labelme转COCO数据集(物体检测)
数据 检测 物体 coco
2023-09-14 09:05:45 时间
本次采用的数据集是Labelme标注的数据集,地址:链接:https://pan.baidu.com/s/1nxo9-NpNWKK4PwDZqwKxGQ 提取码:kp4e,需要将其转为COCO格式的数据集。转换代码如下:
新建labelme2coco.py
import argparse
import json
import matplotlib.pyplot as plt
import skimage.io as io
import cv2
from labelme import utils
import numpy as np
import glob
import PIL.Image
REQUIRE_MASK = False
labels = {'aircraft': 1, 'oiltank': 2}
class labelme2coco(object):
def __init__(self, labelme_json=[], save_json_path='./new.json'):
'''
:param labelme_json: the list of all labelme json file paths
:param save_json_path: the path to save new json
'''
self.labelme_json = labelme_json
self.save_json_path = save_json_path
self.images = []
self.categories = []
self.annotations = []
# self.data_coco = {}
self.label = []
self.annID = 1
self.height = 0
self.width = 0
self.require_mask = REQUIRE_MASK
self.save_json()
def data_transfer(self):
for num, json_file in enumerate(self.labelme_json):
if not json_file == self.save_json_path:
with open(json_file, 'r') as fp:
data = json.load(fp)
self.images.append(self.image(data, num))
for shapes in data['shapes']:
print("label is ")
print(shapes['label'])
label = shapes['label']
# if label[1] not in self.label:
if label not in self.label:
print("find new category: ")
self.categories.append(self.categorie(label))
print(self.categories)
# self.label.append(label[1])
self.label.append(label)
points = shapes['points']
self.annotations.append(self.annotation(points, label, num))
self.annID += 1
def image(self, data, num):
image = {}
img = utils.img_b64_to_arr(data['imageData'])
height, width = img.shape[:2]
img = None
image['height'] = height
image['width'] = width
image['id'] = num + 1
image['file_name'] = data['imagePath'].split('/')[-1]
self.height = height
self.width = width
return image
def categorie(self, label):
categorie = {}
categorie['supercategory'] = label
# categorie['supercategory'] = label
categorie['id'] = labels[label] # 0 默认为背景
categorie['name'] = label
return categorie
def annotation(self, points, label, num):
annotation = {}
print(points)
x1 = points[0][0]
y1 = points[0][1]
x2 = points[1][0]
y2 = points[1][1]
contour = np.array([[x1, y1], [x2, y1], [x2, y2], [x1, y2]]) # points = [[x1, y1], [x2, y2]] for rectangle
contour = contour.astype(int)
area = cv2.contourArea(contour)
print("contour is ", contour, " area = ", area)
annotation['segmentation'] = [list(np.asarray([[x1, y1], [x2, y1], [x2, y2], [x1, y2]]).flatten())]
# [list(np.asarray(contour).flatten())]
annotation['iscrowd'] = 0
annotation['area'] = area
annotation['image_id'] = num + 1
if self.require_mask:
annotation['bbox'] = list(map(float, self.getbbox(points)))
else:
x1 = points[0][0]
y1 = points[0][1]
width = points[1][0] - x1
height = points[1][1] - y1
annotation['bbox'] = list(np.asarray([x1, y1, width, height]).flatten())
annotation['category_id'] = self.getcatid(label)
annotation['id'] = self.annID
return annotation
def getcatid(self, label):
for categorie in self.categories:
