COCO数据集转VOC（提取自己需要的类）
github:https://github.com/zcc720/COCO2VOC.git
接上篇VOC数据集提取自己需要的类，这次我们依然从coco数据集中提取我们想要的类，并转为voc格式，用于目标检测。
一、去官网下载数据集
train2007
val2007
train2014
val2014
annotations2014
annotations2017
二、安装coco-PythonAPI
linux用户：
pip install cython
git clone https://github.com/cocodataset/cocoapi.git
cd coco/PythonAPI
makewindows用户：
pip install cython
git clone https://github.com/cocodataset/cocoapi.git
cd coco/PythonAPI
python setup.py build_ext --inplace三、get自己想要的类，制作成voc文件
COCO数据集目标检测中有90类：
classes:
{1: 'person', 2: 'bicycle', 3: 'car', 4: 'motorcycle', 5: 'airplane', 6: 'bus', 7: 'train', 8: 'truck', 9: 'boat', 10: 'traffic light', 11: 'fire hydrant', 13: 'stop sign', 14: 'parking meter', 15: 'bench', 16: 'bird', 17: 'cat', 18: 'dog', 19: 'horse', 20: 'sheep', 21: 'cow', 22: 'elephant', 23: 'bear', 24: 'zebra', 25: 'giraffe', 27: 'backpack', 28: 'umbrella', 31: 'handbag', 32: 'tie', 33: 'suitcase', 34: 'frisbee', 35: 'skis', 36: 'snowboard', 37: 'sports ball', 38: 'kite', 39: 'baseball bat', 40: 'baseball glove', 41: 'skateboard', 42: 'surfboard', 43: 'tennis racket', 44: 'bottle', 46: 'wine glass', 47: 'cup', 48: 'fork', 49: 'knife', 50: 'spoon', 51: 'bowl', 52: 'banana', 53: 'apple', 54: 'sandwich', 55: 'orange', 56: 'broccoli', 57: 'carrot', 58: 'hot dog',59: 'pizza', 60: 'donut', 61: 'cake', 62: 'chair', 63: 'couch', 64: 'potted plant', 65: 'bed', 67: 'dining table', 70: 'toilet', 72: 'tv', 73: 'laptop', 74: 'mouse', 75: 'remote', 76: 'keyboard',77: 'cell phone', 78: 'microwave', 79: 'oven', 80: 'toaster', 81: 'sink', 82: 'refrigerator', 84: 'book', 85: 'clock', 86: 'vase', 87: 'scissors', 88: 'teddy bear', 89: 'hair drier', 90: 'toothbrush'}
想要的类
classes_names = ['car', 'bicycle', 'person', 'motorcycle', 'bus', 'truck']from pycocotools.coco import COCO
import os
import shutil
from tqdm import tqdm
import skimage.io as io
import matplotlib.pyplot as plt
import cv2
from PIL import Image, ImageDraw
#the path you want to save your results for coco to voc
savepath="E:/datasets/COCO/result/"
img_dir=savepath+'images/'
anno_dir=savepath+'Annotations/'
# datasets_list=['train2014', 'val2014']
datasets_list=['train2017']
classes_names = ['car', 'bicycle', 'person', 'motorcycle', 'bus', 'truck']
#Store annotations and train2014/val2014/... in this folder
dataDir= 'E:/datasets/COCO/'
headstr = """\
VOC
%s
My Database
COCO
flickr
NULL
NULL
company
%d
%d
%d
0
"""
objstr = """\
"""
tailstr = '''\
'''
#if the dir is not exists,make it,else delete it
def mkr(path):
if os.path.exists(path):
shutil.rmtree(path)
os.mkdir(path)
else:
os.mkdir(path)
mkr(img_dir)
mkr(anno_dir)
def id2name(coco):
classes=dict()
for cls in coco.dataset['categories']:
classes[cls['id']]=cls['name']
return classes
def write_xml(anno_path,head, objs, tail):
f = open(anno_path, "w")
f.write(head)
for obj in objs:
f.write(objstr%(obj[0],obj[1],obj[2],obj[3],obj[4]))
f.write(tail)
def save_annotations_and_imgs(coco,dataset,filename,objs):
#eg:COCO_train2014_000000196610.jpg-->COCO_train2014_000000196610.xml
anno_path=anno_dir+filename[:-3]+'xml'
img_path=dataDir+dataset+'/'+filename
print(img_path)
dst_imgpath=img_dir+filename
img=cv2.imread(img_path)
if (img.shape[2] == 1):
print(filename + " not a RGB image")
return
shutil.copy(img_path, dst_imgpath)
head=headstr % (filename, img.shape[1], img.shape[0], img.shape[2])
tail = tailstr
write_xml(anno_path,head, objs, tail)
def showimg(coco,dataset,img,classes,cls_id,show=True):
global dataDir
I=Image.open('%s/%s/%s'%(dataDir,dataset,img['file_name']))
#通过id，得到注释的信息
annIds = coco.getAnnIds(imgIds=img['id'], catIds=cls_id, iscrowd=None)
# print(annIds)
anns = coco.loadAnns(annIds)
# print(anns)
# coco.showAnns(anns)
objs = []
for ann in anns:
class_name=classes[ann['category_id']]
if class_name in classes_names:
print(class_name)
if 'bbox' in ann:
bbox=ann['bbox']
xmin = int(bbox[0])
ymin = int(bbox[1])
xmax = int(bbox[2] + bbox[0])
ymax = int(bbox[3] + bbox[1])
obj = [class_name, xmin, ymin, xmax, ymax]
objs.append(obj)
draw = ImageDraw.Draw(I)
draw.rectangle([xmin, ymin, xmax, ymax])
if show:
plt.figure()
plt.axis('off')
plt.imshow(I)
plt.show()
return objs
for dataset in datasets_list:
#./COCO/annotations/instances_train2014.json
annFile='{}/annotations/instances_{}.json'.format(dataDir,dataset)
#COCO API for initializing annotated data
coco = COCO(annFile)
'''
COCO 对象创建完毕后会输出如下信息:
loading annotations into memory...
Done (t=0.81s)
creating index...
index created!
至此, json 脚本解析完毕, 并且将图片和对应的标注数据关联起来.
'''
#show all classes in coco
classes = id2name(coco)
print(classes)
#[1, 2, 3, 4, 6, 8]
classes_ids = coco.getCatIds(catNms=classes_names)
print(classes_ids)
for cls in classes_names:
#Get ID number of this class
cls_id=coco.getCatIds(catNms=[cls])
img_ids=coco.getImgIds(catIds=cls_id)
print(cls,len(img_ids))
# imgIds=img_ids[0:10]
for imgId in tqdm(img_ids):
img = coco.loadImgs(imgId)[0]
filename = img['file_name']
# print(filename)
objs=showimg(coco, dataset, img, classes,classes_ids,show=False)
print(objs)
save_annotations_and_imgs(coco, dataset, filename, objs)