IO format

[asmagen]

trafficstars

Hello,

How do I perform multi class semantic (instance) segmentation over my set of 2D PNG/TIF grayscale images and their corresponding masks file (NPY numpy array, TIF or any other) matrix representation with # channels corresponding to the classes? Do I need to use NIFTI_interface? If so, how do I convert my PNG/TIF/NPY files to this format?

Thank you

[black0017]

Hello Assaf and thanks for your issue! We are currently working on stabilizing the 3D workflow of the project, as it is our main focus. It is true that our 2D image support is limited right now.

When we will release the first stable version, I would like to take a more comprehensive look on the 2D IO. If you are interested or like to contribute let me know.

Please note that this is a project that I develop in my spare time and we are just two people so our progress is kind of slow.

I hope you understand.

All the best :)

N.A.