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

Training in a custom dataset #2

Closed
Zumbalamambo opened this issue Sep 1, 2020 · 4 comments
Closed

Training in a custom dataset #2

Zumbalamambo opened this issue Sep 1, 2020 · 4 comments

Comments

@Zumbalamambo
Copy link

How do I prepare/structure a custom dataset?

@tonyngjichun
Copy link
Owner

tonyngjichun commented Sep 1, 2020

Hi, as you can see in the readme, we are preparing the code necessary to download and pre-process the gl18 dataset. Sorry, it is taking a bit longer than expected as we have to ensure that each and every download link is working, and the dataset is quite huge (1mil+ images). In the code, you will see how to form the database pickle file from landmark labels to suit the dataset class TuplesBatchedDataset in solar_global.datasets.traindataset. Thank you for your patience :)

@tonyngjichun
Copy link
Owner

Hi, as the data processing code has been uploaded, I'm closing this issue. Please open a new issue if you encounter specific issues with that. Thanks! :D

@hewumars
Copy link

Have you successfully trained with custom datasets? @Zumbalamambo

@CodeJjang
Copy link

CodeJjang commented Nov 27, 2021

hi @tonyngjichun, is the local solar training scheme equals the global one (just different dataset and arch setup)?
is there any chance to release the exact steps used to train the local solar system on UBC?

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

4 participants