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

How to train on other data #20

Open
gxu12 opened this issue Oct 21, 2023 · 6 comments
Open

How to train on other data #20

gxu12 opened this issue Oct 21, 2023 · 6 comments

Comments

@gxu12
Copy link

gxu12 commented Oct 21, 2023

Hi,
I just got other dental data in obj format, but I do not know how to label it correctly and create right json file, do you have any suggestions?
Thank you! @limhoyeon

@limhoyeon
Copy link
Owner

Im sorry for late reply.
plz check the data description on this web page.
You just need to fit your data into the same format as the challenge data.
Thanks.

@gxu12
Copy link
Author

gxu12 commented Oct 30, 2023

Hi,
Thanks for your respond. After viewing the page, I got to know how to label it under FDI standard, but I still do not know how to rotate my own data to the same angle as your dataset. Is there any way for me to handle this problem?
(All axes must be aligned as shown in the figure below. Note that the Y-axis points towards the back direction(plz note that both lower jaw and upper jaw have the same z-direction!)
Thank you! @limhoyeon

@limhoyeon
Copy link
Owner

you can use meshlab manually, or apply PCA to align axis automatically.

@gxu12
Copy link
Author

gxu12 commented Nov 24, 2023

you can use meshlab manually, or apply PCA to align axis automatically.

Really appreciate for yiur response! I just have one more question, I now already use mesh lab to manually align axis. But what is the logic between label and instance? the example is like, I found for different json files, the relation between “label” and “instance” is not fixed. For example, for obj1, maybe label = 9 is related to instance = 43, but for obj2, label = 9 is related to instance = 34. It makes me confused about the correct way to label.
Thank you very much! @limhoyeon

@coordxyz
Copy link

coordxyz commented Jan 6, 2024

Hi @gxu12 , How did you align your custom data with the challenge data? Thx
(All axes must be aligned as shown in the figure below. Note that the Y-axis points towards the back direction(plz note that both lower jaw and upper jaw have the same z-direction!)

@limhoyeon
Copy link
Owner

@gxu12
'label' is related to the FDI tooth number.
'instance' is just the random number, which means the points which have same instance value belong to the same tooth.

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

3 participants