批量修改json文件重命名后路径imagPath
问题：json文件转为coco数据集时，coco数据集出错，coco数据集中的文件信息与原图不符。
原因:查看生成的instances_val2014.json文件后发现，文件名的路径还是json重命名之前的路径，所以导致原图与json信息无法匹配。
如下图：json文件名与文件中imagepath不一样。
因此需要将imagepath 改成json现在的文件名。具体代码如下：
import json
import os, sys
json_path= '/home/f405/桌面/my_data/train/json/'
def get_json_data(json_path):
with open(json_path,'rb')as f:
params= json.load(f)
# 加载json文件中的内容给params
a= filename[:-5]
params['imagePath']= a+".jpg" #这两行控制修改的内容 时间有限就写的很草率
dict= params
# 将修改后的内容保存在dict中
f.close()
# 关闭json读模式
return dict
# 返回dict字典内容
def write_json_data(dict):
# 写入json文件
with open(json_path1,'w')as r:
# 定义为写模式，名称定义为r
json.dump(dict, r,indent = 2) #indent控制间隔
# 将dict写入名称为r的文件中
r.close()
# 关闭json写模式
#获取文件夹中的文件名称列表
filenames=os.listdir(json_path)
#遍历文件名
for filename in filenames:
filepath = json_path+'/'+filename
# print(filepath)
dict= {}
the_revised_dict= get_json_data(filepath)
json_path1= '/home/f405/桌面/3/'+filename # 修改json文件后保存的路径
write_json_data(the_revised_dict)附带json转coco数据集代码：
# -*- coding:utf-8 -*-
# !/usr/bin/env python
import json
from labelme import utils
import numpy as np
import glob
import PIL.Image
labels={'cell1':4,'cell2':2,'cell3':3,'cell4':5,'cell5':1}
class MyEncoder(json.JSONEncoder):
def default(self, obj):
if isinstance(obj, np.integer):
return int(obj)
elif isinstance(obj, np.floating):
return float(obj)
elif isinstance(obj, np.ndarray):
return obj.tolist()
else:
return super(MyEncoder, self).default(obj)
class labelme2coco(object):
def __init__(self, labelme_json=[], save_json_path='./tran.json'):
self.labelme_json = labelme_json
self.save_json_path = save_json_path
self.images = []
self.categories = []
self.annotations = []
self.label = []
self.annID = 1
self.height = 0
self.width = 0
self.save_json()
def data_transfer(self):
for num, json_file in enumerate(self.labelme_json):
imagePath=json_file.split('.')[0]+'.jpg'
imageName=imagePath.split('\\')[-1]
print(imageName)
with open(json_file, 'r') as fp:
data = json.load(fp)
self.images.append(self.image(data, num,imageName))
for shapes in data['shapes']:
label = shapes['label']
if label not in self.label:
self.categories.append(self.categorie(label))
self.label.append(label)
points = shapes['points']
self.annotations.append(self.annotation(points, label, num))
self.annID += 1
def image(self, data, num,imagePath):
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]
image['file_name'] = imagePath
self.height = height
self.width = width
return image
def categorie(self, label):
categorie = {}
categorie['supercategory'] = 'Cancer'
categorie['id'] = labels[label]
categorie['name'] = label
return categorie
def annotation(self, points, label, num):
annotation = {}
annotation['segmentation'] = [list(np.asarray(points).flatten())]
annotation['iscrowd'] = 0
annotation['image_id'] = num + 1
annotation['bbox'] = list(map(float, self.getbbox(points)))
annotation['area'] = annotation['bbox'][2] * annotation['bbox'][3]
annotation['category_id'] = self.getcatid(label)
print(label,annotation['category_id'])
annotation['id'] = self.annID
return annotation
def getcatid(self, label):
for categorie in self.categories:
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):
index = np.argwhere(mask == 1)
rows = index[:, 0]
clos = index[:, 1]
left_top_r = np.min(rows)
left_top_c = np.min(clos)
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):
self.data_transfer()
self.data_coco = self.data2coco()
json.dump(self.data_coco, open(self.save_json_path, 'w'), indent=4, cls=MyEncoder)
labelme_json = glob.glob(r'./*.json')
