COCO格式转化为YOLOv8格式
目录格式
yolov8仅支持YOLO格式的标签,COCO的默认标签为JSON格式,所以需要将COCO格式转换为YOLO格式。
如果训练COCO数据集的话一定要按照这个格式,摆放目录images,labels这两个目录名不可以改变
因为在内部已经写好了就这么去找数据,如果不按照这个规则写就会报错:No labels found in
datasets
|
coco
|
images
|
train2017
val2017
labels
|
train2017
val2017
代码
该代码可将COCO格式转换为YOLO格式并保存在labels/下。这里需要运行两次,train和val都需要转换。
import os
import json
from tqdm import tqdm
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--json_path', default='/home/ubuntu/data/coco2017/annotations/instances_train2017.json',type=str, help="input: coco format(json)")
parser.add_argument('--save_path', default='/home/ubuntu/data/coco2017/labels/train2017', 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] / 2.0
y = box[1] + box[3] / 2.0
w = box[2]
h = box[3]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
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!
for i, category in enumerate(data['categories']):
id_map[category['id']] = i
# 通过事先建表来降低时间复杂度
max_id = 0
for img in data['images']:
max_id = max(max_id, img['id'])
# 注意这里不能写作 [[]]*(max_id+1),否则列表内的空列表共享地址
img_ann_dict = [[] for i in range(max_id+1)]
for i, ann in enumerate(data['annotations']):
img_ann_dict[ann['image_id']].append(i)
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]))'''
# 这里可以直接查表而无需重复遍历
for ann_id in img_ann_dict[img_id]:
ann = data['annotations'][ann_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()