目录
将下载好的VOC数据集转换为COCO格式(xml转为json)
需要注意的是无论是coco数据集,他们的类别id都是从1开始,如果这里的类别从0开始设置,那么在调用coco的api时就会出现list越界的问题
自己建立COCO数据集格式
如果是通过labelme自行标注的COCO数据集,标注时会对应每张图片生成一个json文件,然后通过json2coco.py(参考http://t.csdn.cn/eOosY)将训练集和验证集分别生成一个json文件 ,json2coco.py源码如下:
import os
import json
import numpy as np
import glob
import shutil
import cv2
from sklearn.model_selection import train_test_split
from labelme import utils
np.random.seed(41)
# 修改1->改成自己的类别
classname_to_id = {
"copymove": 1,
"remove": 2,
"splice": 3
}
class Lableme2CoCo:
def __init__(self):
self.images = []
self.annotations = []
self.categories = []
self.img_id = 0
self.ann_id = 0
def save_coco_json(self, instance, save_path):
json.dump(instance, open(save_path, 'w', encoding='utf-8'), ensure_ascii=False, indent=1) # indent=2 更加美观显示
# 由json文件构建COCO
def to_coco(self, json_path_list):
self._init_categories()
for json_path in json_path_list:
obj = self.read_jsonfile(json_path)
self.images.append(self._image(obj, json_path))
shapes = obj['shapes']
for shape in shapes:
annotation = self._annotation(shape)
self.annotations.append(annotation)
self.ann_id += 1
self.img_id += 1
instance = {}
instance['info'] = 'spytensor created'
instance['license'] = ['license']
instance['images'] = self.images
instance['annotations'] = self.annotations
instance['categories'] = self.categories
return instance
# 构建类别
def _init_categories(self):
for k, v in classname_to_id.items():
category = {}
category['id'] = v
category['name'] = k
self.categories.append(category)
# 构建COCO的image字段
def _image(self, obj, path):
image = {}
img_x = utils.img_b64_to_arr(obj['imageData'])
h, w = img_x.shape[:-1]
image['height'] = h
image['width'] = w
image['id'] = self.img_id
image['file_name'] = os.path.basename(path).replace(".json", ".jpg")
return image
# 构建COCO的annotation字段
def _annotation(self, shape):
# print('shape', shape)
label = shape['label']
# print('label:', label)
points = shape['points']
annotation = {}
annotation['id'] = self.ann_id
annotation['image_id'] = self.img_id
annotation['category_id'] = int(classname_to_id[label])
annotation['segmentation'] = [np.asarray(points).flatten().tolist()]
annotation['bbox'] = self._get_box(points)
annotation['iscrowd'] = 0
annotation['area'] = 1.0
return annotation
# 读取json文件,返回一个json对象
def read_jsonfile(self, path):
with open(path, "r", encoding='utf-8') as f:
return json.load(f)
# COCO的格式: [x1,y1,w,h] 对应COCO的bbox格式
def _get_box(self, points):
min_x = min_y = np.inf
max_x = max_y = 0
for x, y in points:
min_x = min(min_x, x)
min_y = min(min_y, y)
max_x = max(max_x, x)
max_y = max(max_y, y)
return [min_x, min_y, max_x - min_x, max_y - min_y]
# 训练过程中,如果遇到Index put requires the source and destination dtypes match, got Long for the destination and Int for the source
# 参考:https://github.com/open-mmlab/mmdetection/issues/6706
if __name__ == '__main__':
labelme_path = "E:\python\datasets\detr-dataset\dataset"
saved_coco_path = "./detr-dataset/"
print('reading...')
