# -*- coding:utf-8 -*- """只需要按照实际改写images/annotations/categories另外两个字段其实可以忽略 在keypoints/categories内容是固定的不需修改 """ import os import json import re import cv2 import argparse from tqdm import tqdm import numpy as np def get_landmark(txt_path, save_path): txt_write = open(save_path, 'w') annotationfile = open(txt_path) min_bbox = 10 blur_value = 0.3 Init = False img_path = None bbox_landmarks = [] while (True): line = annotationfile.readline()[:-1] if not line: break if re.search('jpg', line): if Init: if len(bbox_landmarks) < 1: continue txt_write.write(img_path + '\n') txt_write.write(str(len(bbox_landmarks)) + '\n') for lm in bbox_landmarks: txt_write.write(str(lm)+'\n') Init = True img_path = line.split('# ')[1] # line[2:] bbox_landmarks = [] continue else: values = line.strip().split() bbox = values[:4] if min(int(bbox[2]), int(bbox[3])) < min_bbox: continue if len(values) > 4: if float(values[19]) < blur_value: continue for li in range(5): value = float(values[(li+2)*3]) if value == 0: # visible values[(li + 2) * 3] = str(2) elif value == 1: # visible values[(li + 2) * 3] = str(1) else: values[3*li+4] = str(0) values[3*li+5] = str(0) values[3*li+6] = str(0) values = ' '.join(values) bbox_landmarks.append(values) txt_write.close() annotationfile.close() class COCO(object): def info(self): return {"version": "1.0", "year": 2020, "contributor": "Mr.yang", "date_created": "2018/08/21", "github": "https://github.com/bleakie"} def licenses(self): return [ { "url": "http://creativecommons.org/licenses/by-nc-sa/2.0/", "name": "Attribution-NonCommercial-ShareAlike License", "id": 1 } ] def image(self): return { "license": 4, "file_name": "000000397133.jpg", # 图片名 "coco_url": "http://images.cocodataset.org/val2017/000000397133.jpg", # 网路地址路径 "height": 427, # 高 "width": 640, # 宽 "date_captured": "2013-11-14 17:02:52", # 数据获取日期 "flickr_url": "http://farm7.staticflickr.com/6116/6255196340_da26cf2c9e_z.jpg", # flickr网路地址 "id": 397133 # 图片的ID编号（每张图片ID是唯一的） } def annotation(self): return { "segmentation": [ # 对象的边界点（边界多边形） [ 0., 0., # 第一个点 x,y坐标 0., 0., # 第二个点 x,y坐标 0., 0., 0., 0. ] ], "num_keypoints": 5, # keypoints是按照以下关键点来标记的，如果nose 没有标则为0,0,0(3个数字为一组，分别为x,y,v v=0表示为标记此时的x=y=0, # v=1表示标记了但是在图上是不可见，v=2表示标记了，在图上可见) "keypoints": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], "area": 0., # 区域面积 "iscrowd": 0, "image_id": 397133, # 对应的图片ID（与images中的ID对应） "bbox": [0., 0., 0., 0.], # 定位边框 [x,y,w,h] "category_id": 1, # 类别ID（与categories中的ID对应） "id": 82445 # 对象ID，因为每一个图像有不止一个对象，所以要对每一个对象编号（每个对象的ID是唯一的） } def categorie(self): return { "supercategory": "face", # 主类别 "id": 1, # 类对应的id （0 默认为背景） "name": "face", # 子类别 "keypoints": ["left_eye", "right_eye", "nose", "left_mouth", "right_mouth"], # "skeleton": [[1, 3], [2, 3], [3, 4], [3, 5]] } class Keypoints2COCO(COCO): def __init__(self, label_path, save_json_path, images_path): self.label = open(label_path, ) self.save_json_path = save_json_path # 最终保存的json文件 self.images_path = images_path # 原始图片保存的位置 self.images = [] self.annotations = [] # self.label = [] self.annID = 1 self.height = 0 self.width = 0 self.num = 1 self.keypoints = ["left_eye", "right_eye", "nose", "left_mouth", "right_mouth"] self.num_keypoints = 5 def __call__(self): while (True): img_path = self.label.readline()[:-1] if not img_path: break if img_path.endswith('.jpg'): img_full_path = os.path.join(self.images_path, img_path) if not os.path.exists(img_full_path): # print("img not exist", img_full_path) continue # print("img_full_path", img_full_path) # init image image = self.image() image["file_name"] = img_path image["id"] = self.num img = cv2.imread(img_full_path) if img is None: continue image["height"] = img.shape[0] image["width"] = img.shape[1] line = self.label.readline()[:-1] if not line: break facenum = (int)(line) # print("facenum", facenum) # init annotation annotation = self.annotation() for _ in range(facenum): line = [float(x) for x in self.label.readline().strip().split()] # print("***", line) bbox = list(line[:4]) if len(line) > 4: line[6], line[9], line[12], line[15], line[18] = int(line[6]), int( line[9]), int(line[12]), int(line[15]), int(line[18]) index = [line[6], line[9], line[12], line[15], line[18]] self.num_keypoints = len(np.minimum(index, 1)) annotation['keypoints'] = line[4:-1] # 默认为可见 v=2 annotation['num_keypoints'] = self.num_keypoints annotation["image_id"] = self.num annotation["id"] = self.annID annotation["bbox"] = bbox annotation['area'] = bbox[2]*bbox[3] annotation['segmentation'] = [ bbox[0], bbox[1], bbox[0]+bbox[2], bbox[1]+bbox[3]] self.annotations.append(annotation) self.annID += 1 # 对应对象 annotation = self.annotation() # 计算下一个对象 self.num += 1 # 对应图像 self.images.append(image) jsdata = {"info": self.info(), "licenses": self.licenses(), "images": self.images, "annotations": self.annotations, "categories": [self.categorie()]} json.dump(jsdata, open(self.save_json_path, 'w'), indent=4, default=float) # python3 需加上default=float 否则会报错 parser = argparse.ArgumentParser() # basic experiment setting parser.add_argument('--mode', default='train', help='Please input train or val') parser.add_argument('--txtPath', default='./annotations/train/train_keypoints_widerface.txt') opt = parser.parse_args() if __name__ == "__main__": ROOT_PATH = './' label_type = opt.mode img_path = os.path.join(ROOT_PATH, 'images', f'{label_type}') txt_path = opt.txtPath save_landmark_path = txt_path[:txt_path.rfind('/')] save_landmark_path = os.path.join( save_landmark_path, f'landmark_{label_type}.txt') get_landmark(txt_path, save_landmark_path) # 处理关键点标注数据 save_label_path = os.path.join(ROOT_PATH, 'labels') if not os.path.exists(save_label_path): os.makedirs(save_label_path) save_label_path = os.path.join( save_label_path, f'./{label_type}_face.json') Keypoints2COCO(save_landmark_path, save_label_path, img_path)() print("dealing labels end.")