湖南隆回建设局网站,怎么做网站排版,网站建设怎设计,四川网站建设设计公司排名实现VOC数据集与COCO数据集格式转换2、将voc数据集的xml转化为coco数据集的json格式2、COCO格式的json文件转化为VOC格式的xml文件3、将 txt 文件转换为 Pascal VOC 的 XML 格式annotationfolder文件夹目录/folderfilename图片名.jpg/file…
实现VOC数据集与COCO数据集格式转换2、将voc数据集的xml转化为coco数据集的json格式2、COCO格式的json文件转化为VOC格式的xml文件3、将 txt 文件转换为 Pascal VOC 的 XML 格式annotationfolder文件夹目录/folderfilename图片名.jpg/filenamepathpath_to\at002eg001.jpg/pathsourcedatabaseUnknown/database/sourcesizewidth550/widthheight518/heightdepth3/depth/sizesegmented0/segmentedobjectnameApple/nameposeUnspecified/posetruncated0/truncateddifficult0/difficultbndboxxmin292/xminymin218/yminxmax410/xmaxymax331/ymax/bndbox/objectobject.../object
/annotation coco
|______annotations # 存放标注信息
| |__train.json
| |__val.json
| |__test.json
|______trainset # 存放训练集图像
|______valset # 存放验证集图像
|______testset # 存放测试集图像
一个标准的json文件包含如下信息
{ info : info,licenses : [license],images : [image],annotations : [annataton],categories : [category]
} 1images字段列表元素的长度 划入训练集或者测试集的图片的数量
2annotations字段列表元素的数量 训练集或者测试集中bounding box的数量
3categories字段列表元素的数量 类别的数量接下来我们看每个key对应的内容 1info
info{
year : int, # 年份
version : str, # 版本
description : str, # 详细描述信息
contributor : str, # 作者
url : str, # 协议链接
date_created : datetime, # 生成日期
}
2images
images: [
{id: 0, # int 图像id可从0开始file_name: 0.jpg, # str 文件名width: 512, # int 图像的宽height: 512, # int 图像的高date_captured: 2020-04-14 01:45:07.508146, # datatime 获取日期license: 1, # int 遵循哪个协议coco_url: , # str coco图片链接urlflickr_url: # str flick图片链接url
}]
3licenses licenses: [
{id: 1, # int 协议id号 在images中遵循的license即1name: null, # str 协议名 url: null # str 协议链接
}]4annotations
annotations: [
{id: 0, # int 图片中每个被标记物体的id编号image_id: 0, # int 该物体所在图片的编号category_id: 2, # int 被标记物体的类别id编号iscrowd: 0, # 0 or 1 目标是否被遮盖默认为0area: 4095.9999999999986, # float 被检测物体的面积64 * 64 4096)bbox: [200.0, 416.0, 64.0, 64.0], # [x, y, width, height] 目标检测框的坐标信息segmentation: [[200.0, 416.0, 264.0, 416.0, 264.0, 480.0, 200.0, 480.0]]
}] 5categories
categories:[
{id: 1, # int 类别id编号name: rectangle, # str 类别名字supercategory: None # str 类别所属的大类如卡车和轿车都属于机动车这个class
},
{id: 2,name: circle, supercategory: None}
]2、将voc数据集的xml转化为coco数据集的json格式 # create_xml_list.py
import os
xml_list os.listdir(C:/Users/user/Desktop/train)
with open(C:/Users/user/Desktop/xml_list.txt,a) as f:for i in xml_list:if i[-3:]xml:f.write(str(i)\n)# voc2coco.py# pip install lxmlimport sys
import os
import json
import xml.etree.ElementTree as ETSTART_BOUNDING_BOX_ID 1
PRE_DEFINE_CATEGORIES {}
# If necessary, pre-define category and its id
# PRE_DEFINE_CATEGORIES {aeroplane: 1, bicycle: 2, bird: 3, boat: 4,# bottle:5, bus: 6, car: 7, cat: 8, chair: 9,# cow: 10, diningtable: 11, dog: 12, horse: 13,# motorbike: 14, person: 15, pottedplant: 16,# sheep: 17, sofa: 18, train: 19, tvmonitor: 20}def get(root, name):vars root.findall(name)return varsdef get_and_check(root, name, length):vars root.findall(name)if len(vars) 0:raise NotImplementedError(Can not find %s in %s.%(name, root.tag))if length 0 and len(vars) ! length:raise NotImplementedError(The size of %s is supposed to be %d, but is %d.