labelme2coco(labelme_json, '.\\instances_val2014.json')
若出错使用下面的
# -*- coding:utf-8 -*-
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
labels={'cell1':1,'cell2':2,'cell3':3,'cell4':4,'cell5':5}
class MyEncoder(json.JSONEncoder):
def default(self, obj):
if isinstance(obj, np.integer):
return int(obj)
elif isinstance(obj, np.floating):
return float(obj)
elif isinstance(obj, np.ndarray):
return obj.tolist()
else:
return super(MyEncoder, self).default(obj)
class labelme2coco(object):
def __init__(self, labelme_json=[], save_json_path='./tran.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.save_json()
def data_transfer(self):
for num, json_file in enumerate(self.labelme_json):
with open(json_file, 'r') as fp:
data = json.load(fp) # 加载json文件
self.images.append(self.image(data, num))
for shapes in data['shapes']:
label = shapes['label']
if label not in self.label:
self.categories.append(self.categorie(label))
self.label.append(label)
points = shapes['points'] # 这里的point是用rectangle标注得到的，只有两个点，需要转成四个点
points.append([points[0][0], points[1][1]])
points.append([points[1][0], points[0][1]])
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']) # 解析原图片数据
# img=io.imread(data['imagePath']) # 通过图片路径打开图片
# img = cv2.imread(data['imagePath'], 0)
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'] = 'Cancer'
categorie['id'] =labels[label] # 0 默认为背景
categorie['name'] = label
return categorie
def annotation(self, points, label, num):
annotation = {}
annotation['segmentation'] = [list(np.asarray(points).flatten())]
annotation['iscrowd'] = 0
annotation['image_id'] = num + 1
# annotation['bbox'] = str(self.getbbox(points)) # 使用list保存json文件时报错（不知道为什么）
# list(map(int,a[1:-1].split(','))) a=annotation['bbox'] 使用该方式转成list
annotation['bbox'] = list(map(float, self.getbbox(points)))
annotation['area'] = annotation['bbox'][2] * annotation['bbox'][3]
# annotation['category_id'] = self.getcatid(label)
annotation['category_id'] = self.getcatid(label) # 注意，源代码默认为1
annotation['id'] = self.annID
return annotation
def getcatid(self, label):
for categorie in self.categories:
if label == categorie['name']:
return categorie['id']
return 1
def getbbox(self, points):
# img = np.zeros([self.height,self.width],np.uint8)
# cv2.polylines(img, [np.asarray(points)], True, 1, lineType=cv2.LINE_AA) # 画边界线
# cv2.fillPoly(img, [np.asarray(points)], 1) # 画多边形 内部像素值为1
polygons = points
mask = self.polygons_to_mask([self.height, self.width], polygons)
return self.mask2box(mask)
def mask2box(self, mask):
'''从mask反算出其边框
mask：[h,w] 0、1组成的图片
1对应对象，只需计算1对应的行列号（左上角行列号，右下角行列号，就可以算出其边框）
'''
# np.where(mask==1)
index = np.argwhere(mask == 1)
rows = index[:, 0]
clos = index[:, 1]
# 解析左上角行列号
left_top_r = np.min(rows) # y
left_top_c = np.min(clos) # x
# 解析右下角行列号
right_bottom_r = np.max(rows)
right_bottom_c = np.max(clos)
# return [(left_top_r,left_top_c),(right_bottom_r,right_bottom_c)]
# return [(left_top_c, left_top_r), (right_bottom_c, right_bottom_r)]
# return [left_top_c, left_top_r, right_bottom_c, right_bottom_r] # [x1,y1,x2,y2]
return [left_top_c, left_top_r, right_bottom_c - left_top_c,
right_bottom_r - left_top_r] # [x1,y1,w,h] 对应COCO的bbox格式
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):
self.data_transfer()
self.data_coco = self.data2coco()
# 保存json文件
json.dump(self.data_coco, open(self.save_json_path, 'w'), indent=4, cls=MyEncoder) # indent=4 更加美观显示
labelme_json = glob.glob(r'./*.json')
# labelme_json=['./1.json']
labelme2coco(labelme_json, '.\\instances_val2014.json')