labelme批量json_to_dataset转换

我会带着你远行 2022-12-27 14:09 195阅读 0赞

之前写过的一篇博客，[https://blog.csdn.net/yql\_617540298/article/details/81110685][https_blog.csdn.net_yql_617540298_article_details_81110685]，发现朋友遇到了好多问题。

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70][]

刚好，我换了电脑之后，还没有安装这个环境，所以重新尝试了一下安装labelme，然后把遇到的问题和大家分享一下。

我之前的环境是win10+python3.6.2，现在的环境是win10+python3.7.0。

![20201213215219701.png][]

# 一、安装labelme #

pip install labelme

安装成功后，检查一下labelme的版本：

![2020121322000538.png][]

# 二、进入labelme安装目录 #

进入labelme的安装目录，主要是找到anaconda的安装目录。打开：D:\\Anaconda3\\Lib\\site-packages\\labelme\\cli

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 1][]

依然是找到json\_to\_dataset.py文件

![2020121321563746.png][]

#  三、代码修改 #

安装完labelme之后的源码：

import argparse
    import base64
    import json
    import os
    import os.path as osp
    
    import imgviz
    import PIL.Image
    
    from labelme.logger import logger
    from labelme import utils
    
    
    def main():
        logger.warning(
            "This script is aimed to demonstrate how to convert the "
            "JSON file to a single image dataset."
        )
        logger.warning(
            "It won't handle 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)
    
        data = json.load(open(json_file))
        imageData = data.get("imageData")
    
        if not imageData:
            imagePath = os.path.join(os.path.dirname(json_file), 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 sorted(data["shapes"], key=lambda x: x["label"]):
            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
        lbl, _ = utils.shapes_to_label(
            img.shape, data["shapes"], label_name_to_value
        )
    
        label_names = [None] * (max(label_name_to_value.values()) + 1)
        for name, value in label_name_to_value.items():
            label_names[value] = name
    
        lbl_viz = imgviz.label2rgb(
            label=lbl, img=imgviz.asgray(img), label_names=label_names, loc="rb"
        )
    
        PIL.Image.fromarray(img).save(osp.join(out_dir, "img.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")
    
        logger.info("Saved to: {}".format(out_dir))
    
    
    if __name__ == "__main__":
        main()

想要实现批量修改，就是要找到labelme中生成一个json文件的代码，然后加一个循环就可以了。

## 循环代码： ##

所以说，这个python的版本不重要，安装的哪个版本的labelme也不重要，主要就是在安装好的labelme的源码中加一个循环即可。

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):

然后把单张处理的代码放在这个循环内即可，全部代码：

import argparse
    import base64
    import json
    import os
    import os.path as osp
    
    import imgviz
    import PIL.Image
    
    from labelme.logger import logger
    from labelme import utils
    
    
    def main():
        logger.warning(
            "This script is aimed to demonstrate how to convert the "
            "JSON file to a single image dataset."
        )
        logger.warning(
            "It won't handle 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))
    		    imageData = data.get("imageData")
    		    
    		    if not imageData:
    		        imagePath = os.path.join(os.path.dirname(json_file), 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 sorted(data["shapes"], key=lambda x: x["label"]):
    		        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
    		    lbl, _ = utils.shapes_to_label(
    		        img.shape, data["shapes"], label_name_to_value
    		    )
    
    		    label_names = [None] * (max(label_name_to_value.values()) + 1)
    		    for name, value in label_name_to_value.items():
    		        label_names[value] = name
    
    		    lbl_viz = imgviz.label2rgb(
    		        label=lbl, img=imgviz.asgray(img), label_names=label_names, loc="rb"
    		    )
    
    		    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)
    		    	print(out_dir)
    
    		    PIL.Image.fromarray(img).save(osp.join(out_dir, "img.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")
    
    		    logger.info("Saved to: {}".format(out_dir))
    
    
    if __name__ == "__main__":
        main()

# 四、批量操作 #

打开label,exe，开始描绘勾边。

![20201213220221419.png][]

主界面如下面这样：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 2][]

随便选择几张图片，测试一下批量操作。所选的图片来源于B站上面的ps教程素材，链接：[https://www.bilibili.com/video/BV1A4411M729/?p=4][https_www.bilibili.com_video_BV1A4411M729_p_4]

![20201213223433496.png][]

在cmd中cd到labelme\_json\_to\_dataset.exe路径下，然后输入

D:\Anaconda\Scripts

其中，total这个目录是放置label.exe中保存出来的json文件。

labelme_json_to_dataset.exe C:\Users\Mango\Desktop\total

中间出现了一个错误：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 3][]

这是由于PILLOW的版本不匹配导致的，所以重新安装一下PILLOW，

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 4][]

然后，可以看到执行出来的已经是批量完成的啦。

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 5][]

在安装目录D:\\Anaconda\\Scripts中可以看到保存的两个文件夹，

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 6][]

[https_blog.csdn.net_yql_617540298_article_details_81110685]: https://blog.csdn.net/yql_617540298/article/details/81110685
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70]: /images/20221120/2b8d2b82ff274b0fb629b16b04666530.png
[20201213215219701.png]: /images/20221120/2e7252521326476eb526641c6568b638.png
[2020121322000538.png]: /images/20221120/cf02169c13114811bc8f1873d7b559e6.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 1]: /images/20221120/bd2dee49183b4a8a854097c8d127b5cc.png
[2020121321563746.png]: /images/20221120/eeda188750144eca883c3a436922cbeb.png
[20201213220221419.png]: /images/20221120/c1d17759de4c4c6b86e073e6a213b69e.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 2]: /images/20221120/e4361d7234394655992232bb4602bbc4.png
[https_www.bilibili.com_video_BV1A4411M729_p_4]: https://www.bilibili.com/video/BV1A4411M729/?p=4
[20201213223433496.png]: /images/20221120/f3ee0f05f4d04c0a90977251027ea63e.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 3]: /images/20221120/8d19d42cdbdf4b8fbd6c7145d9043722.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 4]: /images/20221120/83da1e60c7004274a6bf9df88ed2fe3c.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 5]: /images/20221120/ce3bd4f8bacb41d09b61cae9b39b34b4.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lxbF82MTc1NDAyOTg_size_16_color_FFFFFF_t_70 6]: /images/20221120/94e5374922e24e229b050ad3563ef13d.png