%(name, length, len(vars)))if length 1:vars vars[0]return varsdef get_filename_as_int(filename):try:filename os.path.splitext(filename)[0]return int(filename)except:raise NotImplementedError(Filename %s is supposed to be an integer.%(filename))def convert(xml_list, xml_dir, json_file):list_fp open(xml_list, r)json_dict {images:[], type: instances, annotations: [],categories: []}categories PRE_DEFINE_CATEGORIESbnd_id START_BOUNDING_BOX_IDfor line in list_fp:line line.strip()print(Processing %s%(line))xml_f os.path.join(xml_dir, line)tree ET.parse(xml_f)root tree.getroot()path get(root, path)if len(path) 1:filename os.path.basename(path[0].text)elif len(path) 0:filename get_and_check(root, filename, 1).textelse:raise NotImplementedError(%d paths found in %s%(len(path), line))## The filename must be a numberimage_id get_filename_as_int(filename)size get_and_check(root, size, 1)width int(get_and_check(size, width, 1).text)height int(get_and_check(size, height, 1).text)image {file_name: filename, height: height, width: width,id:image_id}json_dict[images].append(image)## Cruuently we do not support segmentation# segmented get_and_check(root, segmented, 1).text# assert segmented 0for obj in get(root, object):category get_and_check(obj, name, 1).textif category not in categories:new_id len(categories)categories[category] new_idcategory_id categories[category]bndbox get_and_check(obj, bndbox, 1)xmin int(get_and_check(bndbox, xmin, 1).text) - 1ymin int(get_and_check(bndbox, ymin, 1).text) - 1xmax int(get_and_check(bndbox, xmax, 1).text)ymax int(get_and_check(bndbox, ymax, 1).text)assert(xmax xmin)assert(ymax ymin)o_width abs(xmax - xmin)o_height abs(ymax - ymin)ann {area: o_width*o_height, iscrowd: 0, image_id:image_id, bbox:[xmin, ymin, o_width, o_height],category_id: category_id, id: bnd_id, ignore: 0,segmentation: []}json_dict[annotations].append(ann)bnd_id bnd_id 1for cate, cid in categories.items():cat {supercategory: none, id: cid, name: cate}json_dict[categories].append(cat)json_fp open(json_file, w)json_str json.dumps(json_dict)json_fp.write(json_str)json_fp.close()list_fp.close()if __name__ __main__:if len(sys.argv) 1:print(3 auguments are need.)print(Usage: %s XML_LIST.txt XML_DIR OUTPU_JSON.json%(sys.argv[0]))exit(1)convert(sys.argv[1], sys.argv[2], sys.argv[3])import os
img_dirF:/Billboard/dataset/images/
lab_dirF:/Billboard/dataset/labels/
name_list os.listdir(img_dir)
for i,name in enumerate(name_list):os.rename(img_dirname,img_dirstr(i).jpg)os.rename(lab_dirname[:-4].txt,lab_dirstr(i).txt) xmin int(float(get_and_check(bndbox, xmin, 1).text)) - 1
ymin int(float(get_and_check(bndbox, ymin, 1).text)) - 1
xmax int(float(get_and_check(bndbox, xmax, 1).text))
ymax int(float(get_and_check(bndbox, ymax, 1).text))
2、COCO格式的json文件转化为VOC格式的xml文件 # coco2voc.py# pip install pycocotools
import os
import time
import json
import pandas as pd
from tqdm import tqdm
from pycocotools.coco import COCO#json文件路径和用于存放xml文件的路径
anno C:/Users/user/Desktop/val/instances_val2017.json