# if label[1]==categorie['name']:
if label == categorie['name']:
return categorie['id']
return -1
def getbbox(self, points):
polygons = points
mask = self.polygons_to_mask([self.height, self.width], polygons)
return self.mask2box(mask)
def mask2box(self, mask):
# np.where(mask==1)
index = np.argwhere(mask == 1)
rows = index[:, 0]
clos = index[:, 1]
left_top_r = np.min(rows) # y
left_top_c = np.min(clos) # x
right_bottom_r = np.max(rows)
right_bottom_c = np.max(clos)
return [left_top_c, left_top_r, right_bottom_c - left_top_c, right_bottom_r - left_top_r]
def polygons_to_mask(self, img_shape, polygons):
mask = np.zeros(img_shape, dtype=np.uint8)
mask = PIL.Image.fromarray(mask)
xy = list(map(tuple, polygons))
PIL.ImageDraw.Draw(mask).polygon(xy=xy, outline=1, fill=1)
mask = np.array(mask, dtype=bool)
return mask
def data2coco(self):
data_coco = {}
data_coco['images'] = self.images
data_coco['categories'] = self.categories
data_coco['annotations'] = self.annotations
return data_coco
def save_json(self):
print("in save_json")
self.data_transfer()
self.data_coco = self.data2coco()
print(self.save_json_path)
json.dump(self.data_coco, open(self.save_json_path, 'w'), indent=4)
labelme_json = glob.glob('LabelmeData/*.json')
from sklearn.model_selection import train_test_split
trainval_files, test_files = train_test_split(labelme_json, test_size=0.2, random_state=55)
import os
if not os.path.exists("datasets/coco/annotations"):
os.makedirs("datasets/coco/annotations/")
if not os.path.exists("/datasets/coco/train2017"):
os.makedirs("datasets/coco/train2017")
if not os.path.exists("datasets/coco/val2017"):
os.makedirs("datasets/coco/val2017")
labelme2coco(trainval_files, 'datasets/coco/annotations/instances_train2017.json')
labelme2coco(test_files, 'datasets/coco/annotations/instances_val2017.json')
import shutil
for file in trainval_files:
shutil.copy(os.path.splitext(file)[0] + ".jpg", "datasets/coco/train2017/")
for file in test_files:
shutil.copy(os.path.splitext(file)[0] + ".jpg", "datasets/coco/val2017/")
相关文章
- hibernate向mysql插入数据后,得到该条数据主键的方法
- 03-网页内容的编码检测 | 02.数据解析 | Python
- 我们怎样确保从大数据计算中获得价值
- R语言实现金融数据的时间序列分析及建模
- 大数据时代数据管理方式研究
- 【目标检测】数据增强:YOLO官方数据增强实现/imgaug的简单使用
- 向分析型数据库ADS中导入数据
- DL之RetinaNet:基于RetinaNet算法(keras框架)利用resnet50_coco数据集(.h5文件)实现目标检测
- Labelme转COCO数据集(物体检测)
- Windows下使用QT+OpenCV完成人脸检测(获取摄像头的数据进行检测)
- Vue学习之--------列表排序(ffilter、sort、indexOf方法的使用)、Vue检测数据变化的原理(2022/7/15)
- VL27-不重叠序列检测,检测信号是否满足011100序列,六个一组,连续不断,如果数据中断,则继续第七个开始,又是6个数据一组。
- 利用CTU-13数据集进行僵尸网络检测
- 智能威胁分析之图数据构建——关联数据为环境数据图:如资产、资产脆弱性、文件信息、用户信息、IT系统架构信息等 行为数据图:如网络侧检测告警、终端侧检测告警、文件分析日志、应用日志、蜜罐日志、沙箱日志等 情报数据图:各类外部威胁情报 知识数据图:各类知识库(如ATT&CK,CAPEC,CWE)等
- LSTM 时间序列数据的异常检测
- 万亿级日志与行为数据存储查询技术剖析(续)——Tindex是改造的lucene和druid
- 目标检测算法——垃圾分类数据集汇总(附下载链接)
- 目标检测00-03:mmdetection(Foveabox为例)-训练自定义的coco数据集(提供示例数据集)
- detectron2(目标检测框架)无死角玩转-02:训练,测试coco数据
- Java往MySQL数据库中写数据出现乱码
- [YOLOv7]基于YOLOv7的食物卡路里检测系统(源码&部署教程&数据集)
- 【数据集NO.5】小目标检测数据集汇总
- Docker 数据迁移
- Object s 365目标检测 数据集