Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

problems during the experiment #4

Open
wawjwyy123 opened this issue Jul 25, 2023 · 8 comments
Open

problems during the experiment #4

wawjwyy123 opened this issue Jul 25, 2023 · 8 comments

Comments

@wawjwyy123
Copy link

Thank you for providing such a good open source code, I am reproducing your experiment, the TUT-SED Synthetic 2016 link provided on github has no longer worked, so I downloaded the dataset on the official website. But there are only cpickle files and txt format comments in features, and there are no .npy files, do you need to convert cpickle files to npy? I've been confused for a long time because of this question, looking forward to your reply!

@dr-costas
Copy link
Owner

Hi, the .npy files are features plus labels. You need to create those by following the description in the corresponding papers.

@dr-costas
Copy link
Owner

dr-costas commented Aug 22, 2023

At the README of this repo is written:

To set-up the data, you first have to follow the procedure and download the data from the corresponding web-page. Then, you should create your input/output values and use them with our method.

@wawjwyy123
Copy link
Author

在此存储库的自述文件中写道:

要设置数据,您首先必须按照该过程从相应的网页下载数据。然后,您应该创建输入/输出值并将其与我们的方法一起使用。

Thank you for your reply! I have downloaded the data, but how do I create an .npy file? This is a question that I have been confused about. Can you tell me the specific method?

@dr-costas
Copy link
Owner

dr-costas commented Aug 22, 2023

The .npy files are just numpy arrays. To create such a file, you can use the numpy methods for saving an array and give the file name xxxx.npy where xxxx is whatever you want.

@dr-costas
Copy link
Owner

Sorry, but I don't remember what these pickle files are. The target value is the targeted output of your network. You should check the code and the paper, there is enough information for reproducing the experiment, but I cannot remember exactly now the details. I need to also check the paper and code in order to give you answers, and I don't think that I can do that now. You need to do it yourself :)

@wawjwyy123
Copy link
Author

在此存储库的自述文件中写道:

要设置数据,您首先必须按照该过程从相应的网页下载数据。然后,您应该创建输入/输出值并将其与我们的方法一起使用。

In addition, the link you sent to this page is invalid. These features of mine are all data downloaded on the DCASE website, is it different from the content of this invalid link you shared?

@dr-costas
Copy link
Owner

Sorry, but I don't know what is in the files from the DCASE website. At the paper that is associated with this repo, there is a detailed description of the features used. You can compare and see.

@githubusercontentmi
Copy link

在此存储库的自述文件中写道:

要设置数据,您首先必须按照该过程从相应的网页下载数据。然后,您应该创建输入/输出值并将其与我们的方法一起使用。

In addition, the link you sent to this page is invalid. These features of mine are all data downloaded on the DCASE website, is it different from the content of this invalid link you shared?

Hello brother, may I ask if you have successfully reproduced?,I'm also reproducing this article.,When it's running, it keeps showing that you don't have permission to open training.,But this file can be read with other programs.。 I've been confused for a long time, if you have a successful reproduction, can you add your contact information and ask for advice.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants