上一篇我们在ubuntu系统下搭建了mmdetection所需的环境,这篇将介绍如何转化数据集(如果已经是coco数据集则可以跳过本文)。
voc和coco格式的数据集都能放在mmdetection下训练测试,但是为了方便后续的大图切分操作,因此将voc格式的数据集转为coco格式。
新建一个tmp_folder的文件夹,将labelimg标注的xml和jpg放在tmp_folder文件夹下,并且在同级目录下新建一个convert_data.py
的py文件,将下述代码复制进去,数据目录如下:
.
├── ./data
│ ├── ./data/tmp_folder
│ │ ├── ./data/tmp_folder/0.xml
│ │ ├── ./data/tmp_folder/0.jpg
│ │ ├── ./data/tmp_folder/1000.jpg
│ │ ├── ./data/tmp_folder/1000.xml
│ │ ├── ./data/tmp_folder/1001.jpg
│ │ ├── ./data/tmp_folder/1001.xml
│ │ ├── ...
│ ├── ./c
代码如下:
# coding:utf-8
# pip install lxml
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()
filename = os.path.basename(xml_f)[:-4] + suffix
image_id = index +1
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)
## Cruuently we do not support segmentation
# segmented = get_and_check(root, 'segmented', 1).text
# assert segmented == '0'
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(os.path.join("annotations", 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__':
# 类别
classes = ['1', '5', '12', '16']
# 后缀
suffix = '.jpg'
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
# only_care_pre_define_categories = False
train_ratio = 0.9
save_json_train = 'instances_train2017.json'
save_json_val = 'instances_val2017.json'
xml_dir = "./tmp_folder"
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:]
if os.path.exists(path2 + "/annotations"):
shutil.rmtree(path2 + "/annotations")
os.makedirs(path2 + "/annotations")
convert(xml_list_train, save_json_train)
convert(xml_list_val, save_json_val)
if os.path.exists(path2 + "/train2017"):
shutil.rmtree(path2 + "/train2017")
os.makedirs(path2 + "/train2017")
if os.path.exists(path2 + "/val2017"):
shutil.rmtree(path2 + "/val2017")
os.makedirs(path2 + "/val2017")
f1 = open("train.txt", "w")
for xml in xml_list_train:
img = xml[:-4] + suffix
f1.write(os.path.basename(xml)[:-4] + "\n")
shutil.copyfile(img, path2 + "/train2017/" + os.path.basename(img))
f2 = open("test.txt", "w")
for xml in xml_list_val:
img = xml[:-4] + suffix
f2.write(os.path.basename(xml)[:-4] + "\n")
shutil.copyfile(img, path2 + "/val2017/" + os.path.basename(img))
f1.close()
f2.close()
os.remove("train.txt")
os.remove("test.txt")
print("-------------------------------")
print("train number:", len(xml_list_train))
print("val number:", len(xml_list_val))
代码的第103行和105行需要修改为自己的配置,其中103行是标签类别,105行是图片后缀,如果数据集同时有jpg/png/bmp等不同类别的,暂时不能使用本代码
python convert_data.py
此时在目录下会生成3个文件夹,其中annotations是标签数据,train2017和val2017是按9:1划分的图像数据