Detectron2 自定义数据集 完成训练与测试

安装Detectron2 请移步  win10下 detectron2的安装和测试_d597797974的博客-CSDN博客

1、安装标注软件  labelme

pip install labelme=3.3.1

conda install pyqt

2、自定义数据集

数据结构

----my_data

--------annotations   存放标注文件

--------train   存放训练集图片

--------val     存放测试集图片

Detectron2 自定义数据集 完成训练与测试_第1张图片

Detectron2 自定义数据集 完成训练与测试_第2张图片

Detectron2 自定义数据集 完成训练与测试_第3张图片

Detectron2 自定义数据集 完成训练与测试_第4张图片

使用labelme标注数据

通过labelme2coco.py 将标注好的多个json文件转换为一个json文件.  训练集和测试集的标注文件都转换一下

将转换后的train.json文件和test.json文件放入annotations文件夹下

#labeelme2coco.py 代码


# -*- coding:utf-8 -*-

import json
from labelme import utils
import numpy as np
import glob
import PIL.Image


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='./train.json'):
        '''
        :param labelme_json: 所有labelme的json文件路径组成的列表
        :param save_json_path: json保存位置
        '''
        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'] = len(self.label) + 1  # 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'F:\my_data\annotations\*.json')  #换成自己json文件所在路径
labelme2coco(labelme_json,"test.json")
print("完成")

3、数据集的注册

创建 fruitsnuts_data.py  注册数据集

from detectron2.data.datasets import register_coco_instances
from detectron2.data import MetadataCatalog
import os

#声明类别,尽量保持
CLASS_NAMES =["cat","dog"]
# 数据集路径
DATASET_ROOT = r'E:\models\detectron2-master\my_data\data'
#标注文件夹路径
ANN_ROOT = os.path.join(DATASET_ROOT, 'annotations')
#训练图片路径
TRAIN_PATH = os.path.join(DATASET_ROOT, 'train')
#测试图片路径
VAL_PATH = os.path.join(DATASET_ROOT, 'val')
#训练集的标注文件
TRAIN_JSON = os.path.join(ANN_ROOT, 'train.json')
#验证集的标注文件
# VAL_JSON = os.path.join(ANN_ROOT, 'val.json')
#测试集的标注文件
VAL_JSON = os.path.join(ANN_ROOT, 'test.json')

register_coco_instances("my_train", {}, TRAIN_JSON, TRAIN_PATH)
MetadataCatalog.get("my_train").set(thing_classes=CLASS_NAMES,  # 可以选择开启,但是不能显示中文,这里需要注意,中文的话最好关闭
                                                    evaluator_type='coco', # 指定评估方式
                                                    json_file=TRAIN_JSON,
                                                    image_root=TRAIN_PATH)
register_coco_instances("my_val", {}, VAL_JSON, VAL_PATH)
MetadataCatalog.get("my_val").set(thing_classes=CLASS_NAMES,  # 可以选择开启,但是不能显示中文,这里需要注意,中文的话最好关闭
                                                    evaluator_type='coco', # 指定评估方式
                                                    json_file=VAL_JSON,
                                                    image_root=VAL_PATH)

4、训练 

from detectron2.engine import DefaultTrainer
from detectron2.config import get_cfg
from detectron2.utils.logger import setup_logger
import os
setup_logger()
import fruitsnuts_data   #导入注册文件,完成注册

if __name__ == "__main__":
    cfg = get_cfg()
    cfg.merge_from_file(
        "../configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"
    )
    cfg.DATASETS.TRAIN = ("my_train",)
    cfg.DATASETS.TEST = ("my_val",)  # 没有不用填
    cfg.DATALOADER.NUM_WORKERS = 2
    #预训练模型文件
    #没有可以下载
    cfg.MODEL.WEIGHTS = r"detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl"
    #或者使用自己的预训练模型
    # cfg.MODEL.WEIGHTS = "../tools/output/model_0003191.pth"
    cfg.SOLVER.IMS_PER_BATCH = 2
    cfg.SOLVER.BASE_LR = 0.0025
    #最大迭代次数
    cfg.SOLVER.MAX_ITER = (2500)
    cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = (128)  # faster, and good enough for this toy dataset
    cfg.MODEL.ROI_HEADS.NUM_CLASSES = 2  # 3 classes (data, fig, hazelnut)
    os.makedirs(cfg.OUTPUT_DIR, exist_ok=True)
    trainer = DefaultTrainer(cfg)
    trainer.resume_or_load(resume=False)
    trainer.train()

如果使用验证集验证出现如下报错:

No evaluator found. Use `DefaultTrainer.test(evaluators=)`, or implement its `build_evaluator` method.

 参考:  https://blog.csdn.net/weixin_42899627/article/details/119831887

5、测试

from detectron2.utils.visualizer import Visualizer
from detectron2.data.catalog import MetadataCatalog
import cv2
from detectron2.config import get_cfg
import os
from detectron2.engine.defaults import DefaultPredictor
from detectron2.utils.visualizer import ColorMode
import fruitsnuts_data   #导入注册文件,完成注册


fruits_nuts_metadata = MetadataCatalog.get("my_train")  #换成自己注册的数据集


if __name__ == "__main__":
    cfg = get_cfg()
    #加载模型文件
    cfg.merge_from_file(
        "../configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"
    )
    #加载训练好的模型文件
    cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth") 
    print('loading from: {}'.format(cfg.MODEL.WEIGHTS))
    cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5   # 阈值
    cfg.MODEL.ROI_HEADS.NUM_CLASSES = 2  #类别数
    cfg.DATASETS.TEST = ("my_val", )
    predictor = DefaultPredictor(cfg)

    data_f = 'test1.jpg'   #测试图片
    im = cv2.imread(data_f)
    outputs = predictor(im)
    v = Visualizer(im[:, :, ::-1],
                   metadata=fruits_nuts_metadata,
                   scale=0.8,
                   instance_mode=ColorMode.IMAGE_BW   # remove the colors of unsegmented pixels
                   )
    v = v.draw_instance_predictions(outputs["instances"].to("cpu"))
    img = v.get_image()[:, :, ::-1]
    cv2.imshow('rr', img)
    cv2.waitKey(0)

效果展示

Detectron2 自定义数据集 完成训练与测试_第5张图片

你可能感兴趣的:(pytorch,图像识别,图像处理)