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.

Sign up for GitHub

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

Jump to bottom

Sliding window ? #1

Open
AlKun25 opened this issue Dec 4, 2023 · 2 comments
Open

Sliding window ? #1

AlKun25 opened this issue Dec 4, 2023 · 2 comments

Comments

@AlKun25
Copy link

AlKun25 commented Dec 4, 2023 •
edited
Loading

I was looking at the official dataset code from the Auditory EEG Decoding challenge. They seem to be implementing a sliding window. I needed clarity whether you guys are implementing sliding window elsewhere, cause I didn't find it in the dataset.py.

I would really appreciate any help, as I am trying to run the code in PyTorch
@jkyunnng
Copy link
Owner

jkyunnng commented Dec 6, 2023

Thank you for your inquiry.

Unlike conventional training code, our approach omits the use of a sliding window.
During training, we employed 5-second signal segments for stability, randomly cropped from each EEG/speech envelope segment. In the inference phase, input signals are partitioned into multiple 5-second segments, and the outputs are concatenated to form the complete envelope.

Hope this provides you clarity :)

@AlKun25
Copy link
Author

AlKun25 commented Dec 14, 2023

Thank you very much, that was actually very helpful. But could you elaborate what is happening in _train_data() in dataset.py?
I am getting confused what is the need for randint.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@AlKun25 @jkyunnng