其他分享
首页 > 其他分享> > labelme标注后如何生成数据集

labelme标注后如何生成数据集

作者:互联网

安装labelme环境

打开Anaconda Prompt, 直接输入pip install labelme即可安装

<!-- more -->

标注图片的两种方法

由于课题研究主要针对髋骨附近的股骨进行标注,只需要一种标签即可:

方法一

1)直接在Anaconda Prompt中输入labelme即可;

2)点击OpenDir选择所要标注的图片目录,标签名自己随意起就好了;

3)点击File->Change OutputDir来改变保存json文件的位置;

4)标注完成后需要生成数据集,首先找到Anaconda环境下的labelme_json_to_dataset.exe文件,在我的电脑上文件路径是D:\anaconda3\Scripts,将labelme_json_to_dataset.exe复制到你想要保存图片的文件夹,然后修改D: \anaconda3\Lib\site-packages\labelme\cl 目录下的json_to_dataset.py文件, 修改为:

  

import argparse
import json
import os
import os.path as osp
import warnings
​
import PIL.Image
import yaml
​
from labelme import utils
import base64
​
def main():
    warnings.warn("This script is aimed to demonstrate how to convert the\n"
                  "JSON file to a single image dataset, and not to handle\n"
                  "multiple JSON files to generate a real-use dataset.")
    parser = argparse.ArgumentParser()
    parser.add_argument('json_file')
    parser.add_argument('-o', '--out', default=None)
    args = parser.parse_args()
json_file = args.json_file
if args.out is None:
    out_dir = osp.basename(json_file).replace('.', '_')
    out_dir = osp.join(osp.dirname(json_file), out_dir)
else:
    out_dir = args.out
if not osp.exists(out_dir):
    os.mkdir(out_dir)
 
count = os.listdir(json_file) 
for i in range(0, len(count)):
    path = os.path.join(json_file, count[i])
    if os.path.isfile(path):
        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)
        
        captions = ['{}: {}'.format(lv, ln)
            for ln, lv in label_name_to_value.items()]
        lbl_viz = utils.draw_label(lbl, img, captions)
        
        out_dir = osp.basename(count[i]).replace('.', '_')
        out_dir = osp.join(osp.dirname(count[i]), out_dir)
        if not osp.exists(out_dir):
            os.mkdir(out_dir)
 
        PIL.Image.fromarray(img).save(osp.join(out_dir, 'img.png'))
        #PIL.Image.fromarray(lbl).save(osp.join(out_dir, 'label.png'))
        utils.lblsave(osp.join(out_dir, 'label.png'), lbl)
        PIL.Image.fromarray(lbl_viz).save(osp.join(out_dir, 'label_viz.png'))
 
        with open(osp.join(out_dir, 'label_names.txt'), 'w') as f:
            for lbl_name in label_names:
                f.write(lbl_name + '\n')
 
        warnings.warn('info.yaml is being replaced by label_names.txt')
        info = dict(label_names=label_names)
        with open(osp.join(out_dir, 'info.yaml'), 'w') as f:
            yaml.safe_dump(info, f, default_flow_style=False)
 
        print('Saved to: %s' % out_dir)
if __name__ == '__main__':
    main()

 

cd 到labelme_json_to_dataset.exe所在目录,然后执行labelme_json_to_dataset json文件目录;

该方法缺点是json文件生成的都是单独的文件夹,无法将所有标签放在一个目录,在处理多个图片文件夹的时候较为不便,方法二则可以更为方便的标注数据集;

方法二

1)在所要标注的图片文件中新建labels.txt文件,并在文件内输入如下信息:

bone为自己定义的标签,如果需要多种标签则继续换行添加即可

2)在输出目录中添加labelme2voc.py文件,文件内容为:

 

#!/usr/bin/env python
​
from __future__ import print_function
​
import argparse
import glob
import os
import os.path as osp
import sys
​
import imgviz
import numpy as np
​
import labelme
def main():
    parser = argparse.ArgumentParser(
        formatter_class=argparse.ArgumentDefaultsHelpFormatter
    )
    parser.add_argument("input_dir", help="input annotated directory")
    parser.add_argument("output_dir", help="output dataset directory")
    parser.add_argument("--labels", help="labels file", required=True)
    parser.add_argument(
        "--noviz", help="no visualization", action="store_true"
    )
    args = parser.parse_args()
if osp.exists(args.output_dir):
    print("Output directory already exists:", args.output_dir)
    sys.exit(1)
os.makedirs(args.output_dir)
os.makedirs(osp.join(args.output_dir, "JPEGImages"))
os.makedirs(osp.join(args.output_dir, "SegmentationClass"))
os.makedirs(osp.join(args.output_dir, "SegmentationClassPNG"))
if not args.noviz:
    os.makedirs(
        osp.join(args.output_dir, "SegmentationClassVisualization")
    )
print("Creating dataset:", args.output_dir)
​
class_names = []
class_name_to_id = {}
for i, line in enumerate(open(args.labels).readlines()):
    class_id = i - 1  # starts with -1
    class_name = line.strip()
    class_name_to_id[class_name] = class_id
    if class_id == -1:
        assert class_name == "__ignore__"
        continue
    elif class_id == 0:
        assert class_name == "_background_"
    class_names.append(class_name)
class_names = tuple(class_names)
print("class_names:", class_names)
out_class_names_file = osp.join(args.output_dir, "class_names.txt")
with open(out_class_names_file, "w") as f:
    f.writelines("\n".join(class_names))
print("Saved class_names:", out_class_names_file)
​
for filename in glob.glob(osp.join(args.input_dir, "*.json")):
    print("Generating dataset from:", filename)
​
    label_file = labelme.LabelFile(filename=filename)
​
    base = osp.splitext(osp.basename(filename))[0]
    out_img_file = osp.join(args.output_dir, "JPEGImages", base + ".jpg")
    out_lbl_file = osp.join(
        args.output_dir, "SegmentationClass", base + ".npy"
    )
    out_png_file = osp.join(
        args.output_dir, "SegmentationClassPNG", base + ".png"
    )
    if not args.noviz:
        out_viz_file = osp.join(
            args.output_dir,
            "SegmentationClassVisualization",
            base + ".jpg",
        )
​
    with open(out_img_file, "wb") as f:
        f.write(label_file.imageData)
    img = labelme.utils.img_data_to_arr(label_file.imageData)
​
    lbl, _ = labelme.utils.shapes_to_label(
        img_shape=img.shape,
        shapes=label_file.shapes,
        label_name_to_value=class_name_to_id,
    )
    labelme.utils.lblsave(out_png_file, lbl)
​
    np.save(out_lbl_file, lbl)
​
    if not args.noviz:
        viz = imgviz.label2rgb(
            label=lbl,
            img=imgviz.rgb2gray(img),
            font_size=15,
            label_names=class_names,
            loc="rb",
        )
        imgviz.io.imsave(out_viz_file, viz)
if __name__ == "__main__":
    main()        
 

 

3)输入以下命令 labelme images --labels labels.txt --nodata --validatelabel exact --config '{shift_auto_shape_color: -2}' ,若无效,手动打开labelme进行标注;

4)标注完成后执行:python labelme2voc.py images target --labels labels.txt即可

 

标签:标注,name,osp,label,生成,labelme,class,dir,out
来源: https://www.cnblogs.com/Season-Chu/p/14940649.html