python读取与写入json+csv变成coco的json文件+安装labelme

一.python读取与输出json

1.python字典和json互转这里用json.dumps,还原则用json.loads，dumps以后就变为字符串了

import json

# info = {'name': 'Damin', 'address': '北京', 'salary':88888}
info = {"name": "Damin", "address": "北京", "salary": 88888}
print(info["name"])

info_json = json.dumps(info)
print('====info_json===', info_json)#\u,表示这两个编码是Unicode编码
print('===type(info_json):', type(info_json))#注意这个时候已经变为字符串了

info_json_json = json.dumps(info_json)
print('===info_json_json:===', info_json_json)
print('===type(info_json_json):', type(info_json_json))#注意这个时候已经变为字符串了


print(json.loads(info_json_json))
print('===type(json.loads(info_json_json)):', type(json.loads(info_json_json)))
print(json.loads(json.loads(info_json_json)))
print('==type(json.loads(json.loads(info_json_json))):', type(json.loads(json.loads(info_json_json))))

2.处理文件

2.1读取json用json.load

path = './image/003.json'
with open(path) as file:
    json_info = json.load(file)
    #print(len(json_info['shapes']))

2.2写入json 

            with open(path+'/'+name+'.json', 'w+') as fp:
                json.dump(data, fp=fp, ensure_ascii=False, indent=4, separators=(',', ': '))

            with open(output_file, "w+") as jsonfile:
                json.dump(json_data, jsonfile, sort_keys=True, indent=4)

二.coco数据集介绍

{
    "info": info, # dict
    "licenses": [license], # list ，内部是dict
    "images": [image], # list ，内部是dict
    "annotations": [annotation], # list ，内部是dict
    "categories": # list ，内部是dict
}
 

三.csv转coco的json文件

1，train的csv生成coco，json文件

csv文件如下：

图片如下：

import cv2
import math
import numpy as np
import xml.etree.ElementTree as ET
import pandas as pd
from PIL import Image, ImageEnhance
import glob
import json

CLASS_NAMES = ['steel']
class COCOStyleDataset(object):
    # @staticmethod
    # def json_info(json_path=None):
    #     # json_path = '/workspace/mmdetection-0p6rc/gangjin/train_annotations.json'
    #     from pycocotools import coco
    #     cd = coco.COCO(json_path)
    #     print('anno num: ', len(cd.anns))
    #     print('img num: ', len(cd.imgs))
    #     return len(cd.imgs), len(cd.anns)
    @staticmethod
    def json_annotations_for_train():
        class_name2id = {}
        for idx, cls_nm in enumerate(CLASS_NAMES):
            class_name2id[cls_nm] = idx + 1
        print(class_name2id)
        final_json = dict()
        final_json['info'] = None
        final_json['licenses'] = None
        final_json['categories'] = []
        final_json['images'] = []
        final_json['annotations'] = []

        # categories
        for i in range(1):
            cat = dict()
            cat['id'] = i + 1
            cat['name'] = CLASS_NAMES[i]
            cat['supercategory'] = CLASS_NAMES[i]
            final_json['categories'].append(cat)
        print(final_json)
        sv_nm = 'train_annotations_example.json'
        data_root = './'
        path_prefix = 'JPEGImages_example/'
        img_path = data_root + path_prefix
        print('img_path=', img_path)
        img_names = glob.glob1(img_path, '*jpg')
        print('img_names=', img_names)

        def pre_data(df):
            df.iloc[:, 1] = df.apply(lambda x: [float(a) for a in x[1].split(' ')], axis=1)

        def collect(df):
            rlt = dict()
            for i in range(df.shape[0]):
                img_nm = df.iloc[i, 0]
                if img_nm in rlt.keys():
                    rlt[img_nm].append(df.iloc[i, 1])
                else:
                    rlt[img_nm] = [df.iloc[i, 1]]
            for key, val in rlt.items():
                rlt[key] = np.array(val)
            return rlt

        df = pd.read_csv(data_root + '/train_labels.csv')
        print(df)

        """add part csv_name"""
        for i in img_names:
            df_part=df[df['ID']==i]
        pre_data(df_part)
        print(df_part)
        lb_dict = collect(df_part)
        print(lb_dict)
        """df_part replace df"""

        assert len(lb_dict) == len(img_names)
        img_names = list(lb_dict.keys())
        print(img_names)

        # gene json
        image_id_counter = 250
        annotation_id_counter = 30942
        for img_name in img_names:
            print(image_id_counter, annotation_id_counter, img_name)
            # image
            image = dict()
            img_data = Image.open(img_path + img_name)
            image['id'] = image_id_counter
            image['width'] = img_data.width
            image['height'] = img_data.height
            image['file_name'] = img_name
            final_json['images'].append(image)

            print(lb_dict[img_name])
            # annotation
            for i in range(lb_dict[img_name].shape[0]):
                x, y, x2, y2 = lb_dict[img_name][i]
                width, height = x2 - x, y2 - y

                annotation = dict()
                annotation['id'] = annotation_id_counter
                annotation['image_id'] = image_id_counter
                annotation['category_id'] = 1
                annotation['bbox'] = [x, y, width, height]
                annotation['area'] = float(width * height)
                annotation['iscrowd'] = 0
                final_json['annotations'].append(annotation)
                # update annotation id
                annotation_id_counter += 1
            # update image id
            image_id_counter += 1
        # write json
        with open(data_root + sv_nm, 'w') as fp:
            json.dump(final_json, fp=fp, ensure_ascii=False, indent=4, separators=(',', ': '))

    @staticmethod
    def json_annotations_for_test():
        final_json = dict()
        final_json['info'] = None
        final_json['licenses'] = None
        final_json['categories'] = []
        final_json['images'] = []
        final_json['annotations'] = []


        img_path = './JPEGImages_example/'
        img_names = sorted([nm for nm in os.listdir(img_path) if 'jpg' in nm])
        print('img num: ', len(img_names))
        image_id_counter = 0
        for img_name in img_names:
            print(image_id_counter, img_name)
            img_data = Image.open(img_path + img_name)
            # image
            image = dict()
            image['id'] = image_id_counter
            image['width'] = img_data.width
            image['height'] = img_data.height
            image['file_name'] = img_name
            final_json['images'].append(image)
            image_id_counter += 1

        with open('./test_annotations_example.json', 'w') as fp:
            json.dump(final_json, fp=fp, ensure_ascii=False, indent=4, separators=(',', ': '))
if __name__ == '__main__':
    # COCOStyleDataset.json_annotations_for_train()
    COCOStyleDataset.json_annotations_for_test()

生成的json文件截图如下：

2，test的图片生成coco，json文件

test的json文件如下图

四，安装labelme

sudo apt-get install python-qt4 pyqt4-dev-tools
sudo pip install labelme  # python2 works

labelme --nodata --autosave

会自动生成对应的json文件