pascal轉coco 按比例劃分數據

# -*- coding:utf-8 -*-
# !/usr/bin/env python
 
import argparse
import json
import matplotlib.pyplot as plt
import skimage.io as io
import sys
sys.path.remove('/opt/ros/kinetic/lib/python2.7/dist-packages')
import cv2
import numpy as np
import glob
import PIL.Image
import os,sys
import random


#import collections

import copy
 
class PascalVOC2coco(object):
    def __init__(self, xml=[], save_type=''):
        '''
        :param xml: 所有Pascal VOC的xml文件路徑組成的列表
        :param save_type: json保存類型
        '''
        self.xml = xml
        self.save_type = save_type
        self.images = [[] for i in range(3) ]
        self.categories = []
        self.annotations = [ [] for i in range(3) ]
        self.which_type = []        
        # self.data_coco = {}
        self.label = []
        self.annID = 1
        self.height = 0
        self.width = 0
        self.ob = []
        self.save_type_parse()
        self.save_json()

 
    def save_type_parse(self):
        type_list = self.save_type.split('_')        
        self.json_type = type_list
            


    def data_transfer(self):
        
        for num, json_file in enumerate(self.xml):
            rndnum = random.random()            
            if rndnum < 0.7:
                self.which_type.append(0)
            elif rndnum >=0.7 and rndnum <0.8:
                self.which_type.append(1)
            else:
                self.which_type.append(2)

            # 進度輸出
            sys.stdout.write('\r>> Converting image %d/%d' % (
                num + 1, len(self.xml)))
            sys.stdout.flush()
 
            self.json_file = json_file
            #print("self.json", self.json_file)
            self.num = num 
            #print(self.num)
            path = os.path.dirname(self.json_file)
            #print(path)
            path = os.path.dirname(path)
            #print(path)
            # path=os.path.split(self.json_file)[0]
            # path=os.path.split(path)[0]
            obj_path = glob.glob(os.path.join(path, 'SegmentationObject', '*.png'))
            #print(obj_path)


            with open(json_file, 'r') as fp:
                #print(fp)
                flag = 0
                for p in fp:
                    #print(p)
                    # if 'folder' in p:
                    #     folder =p.split('>')[1].split('<')[0]
                    f_name = 1
                    if 'filename' in p:
                        self.filen_ame = p.split('>')[1].split('<')[0]
                        #print(self.filen_ame)
                        f_name = 0
 
                        self.path = os.path.join(path, 'SegmentationObject', self.filen_ame.split('.')[0] + '.png')
                        #if self.path not in obj_path:
                        #    break
 
 
                    if 'width' in p:
                        self.width = int(p.split('>')[1].split('<')[0])
                        #print(self.width)
                    if 'height' in p:
                        self.height = int(p.split('>')[1].split('<')[0])
 
                        self.images[self.which_type[-1]].append(self.image())
                        #print(self.image())
 
                    if flag == 1:
                        self.supercategory = self.ob[0]
                        if self.supercategory not in self.label:
                            self.categories.append(self.categorie())
                            self.label.append(self.supercategory)
 
                        # 邊界框
                        x1 = int(self.ob[1]);
                        y1 = int(self.ob[2]);
                        x2 = int(self.ob[3]);
                        y2 = int(self.ob[4])
                        self.rectangle = [x1, y1, x2, y2]
                        self.bbox = [x1, y1, x2 - x1, y2 - y1]  # COCO 對應格式[x,y,w,h]
 
                        self.annotations[self.which_type[-1]].append(self.annotation())
                        self.annID += 1
                        self.ob = []
                        flag = 0
                    elif f_name == 1:
                        if 'name' in p:
                            self.ob.append(p.split('>')[1].split('<')[0])
 
                        if 'xmin' in p:
                            self.ob.append(p.split('>')[1].split('<')[0])
 
                        if 'ymin' in p:
                            self.ob.append(p.split('>')[1].split('<')[0])
 
                        if 'xmax' in p:
                            self.ob.append(p.split('>')[1].split('<')[0])
 
                        if 'ymax' in p:
                            self.ob.append(p.split('>')[1].split('<')[0])
                            flag = 1
 
                    '''
                    if '<object>' in p:
                        # 類別
                        print(next(fp))
                        d = [next(fp).split('>')[1].split('<')[0] for _ in range(7)]
                        self.supercategory = d[0]
                        if self.supercategory not in self.label:
                            self.categories.append(self.categorie())
                            self.label.append(self.supercategory)
                        # 邊界框
                        x1 = int(d[-4]);
                        y1 = int(d[-3]);
                        x2 = int(d[-2]);
                        y2 = int(d[-1])
                        self.rectangle = [x1, y1, x2, y2]
                        self.bbox = [x1, y1, x2 - x1, y2 - y1]  # COCO 對應格式[x,y,w,h]
                        self.annotations.append(self.annotation())
                        self.annID += 1
                     '''
 
        sys.stdout.write('\n')
        sys.stdout.flush()
 
    def image(self):
        image = {}
        image['height'] = self.height
        image['width'] = self.width
        image['id'] = self.num + 1
        image['file_name'] = self.filen_ame
        return image
 
    def categorie(self):
        categorie = {}
        categorie['supercategory'] = self.supercategory
        categorie['id'] = len(self.label) + 1  # 0 默認爲背景
        categorie['name'] = self.supercategory
        return categorie
 
    def annotation(self):
        annotation = {}
        # annotation['segmentation'] = [self.getsegmentation()]
        annotation['segmentation'] = [list(map(float, self.getsegmentation()))]
        annotation['iscrowd'] = 0
        annotation['image_id'] = self.num + 1
        # annotation['bbox'] = list(map(float, self.bbox))
        annotation['bbox'] = self.bbox
        annotation['category_id'] = self.getcatid(self.supercategory)
        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 getsegmentation(self):
 
        try:
            mask_1 = cv2.imread(self.path, 0)
            mask = np.zeros_like(mask_1, np.uint8)
            rectangle = self.rectangle
            mask[rectangle[1]:rectangle[3], rectangle[0]:rectangle[2]] = mask_1[rectangle[1]:rectangle[3],
                                                                         rectangle[0]:rectangle[2]]
 
            # 計算矩形中點像素值
            mean_x = (rectangle[0] + rectangle[2]) // 2
            mean_y = (rectangle[1] + rectangle[3]) // 2
 
            end = min((mask.shape[1], int(rectangle[2]) + 1))
            start = max((0, int(rectangle[0]) - 1))
 
            flag = True
            for i in range(mean_x, end):
                x_ = i;
                y_ = mean_y
                pixels = mask_1[y_, x_]
                if pixels != 0 and pixels != 220:  # 0 對應背景 220對應邊界線
                    mask = (mask == pixels).astype(np.uint8)
                    flag = False
                    break
            if flag:
                for i in range(mean_x, start, -1):
                    x_ = i;
                    y_ = mean_y
                    pixels = mask_1[y_, x_]
                    if pixels != 0 and pixels != 220:
                        mask = (mask == pixels).astype(np.uint8)
                        break
            self.mask = mask
 
            return self.mask2polygons()
 
        except:
            return [0]
 
    def mask2polygons(self):
        contours = cv2.findContours(self.mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)  # 找到輪廓線
        bbox=[]
        for cont in contours[1]:
            [bbox.append(i) for i in list(cont.flatten())]
            # map(bbox.append,list(cont.flatten()))
        return bbox # list(contours[1][0].flatten())
 
    # '''
    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)  # 畫邊界線
        # cv2.fillPoly(img, [np.asarray(points)], 1)  # 畫多邊形 內部像素值爲1
        polygons = points
        mask = self.polygons_to_mask([self.height, self.width], polygons)
        return self.mask2box(mask)
 
    def mask2box(self, mask):
        '''從mask反算出其邊框
        mask:[h,w]  0、1組成的圖片
        1對應對象,只需計算1對應的行列號(左上角行列號,右下角行列號,就可以算出其邊框)
        '''
        # np.where(mask==1)
        index = np.argwhere(mask == 1)
        rows = index[:, 0]
        clos = index[:, 1]
        # 解析左上角行列號
        left_top_r = np.min(rows)  # y
        left_top_c = np.min(clos)  # x
 
        # 解析右下角行列號
        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] 對應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, wtype=[]):
        x = wtype[0]        
        data_coco = {}
        data_coco['images'] = copy.deepcopy(self.images[x])
        data_coco['categories'] = copy.deepcopy(self.categories)
        data_coco['annotations'] = copy.deepcopy(self.annotations[x])
        if len(wtype) >1 :
            for idx in range(1,len(wtype)):
                data_coco['images'].extend( self.images[wtype[idx]])
                data_coco['annotations'].extend( self.annotations[wtype[idx]])
            
        return data_coco
 
    def save_json(self):
        self.data_transfer()
        self.data_coco_train = self.data2coco([0])
        self.data_coco_val = self.data2coco([1])
        self.data_coco_trainval = self.data2coco([0,1])
        self.data_coco_test = self.data2coco([2])

        print("train num : {}".format(len(self.data_coco_train['images'])))
        print("val num : {}".format(len(self.data_coco_val['images'])))
        print("trainval num : {}".format(len(self.data_coco_trainval['images'])))
        print("test num : {}".format(len(self.data_coco_test['images'])))
        
        # 保存json文件   
        json.dump(self.data_coco_train, open("train.json", 'w'), indent=4)  # indent=4 更加美觀顯示
        json.dump(self.data_coco_val, open("val.json", 'w'), indent=4)  # indent=4 更加美觀顯示
        json.dump(self.data_coco_trainval, open("trainval.json", 'w'), indent=4)  # indent=4 更加美觀顯示
        json.dump(self.data_coco_test, open("test.json", 'w'), indent=4)  # indent=4 更加美觀顯示
        

 
xml_file = glob.glob('./Annotations/*.xml')
# xml_file=['./Annotations/000032.xml']
#xml_file=['00000007_05499_d_0000037.xml']
PascalVOC2coco(xml = xml_file, save_type = 'train_val_trainval_test')
發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章