Skip to content
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

Why parametric space label is generated? #48

Open
HassanBinHaroon opened this issue Aug 9, 2022 · 3 comments
Open

Why parametric space label is generated? #48

HassanBinHaroon opened this issue Aug 9, 2022 · 3 comments

Comments

@HassanBinHaroon
Copy link

When we download the dataset, it contains the ground truth.

Kindly enlighten is it necessary to create parametric space label while creating a custom dataset?

@Hanqer
Copy link
Owner

Hanqer commented Aug 10, 2022

If you want to train DHT on your custom dataset, the straight line annotations is needed to calculate the parameteric space lable.
Then train your model with the parameteric space label.

@HassanBinHaroon
Copy link
Author

If I create the straight line annotations then How can I calculate parametric space label?

There are two scripts of calculating parametric space label each for different dataset (prepare_data_NKL.py & prepare_data_JTLEE.py).

Can any of these two (prepare_data_NKL.py & prepare_data_JTLEE.py) be used If I create my custom dataset to create parametric space label?

@HassanBinHaroon
Copy link
Author

HassanBinHaroon commented Aug 11, 2022

@Hanqer @zeakey @garipovroma Kindly take a look at my Github repository. I tried to reproduce your work on Google Colab. Sometimes its convenient to run on Google Colab for the users and for instant results visualization. If you approve the work then you can provide reference of my repository on yours. Thanks!

https://github.com/HassanBinHaroon/deep-hough-transform

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants