self._imgpath = os.path.join(self.root, {data_path}, {data_format})

import os import shutil sets = os.listdir("ImageSets/Main/") an = os.listdir("Annotations/") print(an)for set in sets: print(set) file = open("ImageSets/Main/"+set,"r") for line in file: name = line.strip()+".xml" print(name) shutil.copyfile("Annotations/"+name, "split/"+set[:-4]+"/"+name)

import os import cv2 import numpy as np X,Y=0,0 img_lists = os.listdir("JPEGImages") for img in img_lists: print(img) read = cv2.imread("JPEGImages/"+img) read = np.array(read) x,y,z = read.shape if x>X: X = x if y>X: Y = y print("max x,y: ",X,Y)

Every 1.0s: gpustat -cpukyle-X8Ti: Tue Jun9 11:58:17 2020kyle-X8TiTue Jun9 11:58:17 2020435.21 [0] GeForce GTX 1060 | 70'C, 100 % |4789 /6078 MB | kyle:python/16401 (4591M) kyle:Xorg/2244(105M) kyle:gnome-shell/2400(87M) kyle:firefox/2165 4(1M)

• VOC数据集要包含必要的ImageSet、images/JPEGImage以及Annotations文件夹以及相关文件。
• COCO数据集要包含对应的.json文件。图像的存储位置必须和.json文件当中要保持一致。
  这里补充一个通过VOC imageSet 的数据集分割的train、test、val的test文件来生成coco数据集的代码：

import os import json import xml.etree.ElementTree as ET import numpy as np import cv2 def _isArrayLike(obj): return hasattr(obj, '__iter__') and hasattr(obj, '__len__') class voc2coco: def __init__(self, devkit_path=None, year=None): self.classes = ('__background__', 'nova') self.num_classes = len(self.classes) #assert 'data716' in devkit_path, 'VOC地址不存在: {}'.format(devkit_path) self.data_path = os.path.join(devkit_path, 'VOC' + year) self.annotaions_path = os.path.join(self.data_path, 'Annotations') self.image_set_path = os.path.join(self.data_path, 'ImageSets') self.year = 2019 self.categories_to_ids_map = self._get_categories_to_ids_map() self.categories_msg = self._categories_msg_generator() def _load_annotation(self, ids=[]): ids = ids if _isArrayLike(ids) else [ids] image_msg = [] annotation_msg = [] annotation_id = 1 for index in ids: filename = '{:0>4}'.format(index) json_file = os.path.join(self.data_path, 'Segmentation_json', filename + '.json') if os.path.exists(json_file): img_file = os.path.join(self.data_path, 'JPEGImages', filename + '.jpg') im = cv2.imread(img_file) width = im.shape[1] height = im.shape[0] seg_data = https://www.it610.com/article/json.load(open(json_file,'r')) assert type(seg_data) == type(dict()), 'annotation file format {} not supported'.format(type(seg_data)) for shape in seg_data['shapes']: seg_msg = [] for point in shape['points']: seg_msg += point one_ann_msg = {"segmentation": [seg_msg], "area": self._area_computer(shape['points']), "iscrowd": 0, "image_id": int(index), "bbox": self._points_to_mbr(shape['points']), "category_id": self.categories_to_ids_map[shape['label']], "id": annotation_id, "ignore": 0 } annotation_msg.append(one_ann_msg) annotation_id += 1 else: xml_file = os.path.join(self.annotaions_path, filename + '.xml') tree = ET.parse(xml_file) size = tree.find('size') objs = tree.findall('object') width = size.find('width').text height = size.find('height').text for obj in objs: bndbox = obj.find('bndbox') [xmin, xmax, ymin, ymax] \ = [int(bndbox.find('xmin').text) - 1, int(bndbox.find('xmax').text), int(bndbox.find('ymin').text) - 1, int(bndbox.find('ymax').text)] if xmin < 0: xmin = 0 if ymin < 0: ymin = 0 bbox = [xmin, xmax, ymin, ymax] one_ann_msg = {"segmentation": self._bbox_to_mask(bbox), "area": self._bbox_area_computer(bbox), "iscrowd": 0, "image_id": int(index), "bbox": [xmin, ymin, xmax - xmin, ymax - ymin], "category_id": self.categories_to_ids_map[obj.find('name').text], "id": annotation_id, "ignore": 0 } annotation_msg.append(one_ann_msg) annotation_id += 1 one_image_msg = {"file_name": filename + ".jpg", "height": int(height), "width": int(width), "id": int(index) } image_msg.append(one_image_msg) return image_msg, annotation_msg def _bbox_to_mask(self, bbox): assert len(bbox) == 4, 'Wrong bndbox!' mask = [bbox[0], bbox[2], bbox[0], bbox[3], bbox[1], bbox[3], bbox[1], bbox[2]] return [mask] def _bbox_area_computer(self, bbox): width = bbox[1] - bbox[0] height = bbox[3] - bbox[2] return width * height def _save_json_file(self, filename=None, data=https://www.it610.com/article/None): json_path = os.path.join(self.data_path,'cocoformatJson') assert filename is not None, 'lack filename' if os.path.exists(json_path) == False: os.mkdir(json_path) if not filename.endswith('.json'): filename += '.json' assert type(data) == type(dict()), 'data format {} not supported'.format(type(data)) with open(os.path.join(json_path, filename), 'w') as f: f.write(json.dumps(data)) def _get_categories_to_ids_map(self): return dict(zip(self.classes, range(self.num_classes))) def _get_all_indexs(self): ids = [] for root, dirs, files in os.walk(self.annotaions_path, topdown=False): for f in files: if str(f).endswith('.xml'): id = int(str(f).strip('.xml')) ids.append(id) assert ids is not None, 'There is none xml file in {}'.format(self.annotaions_path) return ids def _get_indexs_by_image_set(self, image_set=None): if image_set is None: return self._get_all_indexs() else: image_set_path = os.path.join(self.image_set_path, 'Main', image_set + '.txt') assert os.path.exists(image_set_path), 'Path does not exist: {}'.format(image_set_path) with open(image_set_path) as f: ids = [x.strip() for x in f.readlines()] return ids def _points_to_mbr(self, points): assert _isArrayLike(points), 'Points should be array like!' x = [point[0] for point in points] y = [point[1] for point in points] assert len(x) == len(y), 'Wrong point quantity' xmin, xmax, ymin, ymax = min(x), max(x), min(y), max(y) height = ymax - ymin width = xmax - xmin return [xmin, ymin, width, height] def _categories_msg_generator(self): categories_msg = [] for category in self.classes: if category == '__background__': continue one_categories_msg = {"supercategory": "none", "id": self.categories_to_ids_map[category], "name": category } categories_msg.append(one_categories_msg) return categories_msg def _area_computer(self, points): assert _isArrayLike(points), 'Points should be array like!' tmp_contour = [] for point in points: tmp_contour.append([point]) contour = np.array(tmp_contour, dtype=np.int32) area = cv2.contourArea(contour) return area def voc_to_coco_converter(self): img_sets = ['train', 'test', 'val'] for img_set in img_sets: ids = self._get_indexs_by_image_set(img_set) img_msg, ann_msg = self._load_annotation(ids) result_json = {"images": img_msg, "type": "instances", "annotations": ann_msg, "categories": self.categories_msg} self._save_json_file('voc_' + str(self.year) + '_' + img_set, result_json) def demo(): # 转换pascal地址是'./VOC2007/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt' converter = voc2coco('/home/kyle/Programs/FCOS/FCOS/datasets/voc_cocostyle/', '2007/') converter.voc_to_coco_converter() if __name__ == "__main__": demo()

#所有COCO和VOC数据集的名称开头都必须是coco_或者是voc_。 #COCO数据集格式 "coco_{dataset-name}_train": { "img_dir": "{Path_to_your_images}", "ann_file": "{Path_to_your_json_file}.json" },"coco_{dataset-name}_val": { "img_dir": "{Path_to_your_images}", "ann_file": "{Path_to_your_json_file}.json" },"coco_{dataset-name}_test": { "img_dir": "{Path_to_your_images}", "ann_file": "{Path_to_your_json_file}.json" }, ##################################################### #VOC数据集格式 "voc_{dataset-name}_train": { "data_dir": "{your_voc_path}/VOC2012", "split": "train" }, "voc_{dataset-name}_val": { "data_dir": "{your_voc_path}/VOC2012", "split": "val" }, "voc_{dataset-name}_test": { "data_dir": "{your_voc_path}/VOC2012", "split": "test" },

可以定义自己的非主流数据集名字。但是一定要注意会解析数据集前缀来判断数据集的类型，所以第一前缀不能丢失，其次不能混淆。

pip3 uninstall fcos -y python3 setup.py build_ext --inplace python3 setup.py build_ext install

只有这样，才能够在yaml文件当中反问到刚才添加的数据集：

... DATASETS: TRAIN: ("coco_{dataset-name}_train", "coco_{dataset-name}_val") TEST: ("coco_{dataset-name}_test",) ...

推荐阅读

• 

  如何科学坐月子 春季坐月子这6件事千万别做
• 

  广汽本田广汽本田皓影三大件是进口的吗
• 

  小森生活抗寒衣服怎么做 小森生活抗寒套装制作攻略
• 

  冬枣泡了糖精水的怎么看
• 

  怎么用炉甘石治荨麻疹
• 

  警察是否有权上门抓狗
• 

  伊利鲜奶好还是蒙牛纯牛奶好 带你了解伊利纯牛奶和蒙牛纯牛奶有什么区别
• 

  正常胸和下垂胸对比 如何揉胸才能变大
• 

  ps快速替换靠山颜色
• 

  夏天发面要几个小时才会发的好 夏天发面是用冷水还是用温水
• 

  圆点|每日好价：大牌小圆点机械键盘开售 颜值超高
• 

  臀部|臀部引发各种疼痛，令人很苦恼，这些锻炼方法，您会吗？尝试看一看
• 

  接触区域按接触还是挤压强度分析
• 

  NLP教程（Python NLTK用法示例和完整指南）
• 

  三国志战略版震慑状态是什么 九大震慑类战法使用攻略
• 

  如何为企业选择合适的云服务器？ 企业要用云服务器怎么搞
• 

  lol2018战斗之夜奖励重随在哪领取 战斗之夜奖励重随领取地址
• 

  果树环剥的方法及作用 果树环剥注意事项
• 

  考研什么时候出成绩 考研是什么
• 

  瓜蒌皮的功效与作用及禁忌

• AI|论文研读（三）（FCOS: Fully Convolutional One-Stage Object Detection之补充）
• 用 Python 做“贪吃蛇”，在线吃不饱
• 程序员|手把手教你使用 Python 制作贪吃蛇游戏
• c++|Python 什么时候会被取代（）
• 编程语言|Canvas渲染会取代DOM吗（）
• 十套技巧提升你的Python编程水平
• 老猿Python|Python+Pycharm和 VisualStudio C++社区版使用PK及易混淆的语法问题
• transformers|【深度学习】（ICCV-2021）PVT-金字塔 Vision Transformer及PVT_V2
• 无人车|CCF智能无人车比赛（国内绿洲科学实验云平台）心路历程＋AWS Deepracer智能无人车比赛经验（附优秀代码re:lnvent 2018赛道）