Skip to content

Conversation

HyeonJaeGil
Copy link

Current load_and_preprocess_images function only takes RGB images,
but some domains (ex. thermal images) are working with grayscale images.

The purpose of this PR is to add an option to choose between RGB / Grayscale for user's input.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Meta Open Source bot. label May 9, 2025
@jytime
Copy link
Contributor

jytime commented May 13, 2025

Hi,

Since our model expects 3-channel input images, I believe that even grayscale inputs would need to be converted to a 3-channel format (e.g., by converting to RGB or duplicating the single channel).
Using img = img.convert("L") produces a single-channel image, which seems incompatible with our model's requirements.
Please let me know if this is correct, or if I've misunderstood something.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Meta Open Source bot.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants