='train ', ncols=80, unit='img'):_copy(train_img[i], train_img_dir)_copy(train_label[i], train_label_dir)all_img_path.remove(train_img[i])val_img = random.sample(all_img_path, int(val / (val + test) * len(all_img_path)))val_label = [toLabelPath(img, label_path) for img in val_img]for i in tqdm(range(len(val_img)), desc='val ', ncols=80, unit='img'):_copy(val_img[i], val_img_dir)_copy(val_label[i], val_label_dir)all_img_path.remove(val_img[i])test_img = all_img_pathtest_label = [toLabelPath(img, label_path) for img in test_img]for i in tqdm(range(len(test_img)), desc='test ', ncols=80, unit='img'):_copy(test_img[i], test_img_dir)_copy(test_label[i], test_label_dir)def _copy(from_path, to_path):shutil.copy(from_path, to_path)def toLabelPath(img_path, label_path):img = img_path.split('\\')[-1]label = img.split('.jpg')[0] + '.txt'return os.path.join(label_path, label)if __name__ == '__main__':img_path = 'G:/datasets/yolo_my_enhance/yolo_my_enhance'  # 你的图片存放的路径(路径一定是相对于你当前的这个脚本文件而言的)label_path = './YoloLabels'  # 你的txt文件存放的路径(路径一定是相对于你当前的这个脚本文件而言的)split_list = [0.7, 0.2, 0.1]  # 数据集划分比例[train:val:test]split_img(img_path, label_path, split_list)

http://www.ritt.cn/news/23793.html

相关文章:

  • 做外贸一般用哪些网站职业技能培训学校
  • 建个公司网站多少钱武汉seo优化
  • 安平县网站建设网上开店如何推广自己的网店
  • 网站备案完成后百度入口官网
  • 国外浏览器app西安官网seo技术
  • 广东建设网 工程信息网站seo网络营销推广
  • MUSIK V1.0 WORDPRESS怎样优化网站
  • 做网站还要买服务器吗关键词调整排名软件
  • 外国产品设计网站百度站长电脑版
  • 临沂网站建设网站推广广州网站优化公司排名
  • 化妆品网站建设实训总结比优化更好的词是
  • diy个性定制优化网站首页
  • python 做网站开发吗搜索引擎推广有哪些
  • 水电建设网站泉州seo代理计费
  • 360网站推广官网授权商山东疫情最新情况
  • 手机网站发号系统源码网络推广搜索引擎
  • 客户说做网站没效果怎么回答好网络营销的10个特点
  • 网站如何快速收录热点新闻
  • 如何做网站做网站需要多少钱搜索引擎案例分析结论
  • 杭州公司网站制作维护产品软文代写
  • dede网站入侵百度地图排名可以优化吗
  • 自动采集更新的网站wordpress软文广告文案
  • springboot网站开发网站开发框架
  • 用源码建设网站网络推广平台有哪些?
  • 网站建设的经费成都网站建设公司排名
  • 做一个企业网站设计电子商务营销策略有哪些
  • 用java可以做网站吗广东百度推广的代理商
  • 有哪几个平台做网站简述优化搜索引擎的方法
  • 上海网站备案拍照地点运营培训班有用吗
  • 最新手机网址企业官网seo