Many training algorithms use the coco format, and the original data set may use the yolov5 data format, so write a simple tutorial;
The directory format of the yolov5 dataset:
images storage images, such as 1.jpg, 2.jpg.
labels store the annotation information of the corresponding image, such as 1.txt, 2.txt.
The information in the txt is as follows:
(Box height) Each line corresponds to a bbox frame information, which are class_id, xc (the x coordinate of the center of the box), yc (the x coordinate of the center of the box), w (the width of the box), h (the height of the box)
The directory of the coco dataset is as follows:
The format of instances_test2017.json is as follows:
The overall structure of #COCO is as follows
{
"info": info,
"licenses": [license],
"categories": [categories],
"images": [image],
"annotations": [annotation],
}
#The descriptions of info, license, categories, image, and annotation are as follows -----
info = {
"year": int, #year
"version": str, #dataset version
"description": str, #dataset description
"contributor": str, #The provider of the data set
"url": str, #The download address of the data set
"date_created": datetime, #The creation date of the dataset
}
categories = {
"id": int, #category id
"name": str, #category name
"supercategory": str, ##large category name
}
license = {
"id": int,
"name": str,
"url": str,
}
image = {
"id": int, #The index id of the image, specify by yourself
"width": int, #image width
"height": int, #image height
"file_name": str, #The file name of the image
"license": int,
"flickr_url": str,
"coco_url": str,
"date_captured": datetime,
}
annotation = {
"id": int, #boudingbox index id, specify by yourself
"image_id": int, #corresponds to the index id of the image where it is located;
"category_id": int, #id of the category to which it belongs;
"segmentation": RLE or [polygon], #segmented point set sequence;
"area": float, the area of #bbox
"bbox": [x,y,width,height], #Important, the coordinates of the upper left corner, the width and height of the bbox;
"iscrowd": 0 or 1, ##Is it crowded
# }
The completed conversion code is as follows:
import json
import os
import shut-off
import cv2
# info, license, categories structure initialization;
# The information in train.json, val.json, and test.json is consistent;
# info, the license is temporarily unavailable
info = {
"year": 2022,
"version": '1.0',
"date_created": 2022-10-15
}
licenses = {
"id": 1,
"name": "null",
"url": "null",
}
#Your own label category should correspond to yolov5's;
categories = [
{
"id": 0,
"name": 'class_1',
"supercategory": 'lines',
},
{
"id": 1,
"name": 'class_2',
"supercategory": 'lines',
}
]
#Initialize train, test data dictionary
# info licenses categories are consistent in train and test;
train_data = {'info': info, 'licenses': licenses, 'categories': categories, 'images': [], 'annotations': []}
test_data = {'info': info, 'licenses': licenses, 'categories': categories, 'images': [], 'annotations': []}
# image_path corresponds to the image path of yolov5, such as images/train;
# label_path corresponds to the label path of yolov5, for example, labels/train corresponds to images;
def v5_covert_coco_format(image_path, label_path):
images = []
annotations = []
for index, img_file in enumerate(os. listdir(image_path)):
if img_file.endswith('.jpg'):
image_info = {}
img = cv2.imread(os.path.join(image_path, img_file))
height, width, channel = img. shape
image_info['id'] = index
image_info['file_name'] = img_file
image_info['width'], image_info['height'] = width, height
else:
continue
if image_info != {}:
images.append(image_info)
# Processing label information -------
label_file = os.path.join(label_path, img_file.replace('.jpg', '.txt'))
with open(label_file, 'r') as f:
for idx, line in enumerate(f. readlines()):
info_annotation = {}
class_num, xs, ys, ws, hs = line.strip().split(' ')
class_id, xc, yc, w, h = int(class_num), float(xs), float(ys), float(ws), float(hs)
xmin = (xc - w / 2) * width
ymin = (yc - h / 2) * height
xmax = (xc + w / 2) * width
ymax = (yc + h / 2) * height
bbox_w = int(width * w)
bbox_h = int(height * h)
img_copy = img[int(ymin):int(ymax),int(xmin):int(xmax)].copy()
info_annotation["category_id"] = class_id # category id
info_annotation['bbox'] = [xmin, ymin, bbox_w, bbox_h] ## coordinates of bbox
info_annotation['area'] = bbox_h * bbox_w ###area
info_annotation['image_id'] = index # id of bbox
info_annotation['id'] = index * 100 + idx # id of bbox
# cv2.imwrite(f"./temp/{info_annotation['id']}.jpg", img_copy)
info_annotation['segmentation'] = [[xmin, ymin, xmax, ymin, xmax, ymax, xmin, ymax]] # coordinates of four points
info_annotation['iscrowd'] = 0 # singleton
annotations.append(info_annotation)
return images, annotations
# key == train, test, val
# Corresponding to the json file to be generated, such as instances_train2017.json, instances_test2017.json, instances_val2017.json
# Just to avoid duplicating code. . . . .
def gen_json_file(yolov5_data_path, coco_format_path, key):
# json path
json_path = os.path.join(coco_format_path, f'annotations/instances_{key}2017.json')
dst_path = os.path.join(coco_format_path, f'{key}2017')
if not os.path.exists(os.path.dirname(json_path)):
os.makedirs(os.path.dirname(json_path), exist_ok=True)
data_path = os.path.join(yolov5_data_path, f'images/{key}')
label_path = os.path.join(yolov5_data_path, f'labels/{key}')
images, anns = v5_covert_coco_format(data_path, label_path)
if key == 'train':
train_data['images'] = images
train_data['annotations'] = anns
with open(json_path, 'w') as f:
json.dump(train_data, f, indent=2)
# shutil. copy(data_path,'')
elif key == 'test':
test_data['images'] = images
test_data['annotations'] = anns
with open(json_path, 'w') as f:
json.dump(test_data, f, indent=2)
else:
print(f'key is {key}')
print(f'generate {key} json success!')
return
if __name__ == '__main__':
yolov5_data_path = '/your/yolov5/datasets/path'
coco_format_path = '/your/coco/datasets/path'
gen_json_file(yolov5_data_path, coco_format_path, key='train')
gen_json_file(yolov5_data_path, coco_format_path, key='test')