# 创建文件
if not os.path.exists("%scoco/annotations/" % saved_coco_path):
os.makedirs("%scoco/annotations/" % saved_coco_path)
if not os.path.exists("%scoco/train2017/" % saved_coco_path):
os.makedirs("%scoco/train2017" % saved_coco_path)
if not os.path.exists("%scoco/val2017/" % saved_coco_path):
os.makedirs("%scoco/val2017" % saved_coco_path)
# 获取images目录下所有的joson文件列表
print(labelme_path + "/*.json")
json_list_path = glob.glob(labelme_path + "/*.json")
print('json_list_path: ', len(json_list_path))
# 修改2训练集和测试集的比例
# 数据划分,这里没有区分val2017和tran2017目录,所有图片都放在images目录下
train_path, val_path = train_test_split(json_list_path, test_size=0.1, train_size=0.9)
print("train_n:", len(train_path), 'val_n:', len(val_path))
# 把训练集转化为COCO的json格式
l2c_train = Lableme2CoCo()
train_instance = l2c_train.to_coco(train_path)
l2c_train.save_coco_json(train_instance, '%scoco/annotations/instances_train2017.json' % saved_coco_path)
for file in train_path:
# 修改3 换成自己图片的后缀名
img_name = file.replace('json', 'jpg')
temp_img = cv2.imread(img_name)
try:
cv2.imwrite("{}coco/train2017/{}".format(saved_coco_path, img_name.split('\\')[-1]), temp_img)
except Exception as e:
print(e)
print('Wrong Image:', img_name )
continue
print(img_name + '-->', img_name)
for file in val_path:
# 修改4 换成自己图片的后缀名
img_name = file.replace('json', 'jpg')
temp_img = cv2.imread(img_name)
try:
cv2.imwrite("{}coco/val2017/{}".format(saved_coco_path, img_name.split('\\')[-1]), temp_img)
except Exception as e:
print(e)
print('Wrong Image:', img_name)
continue
print(img_name + '-->', img_name)
# 把验证集转化为COCO的json格式
l2c_val = Lableme2CoCo()
val_instance = l2c_val.to_coco(val_path)
l2c_val.save_coco_json(val_instance, '%scoco/annotations/instances_val2017.json' % saved_coco_path)
运行前把classname_to_id 中的类别改为自己数据集的类别,labelme_path和saved_coco_path改为自己的路径,运行后最终生成如下两个文件:
根据如下目录结构将文件放入相应的文件夹中即可
coco
|______annotations # 存放标注信息
| |__instances_train.json
| |__instances_val.json
| |__instances_test.json
|______train # 存放训练集图像
|______val # 存放验证集图像
|______test # 存放测试集图像
将下载好的VOC数据集转换为COCO格式(xml转为json)
对于VOC数据集,每一张图片都有一个对应的.xml文件,而COCO数据集对应的时json文件,这里通过sim10k_to_coco.py(原文链接https://zhuanlan.zhihu.com/p/585928952)直接将所有的.xml文件转化生成一个json文件,对于自己建立COCO数据集的步骤,跳过了生成每一张图片对应一个json文件的步骤。
sim10k_to_coco.py源码如下:
import xml.etree.ElementTree as ET
import os
import json
coco = dict()
coco['images'] = []
coco['type'] = 'instances'
coco['annotations'] = []
coco['categories'] = []
category_set = dict()
image_set = set()
# category_item_id = -1
# VOC数据集的类别id与coco数据集一样都是从1开始,如果初始设为-1,那么转出来的coco的json文件中category_id和类别id会从0开始,不符合coco标准,在调coco.py的时候会报错list越界
category_item_id = 0
image_id = 20180000000
annotation_id = 0
def addCatItem(name):
global category_item_id
category_item = dict()
category_item['supercategory'] = 'none'
category_item_id += 1
category_item['id'] = category_item_id
category_item['name'] = name
coco['categories'].append(category_item)
category_set[name] = category_item_id
return category_item_id
def addImgItem(file_name, size):
global image_id
if file_name is None:
raise Exception('Could not find filename tag in xml file.')
if size['width'] is None:
raise Exception('Could not find width tag in xml file.')
if size['height'] is None:
raise Exception('Could not find height tag in xml file.')
