python实现提取COCO,VOC数据集中特定的类.pdf-资料库

实现提取COCO,VOC数据集中特定的类数据集中特定的类 python实现提取主要介绍了python实现提取COCO,VOC数据集中特定的类，具有很好的参考价值，希望对大家有所帮助。一起跟随小编过来看看吧 1.python提取提取COCO数据集中特定的类数据集中特定的类安装pycocotools github地址：https://github.com/philferriere/cocoapi pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI 提取特定的类别如下： 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="/media/huanglong/Newsmy/COCO/" #保存提取类的路径,我放在同一路径下 img_dir=savepath+'images/' anno_dir=savepath+'Annotations/' # datasets_list=['train2014', 'val2014'] datasets_list=['train2014'] classes_names = ['person'] #coco有80类，这里写要提取类的名字，以person为例 #Store annotations and train2014/val2014/... in this folder dataDir= '/media/huanglong/Newsmy/COCO/' #原coco数据集 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) #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) 2. 将上一步提取的将上一步提取的COCO 某一类某一类 xml转为转为COCO标准的标准的json文件：文件： # -*- coding: utf-8 -*- # @Time : 2019/8/27 10：48 # @Author :Rock # @File : voc2coco.py # just for object detection 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 = 0 image_id = 0 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.') img_id = "%04d" % image_id image_id += 1 image_item = dict() image_item['id'] = int(img_id) # 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 parseXmlFiles(xml_path): for f in os.listdir(xml_path): if not f.endswith('.xml'): continue 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 , , ,

资料库

python实现提取COCO,VOC数据集中特定的类.pdf

相关推荐

开发技术

热门标签

最新资料