Training on own dataset about rfnet HOT 2 OPEN

@paalpri
The data we only need to train RF-Net is a pair image and their transformation.
Therefore, I think your approach is ok.

You could try it, and contact me if you encounter any problem.
:)

from rfnet.

Hi!

I want to train your model on my own dataset that is similar to COCO, with only one image of each area. Would it be possible to train your model on this type of dataset ? would love some of your input.

My idea is to generate/sample a homography of my training image and generate a patch of the same area based on this homography. Similar to what is done in SuperPoint model. And then use this connection between my original image, the generated patch and the now known sample homography between them as training. I think this would be enough to train RF-net, but there might be something i'm missing.

Is there any other parts i need as labels or known facts about my data that i need to train ? Hope i made myself understandable.

Thanks for any input!

Sincerely

Did you succeed？

from rfnet.