image_id += 1
image_item = dict()
image_item['id'] = image_id
image_item['file_name'] = file_name
image_item['width'] = size['width']
image_item['height'] = size['height']
coco['images'].append(image_item)
image_set.add(file_name)
return image_id
def addAnnoItem(object_name, image_id, category_id, bbox):
global annotation_id
annotation_item = dict()
annotation_item['segmentation'] = []
seg = []
# bbox[] is x,y,w,h
# left_top
seg.append(bbox[0])
seg.append(bbox[1])
# left_bottom
seg.append(bbox[0])
seg.append(bbox[1] + bbox[3])
# right_bottom
seg.append(bbox[0] + bbox[2])
seg.append(bbox[1] + bbox[3])
# right_top
seg.append(bbox[0] + bbox[2])
seg.append(bbox[1])
annotation_item['segmentation'].append(seg)
annotation_item['area'] = bbox[2] * bbox[3]
annotation_item['iscrowd'] = 0
annotation_item['ignore'] = 0
annotation_item['image_id'] = image_id
annotation_item['bbox'] = bbox
annotation_item['category_id'] = category_id
annotation_id += 1
annotation_item['id'] = annotation_id
coco['annotations'].append(annotation_item)
def _read_image_ids(image_sets_file):
ids = []
with open(image_sets_file) as f:
for line in f:
ids.append(line.rstrip())
return ids
"""通过txt文件生成"""
#split ='train' 'va' 'trainval' 'test'
def parseXmlFiles_by_txt(data_dir,json_save_path,split='train'):
print("hello")
labelfile=split+".txt"
image_sets_file = data_dir + "/ImageSets/Main/"+labelfile
ids=_read_image_ids(image_sets_file)
for _id in ids:
xml_file=data_dir + f"/Annotations/{_id}.xml"
bndbox = dict()
size = dict()
current_image_id = None
current_category_id = None
file_name = None
size['width'] = None
size['height'] = None
size['depth'] = None
tree = ET.parse(xml_file)
root = tree.getroot()
if root.tag != 'annotation':
raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))
# elem is <folder>, <filename>, <size>, <object>
for elem in root:
current_parent = elem.tag
current_sub = None
object_name = None
if elem.tag == 'folder':
continue
if elem.tag == 'filename':
file_name = elem.text
if file_name in category_set:
raise Exception('file_name duplicated')
# add img item only after parse <size> tag
elif current_image_id is None and file_name is not None and size['width'] is not None:
if file_name not in image_set:
current_image_id = addImgItem(file_name, size)
print('add image with {} and {}'.format(file_name, size))
else:
raise Exception('duplicated image: {}'.format(file_name))
# subelem is <width>, <height>, <depth>, <name>, <bndbox>
for subelem in elem:
bndbox['xmin'] = None
bndbox['xmax'] = None
bndbox['ymin'] = None
bndbox['ymax'] = None
current_sub = subelem.tag
if current_parent == 'object' and subelem.tag == 'name':
object_name = subelem.text
if object_name not in category_set:
current_category_id = addCatItem(object_name)
else:
current_category_id = category_set[object_name]
elif current_parent == 'size':
if size[subelem.tag] is not None:
raise Exception('xml structure broken at size tag.')
size[subelem.tag] = int(subelem.text)
# option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>
for option in subelem:
if current_sub == 'bndbox':
if bndbox[option.tag] is not None:
raise Exception('xml structure corrupted at bndbox tag.')
