Skip to content

Still supported? MaskedAutoencoderViT issue #71

@arzyabl

Description

@arzyabl

Hello! My team and I are trying to run this notebook to do reconstruction. We've been trying to use reconstruction to handle images with lots of clouds in them.

However it seems like perhaps support has shifted, especially with the introduction of Terratorch. Is Prithvi 1.0 on Terratorch? We were able to load the Prithvi 100 model using thenew Hugging face link, but some classes no longer exist:

Image

Our idea was to use PrithviViT class along with Facebook's MaskedAutoencoderViT but if there is a smoother way to go around this issue, that would be super helpful!

On the side note, if you know of any attempts to do that same thing on Prithvi 2, that would be super helpful as well!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions