taming-transformers
taming-transformers copied to clipboard
[Question] How to detect and grab a grid from an image
Hi, I'm new to this field, so as part of my studies I'm trying to detect and return a Sudoku grid from and image. I know I can use the Hough lines transform but it gets messy:
It possible to detect grid more cleanly and efficiently?
I'm been trying figure out how to do image2image translation with this repo for the past few days. I think I figured it out. I'll write a guide on how to do this once I actually successfully trained a model. My issue #51.
@joe733 you could probably do this with pix2pixHD. Maybe CNN to lstm would be better for your use case. Though I dunno.
I did on that issue how to do it a few days ago #51.
Nice, I'll go through it.
I realized I didn't do it correctly. I explained more on the issue thread. Pix2pixHD is better than the way I did it.
You would have to train a vqgan model on Sudoku images and train another vqgan model on Sudoku line patterns. You would then train a transformer that would convert different the 2 images.
Hi, I'm still a beginner, so figuring things slowly. Thank you so much for the pointers!