1、数据格式样本
1.1 COCO的json数据格式
{"info": {"description": "COCO 2017 Dataset","url": "http://cocodataset.org","version": "1.0","year": 2017,"contributor": "COCO Consortium","date_created": "2017/09/01"},"licenses": [{"url": "http://creativecommons.org/licenses/by-nc-sa/2.0/","id": 1,"name": "Attribution-NonCommercial-ShareAlike License"}],
"images": [{"license": 4,"file_name": "000000397133.jpg","coco_url": "http://images.cocodataset.org/val2017/000000397133.jpg","height": 427,"width": 640,"date_captured": "2013-11-14 17:02:52","flickr_url": "http://farm7.staticflickr.com/6116/6255196340_da26cf2c9e_z.jpg","id": 397133},{"license": 1,"file_name": "000000037777.jpg","coco_url": "http://images.cocodataset.org/val2017/000000037777.jpg","height": 230,"width": 352,"date_captured": "2013-11-14 20:55:31","flickr_url": "http://farm9.staticflickr.com/8429/7839199426_f6d48aa585_z.jpg","id": 37777}],
"annotations": [{"segmentation":[[510.66,423.01,511.72,420.03,510.45,416.0,510.34,413.02,510.77,410.26,510.77,407.5,510.34,405.16,511.51,402.83,511.41,400.49,510.24,398.16,509.39,397.31,504.61,399.22,502.17,399.64,500.89,401.66,500.47,402.08,499.09,401.87,495.79,401.98,490.59,401.77,488.79,401.77,485.39,398.58,483.9,397.31,481.56,396.35,478.48,395.93,476.68,396.03,475.4,396.77,473.92,398.79,473.28,399.96,473.49,401.87,474.56,403.47,473.07,405.59,473.39,407.71,476.68,409.41,479.23,409.73,481.56,410.69,480.4,411.85,481.35,414.93,479.86,418.65,477.32,420.03,476.04,422.58,479.02,422.58,480.29,423.01,483.79,419.93,486.66,416.21,490.06,415.57,492.18,416.85,491.65,420.24,492.82,422.9,493.56,424.39,496.43,424.6,498.02,423.01,498.13,421.31,497.07,420.03,497.07,415.15,496.33,414.51,501.1,411.96,502.06,411.32,503.02,415.04,503.33,418.12,501.1,420.24,498.98,421.63,500.47,424.39,505.03,423.32,506.2,421.31,507.69,419.5,506.31,423.32,510.03,423.01,510.45,423.01]],"area": 702.1057499999998,"iscrowd": 0,"image_id": 289343,"bbox": [473.07,395.93,38.65,28.67],"category_id": 18,"id": 1768}],
"categories": [{"supercategory": "person","id": 1,"name": "person"},{"supercategory": "vehicle","id": 2,"name": "bicycle"},{"supercategory": "vehicle","id": 3,"name": "car"},{"supercategory": "vehicle","id": 4,"name": "motorcycle"},{"supercategory": "vehicle","id": 5,"name": "airplane"},{"supercategory": "vehicle","id": 6,"name": "bus"},{"supercategory": "vehicle","id": 7,"name": "train"},{"supercategory": "vehicle","id": 8,"name": "truck"},{"supercategory": "vehicle","id": 9,"name": "boat"},{"supercategory": "outdoor","id": 10,"name": "traffic light"},{"supercategory": "outdoor","id": 11,"name": "fire hydrant"},{"supercategory": "outdoor","id": 13,"name": "stop sign"},{"supercategory": "outdoor","id": 14,"name": "parking meter"},{"supercategory": "outdoor","id": 15,"name": "bench"},{"supercategory": "animal","id": 16,"name": "bird"},{"supercategory": "animal","id": 17,"name": "cat"},{"supercategory": "animal","id": 18,"name": "dog"},{"supercategory": "animal","id": 19,"name": "horse"},{"supercategory": "animal","id": 20,"name": "sheep"},{"supercategory": "animal","id": 21,"name": "cow"},{"supercategory": "animal","id": 22,"name": "elephant"},{"supercategory": "animal","id": 23,"name": "bear"},{"supercategory": "animal","id": 24,"name": "zebra"},{"supercategory": "animal","id": 25,"name": "giraffe"},{"supercategory": "accessory","id": 27,"name": "backpack"},{"supercategory": "accessory","id": 28,"name": "umbrella"},{"supercategory": "accessory","id": 31,"name": "handbag"},{"supercategory": "accessory","id": 32,"name": "tie"},{"supercategory": "accessory","id": 33,"name": "suitcase"},{"supercategory": "sports","id": 34,"name": "frisbee"},{"supercategory": "sports","id": 35,"name": "skis"},{"supercategory": "sports","id": 36,"name": "snowboard"},{"supercategory": "sports","id": 37,"name": "sports ball"},{"supercategory": "sports","id": 38,"name": "kite"},{"supercategory": "sports","id": 39,"name": "baseball bat"},{"supercategory": "sports","id": 40,"name": "baseball glove"},{"supercategory": "sports","id": 41,"name": "skateboard"},{"supercategory": "sports","id": 42,"name": "surfboard"},{"supercategory": "sports","id": 43,"name": "tennis racket"},{"supercategory": "kitchen","id": 44,"name": "bottle"},{"supercategory": "kitchen","id": 46,"name": "wine glass"},{"supercategory": "kitchen","id": 47,"name": "cup"},{"supercategory": "kitchen","id": 48,"name": "fork"},{"supercategory": "kitchen","id": 49,"name": "knife"},{"supercategory": "kitchen","id": 50,"name": "spoon"},{"supercategory": "kitchen","id": 51,"name": "bowl"},{"supercategory": "food","id": 52,"name": "banana"},{"supercategory": "food","id": 53,"name": "apple"},{"supercategory": "food","id": 54,"name": "sandwich"},{"supercategory": "food","id": 55,"name": "orange"},{"supercategory": "food","id": 56,"name": "broccoli"},{"supercategory": "food","id": 57,"name": "carrot"},{"supercategory": "food","id": 58,"name": "hot dog"},{"supercategory": "food","id": 59,"name": "pizza"},{"supercategory": "food","id": 60,"name": "donut"},{"supercategory": "food","id": 61,"name": "cake"},{"supercategory": "furniture","id": 62,"name": "chair"},{"supercategory": "furniture","id": 63,"name": "couch"},{"supercategory": "furniture","id": 64,"name": "potted plant"},{"supercategory": "furniture","id": 65,"name": "bed"},{"supercategory": "furniture","id": 67,"name": "dining table"},{"supercategory": "furniture","id": 70,"name": "toilet"},{"supercategory": "electronic","id": 72,"name": "tv"},{"supercategory": "electronic","id": 73,"name": "laptop"},{"supercategory": "electronic","id": 74,"name": "mouse"},{"supercategory": "electronic","id": 75,"name": "remote"},{"supercategory": "electronic","id": 76,"name": "keyboard"},{"supercategory": "electronic","id": 77,"name": "cell phone"},{"supercategory": "appliance","id": 78,"name": "microwave"},{"supercategory": "appliance","id": 79,"name": "oven"},{"supercategory": "appliance","id": 80,"name": "toaster"},{"supercategory": "appliance","id": 81,"name": "sink"},{"supercategory": "appliance","id": 82,"name": "refrigerator"},{"supercategory": "indoor","id": 84,"name": "book"},{"supercategory": "indoor","id": 85,"name": "clock"},{"supercategory": "indoor","id": 86,"name": "vase"},{"supercategory": "indoor","id": 87,"name": "scissors"},{"supercategory": "indoor","id": 88,"name": "teddy bear"},{"supercategory": "indoor","id": 89,"name": "hair drier"},{"supercategory": "indoor","id": 90,"name": "toothbrush"}]}
其中 info:可以不关注 images：主要包含一张图片的公共信息，如宽高，图片名，图片id
file_name:图片名称 height：高 width：宽 id：图片的id。在images中是唯一的
annotations：主要包含图像中每一个对象的信息，如标出的对象的边框box，标出对象的类别如人，狗，猫对应的id
image_id:图片id对应上面images中的id，但是这个不是唯一的。因为一张图中可能会标出多个对象。 bbox：是标注对象的边框信息[xmin,ymin,width,height] category_id:对象类别id，如person对应的id为1
categories：主要的对象类别的信息，如类别名称，类别id(COCO数据集有90个类别)，我们只关注id、和name就行
id:类别id，唯一 name:类别名称
1.2、VOC的xml数据格式
<?xml version='1.0' encoding='utf-8'?>
<annotation>
<folder>JPEGImages</folder>
<filename>PartA_00000.jpg</filename>
<path>/home/robot11/py-faster-rcnn/data/VOCdevkit2007/VOC2007/JPEGImages/00000.jpg</path>
<source>
<database>Unknown</database>
</source>
<size>
<width>1070</width>
<height>594</height>
<depth>3</depth>
</size>
<segmented>0</segmented>
<object>
<name>head</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>64</xmin>
<ymin>222</ymin>
<xmax>107</xmax>
<ymax>271</ymax>
</bndbox>
</object>
</annotation>
2、COCO的JSON转VOC的XML
import os
import json
import cv2
from lxml import etree
import xml.etree.cElementTree as ET
import time
import pandas as pd
from tqdm import tqdm
from xml.dom.minidom import Document
anno = "instances_val2017.json"
xmldir = "train/"
with open(anno, 'r') as load_f:
f = json.load(load_f)
df_anno = pd.DataFrame(f['annotations'])
imgs = f['images']
cata={}
def createCate():
global cata
df_cate = f['categories']
for item in df_cate:
cata[item['id']]=item['name']
def json2xml():
global cata
for im in imgs:
filename = im['file_name']
height = im['height']
img_id = im['id']
width = im['width']
doc = Document()
annotation = doc.createElement('annotation')
doc.appendChild(annotation)
filenamedoc = doc.createElement("filename")
annotation.appendChild(filenamedoc)
filename_txt=doc.createTextNode(filename)
filenamedoc.appendChild(filename_txt)
size = doc.createElement("size")
annotation.appendChild(size)
widthdoc = doc.createElement("width")
size.appendChild(widthdoc)
width_txt = doc.createTextNode(str(width))
widthdoc.appendChild(width_txt)
heightdoc = doc.createElement("height")
size.appendChild(heightdoc)
height_txt = doc.createTextNode(str(height))
heightdoc.appendChild(height_txt)
annos = df_anno[df_anno["image_id"].isin([img_id])]
for index, row in annos.iterrows():
bbox = row["bbox"]
category_id = row["category_id"]
cate_name = cata[category_id]
object = doc.createElement('object')
annotation.appendChild(object)
name = doc.createElement('name')
object.appendChild(name)
name_txt = doc.createTextNode(cate_name)
name.appendChild(name_txt)
pose = doc.createElement('pose')
object.appendChild(pose)
pose_txt = doc.createTextNode('Unspecified')
pose.appendChild(pose_txt)
truncated = doc.createElement('truncated')
object.appendChild(truncated)
truncated_txt = doc.createTextNode('0')
truncated.appendChild(truncated_txt)
difficult = doc.createElement('difficult')
object.appendChild(difficult)
difficult_txt = doc.createTextNode('0')
difficult.appendChild(difficult_txt)
bndbox = doc.createElement('bndbox')
object.appendChild(bndbox)
xmin = doc.createElement('xmin')
bndbox.appendChild(xmin)
xmin_txt = doc.createTextNode(str(int(bbox[0])))
xmin.appendChild(xmin_txt)
ymin = doc.createElement('ymin')
bndbox.appendChild(ymin)
ymin_txt = doc.createTextNode(str(int(bbox[1])))
ymin.appendChild(ymin_txt)
xmax = doc.createElement('xmax')
bndbox.appendChild(xmax)
xmax_txt = doc.createTextNode(str(int(bbox[0]+bbox[2])))
xmax.appendChild(xmax_txt)
ymax = doc.createElement('ymax')
bndbox.appendChild(ymax)
ymax_txt = doc.createTextNode(str(int(bbox[1]+bbox[3])))
ymax.appendChild(ymax_txt)
xmlpath = os.path.join(xmldir,filename.replace('.jpg','.xml'))
f = open(xmlpath, "w")
f.write(doc.toprettyxml(indent=" "))
f.close()
createCate()
json2xml()
3、VOC的xml转COCO的json
import os
import glob
import json
import shutil
import numpy as np
import xml.etree.ElementTree as ET
path2 = "."
