The trained model is not working well.

[pengweixiang]

Thanks very much for your code! That really help my a lot. I generated the data set according to your paper requirements. I applied the data to the training model code you provided and found that it did not achieve the expected results. The Mixed audio file cannot separate even a little. The separated audio file has only the difference in sound size from the original file.

[JayYang-Fdu]

Thanks very much for your code! That really help my a lot. I generated the data set according to your paper requirements. I applied the data to the training model code you provided and found that it did not achieve the expected results. The Mixed audio file cannot separate even a little. The separated audio file has only the difference in sound size from the original file.

hi! I want to know how to get the dataset, and I can't get the dataset. then,I import the dataset which I made by myself failed,and get the error like this:"
OSError: Unable to open file (unable to open file: name = 'C:\Users\YJ.anaconda\trian', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)" I don't konw how to solve this problem.
Thank you for your time! your prompt reply will be highly appreciated!

[JayYang-Fdu]

Thanks very much for your code! That really help my a lot. I generated the data set according to your paper requirements. I applied the data to the training model code you provided and found that it did not achieve the expected results. The Mixed audio file cannot separate even a little. The separated audio file has only the difference in sound size from the original file.

hello! May I ask that how to convert the dataset "timit" to HD5F,the question is bothering me...

what I should do to solve it, thank you for your reply.

[JayYang-Fdu]

Thanks very much for your code! That really help my a lot. I generated the data set according to your paper requirements. I applied the data to the training model code you provided and found that it did not achieve the expected results. The Mixed audio file cannot separate even a little. The separated audio file has only the difference in sound size from the original file.

hello，I come here again，I only have timit dataset，so how to implement this code？ your prompt reple will be highly appreciated!!!

[pengweixiang]

Thanks very much for your code! That really help my a lot. I generated the data set according to your paper requirements. I applied the data to the training model code you provided and found that it did not achieve the expected results. The Mixed audio file cannot separate even a little. The separated audio file has only the difference in sound size from the original file.

hello，I come here again，I only have timit dataset，so how to implement this code？ your prompt reple will be highly appreciated!!!

You can generate the data of the target field according to the paper provided by the author, and confirm that the version of the corresponding pytorch should be able to run smoothly. Because of the limitations of this project, I temporarily gave up and continued to follow up on this project. But the idea of the project is good.

[JayYang-Fdu]

thank you for your prompt reply！I have saw the original paper...but I can't get the way to generate the data which he use wsj0 dataset!Thank you again for your reply!发自我的华为手机-------- 原始邮件 --------主题：Re: [naplab/DANet] The trained model is not working well. (#1)发件人：pengweixiang 收件人：naplab/DANet 抄送：Yangjie55 ,Comment Thanks very much for your code! That really help my a lot. I generated the data set according to your paper requirements. I applied the data to the training model code you provided and found that it did not achieve the expected results. The Mixed audio file cannot separate even a little. The separated audio file has only the difference in sound size from the original file. hello，I come here again，I only have timit dataset，so how to implement this code？ your prompt reple will be highly appreciated!!! You can generate the data of the target field according to the paper provided by the author, and confirm that the version of the corresponding pytorch should be able to run smoothly. Because of the limitations of this project, I temporarily gave up and continued to follow up on this project. But the idea of the project is good. —You are receiving this because you commented.Reply to this email directly, view it on GitHub, or mute the thread.

[pengweixiang]

A simple audio data of about 5 seconds is fine. There are many free data sets online. The key is to not make mistakes when dealing with audio masks. The principle of the model is also very simple.

…

------------------ 原始邮件 ------------------ 发件人: "Yangjie55"<[email protected]>; 发送时间: 2019年5月14日(星期二) 下午5:27 收件人: "naplab/DANet"<[email protected]>; 抄送: "小丑鱼笨笨"<[email protected]>; "Author"<[email protected]>; 主题: Re: [naplab/DANet] The trained model is not working well. (#1) thank you for your prompt reply！I have saw the original paper...but I can't get the way to generate the data which he use wsj0 dataset!Thank you again for your reply!发自我的华为手机-------- 原始邮件 --------主题：Re: [naplab/DANet] The trained model is not working well. (#1)发件人：pengweixiang 收件人：naplab/DANet 抄送：Yangjie55 ,Comment Thanks very much for your code! That really help my a lot. I generated the data set according to your paper requirements. I applied the data to the training model code you provided and found that it did not achieve the expected results. The Mixed audio file cannot separate even a little. The separated audio file has only the difference in sound size from the original file. hello，I come here again，I only have timit dataset，so how to implement this code？ your prompt reple will be highly appreciated!!! You can generate the data of the target field according to the paper provided by the author, and confirm that the version of the corresponding pytorch should be able to run smoothly. Because of the limitations of this project, I temporarily gave up and continued to follow up on this project. But the idea of the project is good. —You are receiving this because you commented.Reply to this email directly, view it on GitHub, or mute the thread. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.

[weedwind]

@pengweixiang Hi, are you able to figure out the reason why it did not work?