- .odgt转.json(coco)
import os
import json
from PIL import Image
def load_file(fpath):#fpath是具体的文件 ,作用:#str to list
assert os.path.exists(fpath) #assert() raise-if-not
with open(fpath,'r') as fid:
lines = fid.readlines()
records = [json.loads(line.strip('\n')) for line in lines] #str to list
return records
def crowdhuman2coco(odgt_path, json_path): # 一个输入文件路径,一个输出文件路径
records = load_file(odgt_path) # 提取odgt文件数据
# 预处理
json_dict = {"images": [], "annotations": [], "categories": []} # 定义一个字典,coco数据集标注格式
START_B_BOX_ID = 1 # 设定框的起始ID
image_id = 1 # 每个image的ID唯一,自己设定start,每次++
bbox_id = START_B_BOX_ID
image = {} # 定义一个字典,记录image
annotation = {} # 记录annotation
categories = {} # 进行类别记录
record_list = len(records) # 获得record的长度,循环遍历所有数据。
print(record_list)
# 一行一行的处理。
for i in range(record_list):
file_name = records[i]['ID'] + '.jpg' # 这里是字符串格式 eg.273278,600e5000db6370fb
# image_id = int(records[i]['ID'].split(",")[0]) # 这样会导致id唯一,要自己设定
im = Image.open("D:/DataSet/CrowdHuman/CrowdHuman_train/Images/" + file_name)
# 根据文件名,获取图片,这样可以获取到图片的宽高等信息。因为再odgt数据集里,没有宽高的字段信息。
image = {'file_name': file_name, 'height': im.size[1], 'width': im.size[0],
'id': image_id} # im.size[0],im.size[1]分别是宽高
json_dict['images'].append(image) # 这一步完成一行数据到字典images的转换。
gt_box = records[i]['gtboxes']
gt_box_len = len(gt_box) # 每一个字典gtboxes里,也有好几个记录,分别提取记录。
for j in range(gt_box_len):
category = gt_box[j]['tag']
if category not in categories: # 该类型不在categories,就添加上去
new_id = len(categories) + 1 # ID递增
categories[category] = new_id
category_id = categories[category] # 重新获取它的类别ID
fbox = gt_box[j]['fbox'] # 获得全身框
# 对ignore进行处理,ignore有时在key:extra里,有时在key:head_attr里。属于互斥的。
ignore = 0 # 下面key中都没有ignore时,就设为0,据观察,都存在,只是存在哪个字典里,需要判断一下
if "ignore" in gt_box[j]['head_attr']:
ignore = gt_box[j]['head_attr']['ignore']
if "ignore" in gt_box[j]['extra']:
ignore = gt_box[j]['extra']['ignore']
# 对字典annotation进行设值。
annotation = {'area': fbox[2] * fbox[3], 'iscrowd': ignore, 'image_id': # 添加hbox、vbox字段。
image_id, 'bbox': fbox, 'hbox': gt_box[j]['hbox'], 'vbox': gt_box[j]['vbox'],
'category_id': category_id, 'id': bbox_id, 'ignore': ignore, 'segmentation': []}
# area的值,暂且就是fbox的宽高相乘了,观察里面的数据,发现fbox[2]小、fbox[3]很大,刚好一个全身框的宽很小,高就很大。(猜测),不是的话,再自行修改
# segmentation怎么处理?博主自己也不知道,找不到对应的数据,这里就暂且不处理。
# hbox、vbox、ignore是添加上去的,以防有需要。
json_dict['annotations'].append(annotation)
bbox_id += 1 # 框ID ++
image_id += 1 # 这个image_id的递增操作,注意位置,博主一开始,放上面执行了,后面出了bug,自己可以理一下。
# annotations的转化结束。
# 下面这一步,对所有数据,只需执行一次,也就是对categories里的类别进行统计。
for cate, cid in categories.items():
