-
Notifications
You must be signed in to change notification settings - Fork 15
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
How to pre-train the RegNet #3
Comments
@lionlai1989 Would you share you approach? |
Hello @shyu4184
Sorry for bringing more questions. If you can help me to understand the implementation. |
@lionlai1989 I also confused that how they generate the ground truth filter. As mentioned in the paper, they synthesized the ground truth filter as a convolution filter whose intensity value is 1 at the shifted pixel and the rest of the intensity value is 0 such as delta filter. Although I followed their explanation, but I'm not sure it's correctly implemented or not. |
@shyu4184 For example, if a image's shift is (x=1, y=2) pixels (paper said it has to be interger) wrt the reference image. Then what should the ground truth vector look like? And how is it related to the number of filter k*k? It is the part really confuse me. |
Sorry for late reply. |
Now I want to pre-train the RegNet with sentinel-2 and SPOT images. But I don't know how to pre-train RegNet without knowing the ground truth.
In your paper, it said
Then the next sentence is
I don't really understand this part. Where do I get the random integer amount of pixels from? If it's random, does it mean the ground truth is a random vector with a component being 1 and the rest are 0?
My question is what is ground truth data when pretraining the RegNet?
Thank you.
The text was updated successfully, but these errors were encountered: