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

A question on "audio_dataset2d" #1

Open
jeongwonmin opened this issue Aug 28, 2016 · 2 comments
Open

A question on "audio_dataset2d" #1

jeongwonmin opened this issue Aug 28, 2016 · 2 comments

Comments

@jeongwonmin
Copy link

I read your paper "Deep learning and music adversaries" and I am doing some experiments with your source code.
I tried to train my dataset with "mlp_rlu_conv2.yaml" after preparation by using "prepare_dataset.py", but it returns an error message "The value of a Conv2DSpace batch must be 4D".

I also looked for the file "audio_dataset2d", but there was no "audio_dataset2d.py".

What do I have to do before training with the convolutional neural network?

@boblsturm
Copy link
Collaborator

Ah yes. I need to update the readme.

You must prepare the dataset with the flag "--tframes 100”.

From Corey: After the dataset has been prepared for the CDNN run train_mlp_conv_script.py (not train_mpl_script.py) with the file mlp_rlu_conv2.yaml configuration file and your newly prepared train/valid/test configuration fold.

@jeongwonmin
Copy link
Author

Thank you for your comment!
It started working after I had prepared the dataset with the flag "--tframes 100".

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

2 participants