RUNNING ERROR

[qianquanfirstminds]

Hi，thank you for your great work. I encountered this difficulty while running the program. Can you guide me on exactly where the error occurred?

Traceback (most recent call last): File "D:\DDM2\train_noise_model.py", line 25, in opt = Logger.parse(args, stage=1) File "D:\DDM2\core\logger.py", line 28, in parse with open(opt_path, 'r') as f: FileNotFoundError: [Errno 2] No such file or directory: 'config/sr_sr3_16_128.json'

Thank you very much！

[qianquanfirstminds]

My programming language skills are relatively poor, I hope this problem is not too foolish.

[tiangexiang]

Hi Quan, thanks for your interest in our work! This error simply means the corresponding config file: 'sr_sr3_16_128.json' cannot be found under the folder: 'config/'. Can you double-check to make sure the file does exist and there is not any typo in the file name? Feel free to leave further questions here :) Thanks!

[qianquanfirstminds]

非常感谢您的回答，我目前已经解决以上问题，还在想办法将您的方法融合到我们专业中，如果后续有什么问题，我会继续请教您的。再次十分感谢您的文章！

[qianquanfirstminds]

Hi Quan, thanks for your interest in our work! This error simply means the corresponding config file: 'sr_sr3_16_128.json' cannot be found under the folder: 'config/'. Can you double-check to make sure the file does exist and there is not any typo in the file name? Feel free to leave further questions here :) Thanks!

1.代码是在Linux系统下运行的吗？我在windos系统下会报错，如下： (DDM2) PS D:\DDM2> /bin/sh D:/DDM2/run_stage1.sh /bin/sh : 无法将“/bin/sh”项识别为 cmdlet、函数、脚本文件或可运行程序的名称。请检查名称的拼写，如果包括路径，请确保路径正确，然后再试一次。 所在位置 行:1 字符: 1

• /bin/sh D:/DDM2/run_stage1.sh

• 
  + CategoryInfo          : ObjectNotFound: (/bin/sh:String) [], CommandNotFoundException
  + FullyQualifiedErrorId : CommandNotFoundException
  是不是可以修改/bin/sh指令为windos对应的就可以运行？（实在不好意思代码基础比较差）

2.我想问一下您，原始数据的训练集图片大概是多少张呢？

谢谢！

[tiangexiang]

1. 是的，我们的代码是在linux环境下开发/测试的，我们推荐您也使用linux机器（e.g. Ubuntu）或者windows虚拟机（e.g. WSL）来运行并拓展我们的代码。 这个问题确实是因为您对应的windows系统里找不到/bash/sh来执行shell脚本，换成对应指令即可。
2. 我们每个模型都是在一个单独的4D volume上进行训练。e.g. 对于hardi_150数据，其大小为[106, 81, 76, 150], 其中“2D图像”大小为106 x 81，“共有”76 x 150张。由于算法特殊性，我们要求对于[106, 81, 76]这个3D volume, 其有150种对于同一个volume的不同描述，而并非150个毫无关系的图片。当然，150个不同描述也并非强制要求，我们实验中尝试过用只有6种不同描述的数据集，我们的算法依然有效 ：）