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

Custom Datasets #5

Open
pauldeee opened this issue Sep 5, 2024 · 2 comments
Open

Custom Datasets #5

pauldeee opened this issue Sep 5, 2024 · 2 comments

Comments

@pauldeee
Copy link

pauldeee commented Sep 5, 2024

This is some exciting work, thank you!

I have a few questions in regards to custom datasets:

  1. Is there a specific format or structure required for custom datasets?
  2. Are there any configuration options or parameters in the current implementation that need to be adjusted when working with datasets outside the GarageWorld dataset?
  3. Is there a recommended method to load and preprocess custom data for the training process?

Thank you!

@pauldeee pauldeee changed the title Cutsom Datasets Custom Datasets Sep 5, 2024
@zhaofuq
Copy link
Owner

zhaofuq commented Sep 23, 2024

We provide a sample dataset in this repository

This is some exciting work, thank you!

I have a few questions in regards to custom datasets:

  1. Is there a specific format or structure required for custom datasets?
  2. Are there any configuration options or parameters in the current implementation that need to be adjusted when working with datasets outside the GarageWorld dataset?
  3. Is there a recommended method to load and preprocess custom data for the training process?

Thank you!

@Lithinem
Copy link

This is some exciting work, thank you!

I have a few questions in regards to custom datasets:

1. Is there a specific format or structure required for custom datasets?

2. Are there any configuration options or parameters in the current implementation that need to be adjusted when working with datasets outside the GarageWorld dataset?

3. Is there a recommended method to load and preprocess custom data for the training process?

Thank you!

Hi,
did you find any answers to your question by now? Im having similar problems. Like the convert.py generates .bin files where the sample dataset suggests the necessity of .ply and .txt files. Furthermore the file size differs a lot. Like when I try to run the convert.py on the sample dataset images i have like 20 kb where 140 mb would be expected.

Could you please help me?

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