关于coco数据集删减类个数的代码
我也是复制别⼈的代码，并⾮⾃⼰写的。因为平常跑代码，⼤多都会⽤到cooc数据集，但是，因为随着⽹络的复杂，以及显卡的有限，常常不能跑11W张数据集，实在太过费时。其次我们通过减少类数，但不减少类的照⽚个数，这样对⽹络没有太⼤的影响
起初如下所⽰：
第⼀个⾥⾯放了.json⽂件
第⼆第三个分别放了训练集和验证集图⽚
1.把coco数据集转成xml格式
读取出images 和 Annotations 两个⽂件夹
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=""            # 保存的路径
img_dir = savepath+'images/val2017/'  # 保存图⽚的路径
anno_dir = savepath+'Annotations/val2017/'  # 保存xml的路径
# datasets_list=['train2014', 'val2014']
# datasets_list=['train2014']
datasets_list = ['val2017']
# 你需要类的名称
classes_names = ['fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow']
#Store annotations and train2014/val2014/... in this folder
dataDir = 'datasets' # coco数据集所在的位置
headstr = """\
<annotation>
<folder>VOC</folder>
<filename>%s</filename>
<source>
<database>My Database</database>
<annotation>COCO</annotation>
<image>flickr</image>
<flickrid>NULL</flickrid>
</source>
<size>
<width>%d</width>
<height>%d</height>
<depth>%d</depth>
</size>
<segmented>0</segmented>
"""
objstr = """\
<object>
<name>%s</name>
<name>%s</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>%d</xmin>
<ymin>%d</ymin>
<xmax>%d</xmax>
<ymax>%d</ymax>
</bndbox>
</object>
"""
tailstr = '''\
</annotation>
'''
#if the dir is not exists,make it,else delete it
def mkr(path):
if ists(path):
<(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_l    anno_path=anno_dir+filename[:-3]+'xml'
img_path=dataDir+'/images/'+dataset+'/'+filename
# print(img_path)
dst_imgpath=img_dir+filename
# print(img_path,'aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa')
img=cv2.imread(img_path)
# print(img)
if (img.shape[2] == 1):
print(filename + " not a RGB image")
return
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/%s'%(dataDir,'images',dataset,img['file_name']))
#Get the annotated information by ID
annIds = AnnIds(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)
if show:
plt.figure()
plt.axis('off')
plt.imshow(I)
plt.show()
return objs
for dataset in datasets_list:
#./COCO/annotations/instances_train2014.json
# ,json⽂件所在的位置
annFile='{}/images/annotations/instances_{}.json'.format(dataDir,dataset)
#COCO API for initializing annotated data
coco = COCO(annFile)
'''
When the COCO object is created, the following information will be output:
loading annotations
Done (t=0.81s)
index created!
So far, the JSON script has been parsed and the images are associated with the corresponding annotated data.    '''
#show all classes in coco
classes = id2name(coco)
print(classes)
#[1, 2, 3, 4, 6, 8]
classes_ids = CatIds(catNms=classes_names)
print(classes_ids)
# exit()
getsavefilenamefor cls in classes_names:
#Get ID number of this class
cls_CatIds(catNms=[cls])
img_ImgIds(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.把xml格式转化为txt
读取出labels的⽂件夹 并⽣成与labels同级的txt
最终如下图所⽰：
第⼀个放的是xml
第⼆个是分类出来的图⽚ ⽂件内容如下：images/train2017 再是图⽚
第三个个是分类出来的图⽚的txt信息 ⽂件内容如下：labels/train2017 再是则是⼀个索引 记录了每个图⽚所在的位置
代码如下：
ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
classes = ['fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow'] # classes = ['truck']
def convert(size, box):
dw = 1. / (size[0])
dh = 1. / (size[1])
x = (box[0] + box[1]) / 2.0 - 1
y = (box[2] + box[3]) / 2.0 - 1
w = box[1] - box[0]
h = box[3] - box[2]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
return (x, y, w, h)
def convert_annotation(image_id):
in_file = open('/coco/Annotations/train2017/%s.xml' % (image_id))  # xml所在的位置
out_file = open('/coco/labels/trian2017/%s.txt' % (image_id), 'w')    # 转化成txt所在的位置
tree = ET.parse(in_file)
root = t()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
print(cls)
if cls not in classes or int(difficult) == 1:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),            float(xmlbox.find('ymax').text))
bb = convert((w, h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
data_path = '/coco/images/train2017'  # 刚刚分类出来的图⽚的位置
img_names = os.listdir(data_path)
list_file = open('./', 'w')      # 图中所⽰记录索引的txt⽂件
for img_name in img_names:
if not ists('/coco/labels/train2017'):
os.makedirs('/coco/labels/train2017')
list_file.write('./images/train2017/%s\n' % img_name)
image_id = img_name[:-4]
convert_annotation(image_id)
list_file.close()

版权声明：本站内容均来自互联网，仅供演示用，请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系QQ:729038198，我们将在24小时内删除。