使用labelme制作自己的语义分割数据集

安装labelme

在cmd中激活我们使用的python环境，然后使用pip命令安装labelme，命令如下：

• pip install labelme==3.16.7

注意：如果安装最新版本的 labelme，就无须指定版本号(3.16.7就是版本号)

打开labelme

在cmd中激活我们使用的python环境，然后使用下面的命令，就可以打开labelme软件：

• labelme

界面如下图：

使用labelme对数据集进行标注

• 标注之前我们可以先设置一下自动保存：file——>Save Automatically
• 第一步：打开我们要标注图片的文件夹
  
• 第二步：选择多边形标注，然后对图片进行标注，通过点选来绘制多边形。
  

对存储标注信息的json文件进行装换

import base64
import json
import os
import os.path as osp
import numpy as np
import PIL.Image
from labelme import utils
if __name__ == '__main__':
    # 存储原始图片的文件夹
    jpgs_path = "datasets/JPEGImages"
    # 存储标签的文件夹
    pngs_path = "datasets/SegmentationClass"
    # 一共有多少个类，如果标签中有两个类，class列表就是三个值，多一个是背景
    classes = ["_background_","cat","bicycle"]
    
    # 存储原始图片和标注信息的文件夹
    count = os.listdir("./datasets/image_json/") 
    for i in range(0, len(count)):
        path = os.path.join("./datasets/image_json", count[i])

        if os.path.isfile(path) and path.endswith('json'):
            data = json.load(open(path))
            
            if data['imageData']:
                imageData = data['imageData']
            else:
                imagePath = os.path.join(os.path.dirname(path), data['imagePath'])
                with open(imagePath, 'rb') as f:
                    imageData = f.read()
                    imageData = base64.b64encode(imageData).decode('utf-8')

            img = utils.img_b64_to_arr(imageData)
            label_name_to_value = {
     '_background_': 0}
            for shape in data['shapes']:
                label_name = shape['label']
                if label_name in label_name_to_value:
                    label_value = label_name_to_value[label_name]
                else:
                    label_value = len(label_name_to_value)
                    label_name_to_value[label_name] = label_value
            
            # label_values must be dense
            label_values, label_names = [], []
            for ln, lv in sorted(label_name_to_value.items(), key=lambda x: x[1]):
                label_values.append(lv)
                label_names.append(ln)
            assert label_values == list(range(len(label_values)))
            
            lbl = utils.shapes_to_label(img.shape, data['shapes'], label_name_to_value)
            
                
            PIL.Image.fromarray(img).save(osp.join(jpgs_path, count[i].split(".")[0]+'.jpg'))

            new = np.zeros([np.shape(img)[0],np.shape(img)[1]])
            for name in label_names:
                index_json = label_names.index(name)
                index_all = classes.index(name)
                new = new + index_all*(np.array(lbl) == index_json)

            utils.lblsave(osp.join(pngs_path, count[i].split(".")[0]+'.png'), new)
            print('Saved ' + count[i].split(".")[0] + '.jpg and ' + count[i].split(".")[0] + '.png')

运行结束去对应文件夹查看即可

对数据集进行分割以及生成txt文件

import os
import random 
random.seed(0)
# 对数据集进行划分的代码
segfilepath=r'./SegmentationClass'  # 存储标签的文件夹
saveBasePath=r"./ImageSets/Segmentation/"   # 存储txt文件的文件夹
#  修改train_percent用于改变验证集的比例
trainval_percent=1
train_percent=0.9

temp_seg = os.listdir(segfilepath)
total_seg = []
for seg in temp_seg:
    if seg.endswith(".png"):
        total_seg.append(seg)

num=len(total_seg)  
list=range(num)  
tv=int(num*trainval_percent)  
tr=int(tv*train_percent)  
trainval= random.sample(list,tv)  
train=random.sample(trainval,tr)  
 
print("train and val size",tv)
print("traub suze",tr)
ftrainval = open(os.path.join(saveBasePath,'trainval.txt'), 'w')  
ftest = open(os.path.join(saveBasePath,'test.txt'), 'w')  
ftrain = open(os.path.join(saveBasePath,'train.txt'), 'w')  
fval = open(os.path.join(saveBasePath,'val.txt'), 'w')  
 
for i  in list:  
    name=total_seg[i][:-4]+'\n'  
    if i in trainval:  
        ftrainval.write(name)  
        if i in train:  
            ftrain.write(name)  
        else:  
            fval.write(name)  
    else:  
        ftest.write(name)  
        
ftrainval.close()  
ftrain.close()  
fval.close()  
ftest .close()

设置好对应的文件夹路径，直接运行即可