xml_dir C:/Users/user/Desktop/val/xml/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())def trans_id(category_id):names []namesid []for i in range(0, len(cats)):names.append(cats[i][name])namesid.append(cats[i][id])index namesid.index(category_id)return indexdef convert(anno,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], ascendingTrue) # 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,Tqdm是可扩展的Python进度条可以在长循环中添加一个进度提示信息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]version [1.0,utf-8] # xml文件添加属性xml_content.append(?xml version version[0] encoding version[1] ?)xml_content.append(annotation)xml_content.append( filename file_name /filename)xml_content.append( size)xml_content.append( width str(width) /width)xml_content.append( height str(height) /height)xml_content.append( depth 3 /depth)xml_content.append( /size)# 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)]# add new objectxml_content.append( object)xml_content.append( name cate_name /name)xml_content.append( truncated0/truncated)xml_content.append( difficult0/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(.xml, .jpg))xml_path os.path.join(xml_dir, file_name.split(j)[0]xml)print(xml_path)with open(xml_path, w, encodingutf8) as f:f.write(\n.join(xml_content))xml_content[:] []if __name__ __main__:convert(anno,xml_dir)3、将 txt 文件转换为 Pascal VOC 的 XML 格式
比如从OpenImageV5下载下来的BIllboard数据集目录如下
Billboard
|______images # 存放训练集图像
| |__train|__train.jpg
| |__val|__val.jpg
|______labels # 存放标注信息
| |__train|__train.txt
| |__val|__val.txt 将 txt 文件转换为 Pascal VOC 的 XML 格式的代码如下
#! /usr/bin/python
# -*- coding:UTF-8 -*-
import os, sys
import glob
from PIL import Image# VEDAI 图像存储位置
src_img_dir F:/Billboard/dataset/images/val
# VEDAI 图像的 ground truth 的 txt 文件存放位置
src_txt_dir F:/Billboard/dataset/labels/val
src_xml_dir F:/Billboard/dataset/xml/val
name[billboard]img_Lists glob.glob(src_img_dir /*.jpg)img_basenames [] # e.g. 100.jpg
for item in img_Lists:img_basenames.append(os.path.basename(item))img_names [] # e.g. 100
for item in img_basenames:temp1, temp2 os.path.splitext(item)img_names.append(temp1)for img in img_names:im Image.open((src_img_dir / img .jpg))width, height im.size# open the crospronding txt filegt open(src_txt_dir / img .txt).read().splitlines()#gt open(src_txt_dir /gt_ img .txt).read().splitlines()# write in xml file#os.mknod(src_xml_dir / img .xml)xml_file open((src_xml_dir / img .xml), w)xml_file.write(annotation\n)xml_file.write( folderVOC2007/folder\n)xml_file.write( filename str(img) .jpg /filename\n)xml_file.write( size\n)xml_file.write( width str(width) /width\n)xml_file.write( height str(height) /height\n)xml_file.write( depth3/depth\n)xml_file.write( /size\n)# write the region of image on xml filefor img_each_label in gt:spt img_each_label.split( ) #这里如果txt里面是以逗号‘’隔开的那么就改为spt img_each_label.split(,)。xml_file.write( object\n)xml_file.write( name str(name[int(spt[0])]) /name\n)xml_file.write( poseUnspecified/pose\n)xml_file.write( truncated0/truncated\n)xml_file.write( difficult0/difficult\n)xml_file.write( bndbox\n)xml_file.write( xmin str(float(spt[1])*width) /xmin\n)xml_file.write( ymin str(float(spt[3])*height) /ymin\n)xml_file.write( xmax str(float(spt[2])*width) /xmax\n)xml_file.write( ymax str(float(spt[4])*height) /ymax\n)xml_file.write( /bndbox\n)xml_file.write( /object\n)xml_file.write(/annotation)