START_BOUNDING_BOX_ID = 1
def get(root, name):
return root.findall(name)
def 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 vars
def convert(xml_list, json_file):
json_dict = {"images": [], "type": "instances", "annotations": [], "categories": []}
categories = pre_define_categories.copy()
bnd_id = START_BOUNDING_BOX_ID
all_categories = {}
for index, line in enumerate(xml_list):
# print("Processing %s"%(line))
xml_f = line
tree = ET.parse(xml_f)
root = tree.getroot()
xml = os.path.split(xml_f)[-1].split(".")[0]
img = xml+".jpg"
filename = img
image_id = 20210000001 + index
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)
for obj in get(root, 'object'):
category = get_and_check(obj, 'name', 1).text
if category in all_categories:
all_categories[category] += 1
else:
all_categories[category] = 1
if category not in categories:
if only_care_pre_define_categories:
continue
new_id = len(categories) + 1
print(
"[warning] category '{}' not in 'pre_define_categories'({}), create new id: {} automatically".format(
category, pre_define_categories, new_id))
categories[category] = new_id
category_id = categories[category]
bndbox = get_and_check(obj, 'bndbox', 1)
xmin = int(float(get_and_check(bndbox, 'xmin', 1).text))
ymin = int(float(get_and_check(bndbox, 'ymin', 1).text))
xmax = int(float(get_and_check(bndbox, 'xmax', 1).text))
ymax = int(float(get_and_check(bndbox, 'ymax', 1).text))
assert (xmax > xmin), "xmax <= xmin, {}".format(line)
assert (ymax > ymin), "ymax <= ymin, {}".format(line)
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 + 1
for 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()
print("------------create {} done--------------".format(json_file))
print("find {} categories: {} -->>> your pre_define_categories {}: {}".format(len(all_categories),
all_categories.keys(),
len(pre_define_categories),
pre_define_categories.keys()))
print("category: id --> {}".format(categories))
print(categories.keys())
print(categories.values())
if __name__ == '__main__':
classes = ['head']
pre_define_categories = {}
for i, cls in enumerate(classes):
pre_define_categories[cls] = i + 1
# pre_define_categories = {'a1': 1, 'a3': 2, 'a6': 3, 'a9': 4, "a10": 5}
only_care_pre_define_categories = True
train_ratio = 0.9
save_json_train = 'head_train2021.json'
save_json_val = 'head_val2021.json'
xml_dir = "./Annotations1"
xml_list = glob.glob(xml_dir + "/*.xml")
xml_list = np.sort(xml_list)
np.random.seed(100)
np.random.shuffle(xml_list)
train_num = int(len(xml_list) * train_ratio)
xml_list_train = xml_list[:train_num]
xml_list_val = xml_list[train_num:]
convert(xml_list_train, save_json_train)
convert(xml_list_val, save_json_val)
if os.path.exists(path2 + "/images/train2021"):
shutil.rmtree(path2 + "/images/train2021")
os.makedirs(path2 + "/images/train2021")
if os.path.exists(path2 + "/images/val2021"):
shutil.rmtree(path2 + "/images/val2021")
os.makedirs(path2 + "/images/val2021")
f1 = open("train.txt", "w")
for xml in xml_list_train:
xml = os.path.split(xml)[-1].split(".")[0]
img = xml+".jpg"
f1.write(img + "\n")
shutil.copyfile(path2+"/JPEGImages/"+img, path2 + "/images/train2021/" + img)
f2 = open("test.txt", "w")
for xml in xml_list_val:
xml = os.path.split(xml)[-1].split(".")[0]
img = xml+".jpg"
f2.write(img + "\n")
shutil.copyfile(path2+"/JPEGImages/"+img, path2 + "/images/val2021/" + img)
f1.close()
f2.close()
print("-------------------------------")
print("train number:", len(xml_list_train))
print("val number:", len(xml_list_val))