Include Light Weight Bottle Neck Attention Unet (LWBNA_Unet) architecture

[fcossio]

Short Description

I would like to add the architecture described in the paper mentioned below.

Papers

A lightweight deep learning model for automatic segmentation and analysis of ophthalmic images, May 2022. Sharma et al. No citations yet. Was mentioned by fchollet here

Existing Implementations

fcossio/LWBNA_Unet

[fcossio]

Hi, is there any interest for this possible contribution?

[innat]

@fcossio It's a great paper. To have this in keras cv, I think we need to first add basic UNet. No semantic segmentation model is added until now. You can first create issue on that to proceed to PR.

cc. @LukeWood

[Muhammed-EmadEldeen]

Hello @innat ,
I'm wondering if the basic UNET architecture has been incorporated into the project. If it hasn't, I'd like to initiate a new issue to implement this architecture.
Before proceeding, I'd like to clarify a few things:

• Do I need to collect the data myself for this task?
• Could you please provide information about where the model will be trained?
  Thank you!

[innat]

I'm not sure but keras team is not interested to add basic / base unet. (I'm not sure why!)

[Muhammed-EmadEldeen]

Alright, thanks for the update @innat. I appreciate it.
Can you suggest a beginner-friendly issue for me to work on?

[innat]

You can contribute on documentaiton (for example , or this), - generall see the open issue and pick which interests you.

[github-actions]

This issue is stale because it has been open for 180 days with no activity. It will be closed if no further activity occurs. Thank you.

[sachinprasadhs]

Thanks for reporting the issue! We have consolidated the development of KerasCV into the new KerasHub package, which supports image, text, and multi-modal models. Please read keras-team/keras-hub#1831. KerasHub will support all the core functionality of KerasCV.

KerasHub can be installed with !pip install -U keras-hub. Documentation and guides are available at keras.io/keras_hub.

With our focus shifted to KerasHub, we are not planning any further development or releases in KerasCV. If you encounter a KerasCV feature that is missing from KerasHub, or would like to propose an addition to the library, please file an issue with KerasHub.