bndbox[option.tag] = int(option.text)
# only after parse the <object> tag
if bndbox['xmin'] is not None:
if object_name is None:
raise Exception('xml structure broken at bndbox tag')
if current_image_id is None:
raise Exception('xml structure broken at bndbox tag')
if current_category_id is None:
raise Exception('xml structure broken at bndbox tag')
bbox = []
# x
bbox.append(bndbox['xmin'])
# y
bbox.append(bndbox['ymin'])
# w
bbox.append(bndbox['xmax'] - bndbox['xmin'])
# h
bbox.append(bndbox['ymax'] - bndbox['ymin'])
print('add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id,
bbox))
addAnnoItem(object_name, current_image_id, current_category_id, bbox)
json.dump(coco, open(json_save_path, 'w'))
"""直接从xml文件夹中生成"""
def parseXmlFiles(xml_path,json_save_path):
for f in os.listdir(xml_path):
if not f.endswith('.xml'):
continue
# print(path)
bndbox = dict()
size = dict()
current_image_id = None
current_category_id = None
file_name = None
size['width'] = None
size['height'] = None
size['depth'] = None
xml_file = os.path.join(xml_path, f)
print(xml_file)
tree = ET.parse(xml_file)
root = tree.getroot()
if root.tag != 'annotation':
raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))
# elem is <folder>, <filename>, <size>, <object>
for elem in root:
current_parent = elem.tag
current_sub = None
object_name = None
if elem.tag == 'folder':
continue
if elem.tag == 'filename':
# 改成与xml文件同名的图片文件
file_name = f.split(".")[0] + ".jpg"
# file_name = elem.text
# if file_name in category_set:
# raise Exception('file_name duplicated')
# add img item only after parse <size> tag
elif current_image_id is None and file_name is not None and size['width'] is not None:
if file_name not in image_set:
current_image_id = addImgItem(file_name, size)
print('add image with {} and {}'.format(file_name, size))
else:
raise Exception('duplicated image: {}'.format(file_name))
# subelem is <width>, <height>, <depth>, <name>, <bndbox>
for subelem in elem:
bndbox['xmin'] = None
bndbox['xmax'] = None
bndbox['ymin'] = None
bndbox['ymax'] = None
current_sub = subelem.tag
if current_parent == 'object' and subelem.tag == 'name':
object_name = subelem.text
if object_name not in category_set:
current_category_id = addCatItem(object_name)
else:
current_category_id = category_set[object_name]
elif current_parent == 'size':
if size[subelem.tag] is not None:
raise Exception('xml structure broken at size tag.')
size[subelem.tag] = int(subelem.text)
# option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>
for option in subelem:
if current_sub == 'bndbox':
if bndbox[option.tag] is not None:
raise Exception('xml structure corrupted at bndbox tag.')
bndbox[option.tag] = int(option.text)
# only after parse the <object> tag
if bndbox['xmin'] is not None:
if object_name is None:
raise Exception('xml structure broken at bndbox tag')
if current_image_id is None:
raise Exception('xml structure broken at bndbox tag')
if current_category_id is None:
raise Exception('xml structure broken at bndbox tag')
bbox = []
# x
bbox.append(bndbox['xmin'])
# y
bbox.append(bndbox['ymin'])
# w
bbox.append(bndbox['xmax'] - bndbox['xmin'])
# h
bbox.append(bndbox['ymax'] - bndbox['ymin'])
print('add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id,
bbox))
addAnnoItem(object_name, current_image_id, current_category_id, bbox)
json.dump(coco, open(json_save_path, 'w'))
if __name__ == '__main__':
#通过txt文件生成
# voc_data_dir="E:/VOCdevkit/VOC2007"
# json_save_path="E:/VOCdevkit/voc2007trainval.json"
# parseXmlFiles_by_txt(voc_data_dir,json_save_path,"trainval")
#通过文件夹生成
ann_path="E:\python\github\detr-main\detr-dataset\coco2\Annotations_val"
json_save_path="instances_val.json"
parseXmlFiles(ann_path,json_save_path)
该代码只需将下图中的ann_path和json_save_path的路径改为自己的即可
if __name__ == '__main__':
#通过txt文件生成
# voc_data_dir="E:/VOCdevkit/VOC2007"
# json_save_path="E:/VOCdevkit/voc2007trainval.json"
# parseXmlFiles_by_txt(voc_data_dir,json_save_path,"trainval")
#通过文件夹生成
ann_path="E:\python\github\detr-main\detr-dataset\coco2\Annotations_val"
json_save_path="instances_val.json"
parseXmlFiles(ann_path,json_save_path)
最后的文件目录结构参照上一节