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

Generation of normalisation_values.pkl #24

Open
bjovc opened this issue Apr 12, 2024 · 1 comment
Open

Generation of normalisation_values.pkl #24

bjovc opened this issue Apr 12, 2024 · 1 comment

Comments

@bjovc
Copy link

bjovc commented Apr 12, 2024

Hi, I am aiming to use this model with my own dataset. I have used the dataset_preparation.py file to do so, and it created the META and DATA folders correctly. However I am not able to find a way to make the normalisation_values.pkl necesarry to train the model with my data, is there any way to create it?

@VSainteuf
Copy link
Owner

Hi @bjovc,
Good to know that the dataset preparation worked.
You have to compute the normalisation values yourself, it's just the mean and standard deviation of the pixels across the whole dataset. You can do in either of two ways:

  • compute the average and std per channel for all dates, then they would be tensors of of shape C
  • compute the average ad std per channel and date, then they would be tensors of shape CxT

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