1. The difference between the YOLO format dataset and the COCO format
The annotation file of the yolo dataset is a .txt file, and each .txt file in the label folder corresponds to a picture in the dataset. Each
line in each .txt file represents a target in the picture.
The annotation file of the coco dataset is a .json file, and all the data annotation files are composed of three .json files: train.json val.json test.json, each of which contains all the images in the dataset. All targets (note that all targets are not all pictures in the dataset)
Folder composition of YOLO format dataset and COCO dataset
COCO dataset:
|-dataset-cooc
|-|-annotations
|-|-|-train.json
|-|-|-val.json
|-|-|-test.json
|-images
|-|-001. jpg
|-|-002.jpg
…
YOLO dataset: (each .txt file and .jpg file are in one-to-one correspondence)
|-dataset-yolo
|-|-labels
|-|-|-train
|-|- |-|-001.txt
|-|-|-val
|-|-|-|-006.txt
|-|-|-test
|-|-|-|-009.txt
|-|-images
|- |-|-train
|-|-|-|-001.jpg
|-|-|-val
|-|-|-|-006.jpg
|-|-|-test
|-|-|-|-009 .jpg
…
Convert the dataset in YOLO format to COCO format
- Create the corresponding folder according to the above file format
- Add a new one under the COCO fileclasses.txtThe file is as shown in the figure:
Contents in the classes.txt file: each row is a category in the custom dataset
- Run the following code:
"""
YOLO 格式的数据集转化为 COCO 格式的数据集
--root_dir 输入根路径
--save_path 保存文件的名字(没有random_split时使用)
--random_split 有则会随机划分数据集，然后再分别保存为3个文件。
--split_by_file 按照 ./train.txt ./val.txt ./test.txt 来对数据集进行划分。
"""
import os
import cv2
import json
from tqdm import tqdm
from sklearn.model_selection import train_test_split
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--root_dir', default='./data',type=str, help="root path of images and labels, include ./images and ./labels and classes.txt")
parser.add_argument('--save_path', type=str,default='./train.json', help="if not split the dataset, give a path to a json file")
parser.add_argument('--random_split', action='store_true', help="random split the dataset, default ratio is 8:1:1")
parser.add_argument('--split_by_file', action='store_true', help="define how to split the dataset, include ./train.txt ./val.txt ./test.txt ")
arg = parser.parse_args()
def train_test_val_split_random(img_paths,ratio_train=0.8,ratio_test=0.1,ratio_val=0.1):
# 这里可以修改数据集划分的比例。
assert int(ratio_train+ratio_test+ratio_val) == 1
train_img, middle_img = train_test_split(img_paths,test_size=1-ratio_train, random_state=233)
ratio=ratio_val/(1-ratio_train)
val_img, test_img =train_test_split(middle_img,test_size=ratio, random_state=233)
print("NUMS of train:val:test = {}:{}:{}".format(len(train_img), len(val_img), len(test_img)))
return train_img, val_img, test_img
def train_test_val_split_by_files(img_paths, root_dir):
# 根据文件 train.txt, val.txt, test.txt（里面写的都是对应集合的图片名字） 来定义训练集、验证集和测试集
phases = ['train', 'val', 'test']
img_split = []
for p in phases:
define_path = os.path.join(root_dir, f'{
p}.txt')
print(f'Read {
p} dataset definition from {
define_path}')
assert os.path.exists(define_path)
with open(define_path, 'r') as f:
img_paths = f.readlines()
# img_paths = [os.path.split(img_path.strip())[1] for img_path in img_paths] # NOTE 取消这句备注可以读取绝对地址。
img_split.append(img_paths)
return img_split[0], img_split[1], img_split[2]
def yolo2coco(arg):
root_path = arg.root_dir
print("Loading data from ",root_path)
assert os.path.exists(root_path)
originLabelsDir = os.path.join(root_path, 'labels')
originImagesDir = os.path.join(root_path, 'images')
with open(os.path.join(root_path, 'classes.txt')) as f:
classes = f.read().strip().split()
# images dir name
indexes = os.listdir(originImagesDir)
if arg.random_split or arg.split_by_file:
# 用于保存所有数据的图片信息和标注信息
train_dataset = {
'categories': [], 'annotations': [], 'images': []}
val_dataset = {
'categories': [], 'annotations': [], 'images': []}
test_dataset = {
'categories': [], 'annotations': [], 'images': []}
# 建立类别标签和数字id的对应关系, 类别id从0开始。
for i, cls in enumerate(classes, 0):
train_dataset['categories'].append({
'id': i, 'name': cls, 'supercategory': 'mark'})
val_dataset['categories'].append({
'id': i, 'name': cls, 'supercategory': 'mark'})
test_dataset['categories'].append({
'id': i, 'name': cls, 'supercategory': 'mark'})
if arg.random_split:
print("spliting mode: random split")
train_img, val_img, test_img = train_test_val_split_random(indexes,0.8,0.1,0.1)
elif arg.split_by_file:
print("spliting mode: split by files")
train_img, val_img, test_img = train_test_val_split_by_files(indexes, root_path)
else:
dataset = {
'categories': [], 'annotations': [], 'images': []}
for i, cls in enumerate(classes, 0):
dataset['categories'].append({
'id': i, 'name': cls, 'supercategory': 'mark'})
# 标注的id
ann_id_cnt = 0
for k, index in enumerate(tqdm(indexes)):
# 支持 png jpg 格式的图片。
txtFile = index.replace('images','txt').replace('.jpg','.txt').replace('.png','.txt')
# 读取图像的宽和高
im = cv2.imread(os.path.join(root_path, 'images/') + index)
height, width, _ = im.shape
if arg.random_split or arg.split_by_file:
# 切换dataset的引用对象，从而划分数据集
if index in train_img:
dataset = train_dataset
elif index in val_img:
dataset = val_dataset
elif index in test_img:
dataset = test_dataset
# 添加图像的信息
dataset['images'].append({
'file_name': index,
'id': k,
'width': width,
'height': height})
if not os.path.exists(os.path.join(originLabelsDir, txtFile)):
# 如没标签，跳过，只保留图片信息。
continue
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,y2
H, W, _ = im.shape
x1 = (x - w / 2) * W
y1 = (y - h / 2) * H
x2 = (x + w / 2) * W
y2 = (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': k,
'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
folder = os.path.join(root_path, 'annotations')
if not os.path.exists(folder):
os.makedirs(folder)
if arg.random_split or arg.split_by_file:
for phase in ['train','val','test']:
json_name = os.path.join(root_path, 'annotations/{}.json'.format(phase))
with open(json_name, 'w') as f:
if phase == 'train':
json.dump(train_dataset, f)
elif phase == 'val':
json.dump(val_dataset, f)
elif phase == 'test':
json.dump(test_dataset, f)
print('Save annotation to {}'.format(json_name))
else:
json_name = os.path.join(root_path, 'annotations/{}'.format(arg.save_path))
with open(json_name, 'w') as f:
json.dump(dataset, f)
print('Save annotation to {}'.format(json_name))
if __name__ == "__main__":
yolo2coco(arg)
Execute: python yolo2coco.py --root_dir $ROOT_PATH , and then you can see the generated annotations folder.
Parameter Description
--root_path # 输入根目录$ROOT_PATH的位置。
--save_path # 如果不进行数据集划分，可利用此参数指定输出文件的名字，默认保存为train.json
--random_split # 随机划分参数，若指定--random_split参数，则输出在annotations文件夹下包含
# train.json val.json test.json （默认随机划分成8:1:1）
--split_by_file # 自定义数据集划分，若指定--split_by_file参数，则输出在annotations文件夹
# train.json val.json test.json。需要在$ROOT_PATH文件下有 ./train.txt ./val.txt #
# ./test.txt ，可以这3个文件来定义训练集、验证集、测试集。注意， 这里里面填写的应是图片文件名字，
# 而不是图片的绝对地址。
#（在line 43也自行可以修改一下读取方式，为了方便起见，不推荐把图片放在不同位置）