# dict.items()返回列表list的所有列表项,形如这样的二元组list:[(key,value),(key,value),...]
cat = {'supercategory': 'none', 'id': cid, 'name': cate}
json_dict['categories'].append(cat)
# 到此,json_dict的转化全部完成,对于其他的key,
# 因为没有用到(不访问),就不需要给他们空间,也不需要去处理,字典是按key访问的,如果自己需要就自己添加上去就行
json_fp = open(json_path, 'w')
json_str = json.dumps(json_dict) # 写json文件。
json_fp.write(json_str)
json_fp.close()
if __name__ == '__main__':
crowdhuman2coco(r'D:\DataSet\CrowdHuman\annotation_train.odgt', r'D:\DataSet\CrowdHuman\annotation_train\annotation.json')
- .json转.txt
import json
import os
import xml.etree.ElementTree as ET
import cv2
# 将x1, y1, x2, y2转换成yolov5所需要的x, y, w, h格式
def xyxy2xywh(size, box):
dw = 1. / size[0]
dh = 1. / size[1]
x = (box[0] + box[2]) / 2 * dw
y = (box[1] + box[3]) / 2 * dh
w = (box[2] - box[0]) * dw
h = (box[3] - box[1]) * dh
return (x, y, w, h) # 返回的都是标准化后的值
def voc2yolo(path):
# 可以打印看看该路径是否正确
print(len(os.listdir(path)))
pic_path = r'D:\DataSet\46_CUHK Occlusion Dataset\images' # 原始图片路径
txt_out_path = r'D:\DataSet\46_CUHK Occlusion Dataset\labels\txt' # 转换后txt保存路径
# 遍历每一个xml文件
for file in os.listdir(path):
print(file)
if "json" in str(file):
with open(os.path.join(path, file), 'r') as f:
data = json.load(f)
print(data)
points = data['shapes'][0]['points']
pic_name = os.path.join(pic_path, data['imagePath'])
txt_name = data['imagePath'].split(".")[0] + ".txt"
imread = cv2.imread(pic_name)
h = imread.shape[0]
w = imread.shape[1]
print(imread.shape)
xmin = points[0][0]
ymin = points[0][1]
xmax = points[2][0]
ymax = points[2][1]
box = [float(xmin), float(ymin), float(xmax),
float(ymax)]
print(box)
#
# # 将x1, y1, x2, y2转换成yolov5所需要的x, y, w, h格式
bbox = xyxy2xywh((w, h), box)
print(bbox)
# # 写入目标文件中,格式为 id x y w h
with open(os.path.join(txt_out_path, txt_name), 'w') as out_file:
out_file.write(str(0) + " " + " ".join(str(x) for x in bbox) + '\n')
out_file.close()
# exit()
if __name__ == '__main__':
# json格式数据路径
path = r'D:\DataSet\46_CUHK Occlusion Dataset\labels\json'
voc2yolo(path)
- .xml转.txt
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
def convert(size, box):
x_center = (box[0] + box[1]) / 2.0
y_center = (box[2] + box[3]) / 2.0
x = x_center / size[0]
y = y_center / size[1]
w = (box[1] - box[0]) / size[0]
h = (box[3] - box[2]) / size[1]
return (x, y, w, h)
def convert_annotation(xml_files_path, save_txt_files_path, classes):
xml_files = os.listdir(xml_files_path)
print(xml_files)
for xml_name in xml_files:
print(xml_name)
xml_file = os.path.join(xml_files_path, xml_name)
out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')
out_txt_f = open(out_txt_path, 'w')
tree = ET.parse(xml_file)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult) == 1:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
float(xmlbox.find('ymax').text))
# b=(xmin, xmax, ymin, ymax)
print(w, h, b)
bb = convert((w, h), b)
out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
if __name__ == "__main__":
classes = ['bird','cat', 'cow', 'dog', 'horse', 'sheep', 'person']
# 1、voc格式的xml标签文件路径
xml_files1 = r'D:\DataSet\person_datasets\CUHK01\xml'
# 2、转化为yolo格式的txt标签文件存储路径
save_txt_files1 = r'D:\DataSet\person_datasets\CUHK01\txt'
convert_annotation(xml_files1, save_txt_files1, classes)
版权声明:本文为weixin_44708254原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接和本声明。