You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Segment Anything from META: Network implementation. Has someone started already? #6357
Is your feature request related to a problem? Please describe.
Is it someone implementing in MONAI the segment anything model in MONAI? https://github.com/facebookresearch/segment-anything
My concern is the weight matching. We can help with it if someone starts already.
Describe the solution you'd like
This will make more students download and use MONAI
For sure it will be an useful network for MONAILABEL
Describe alternatives you've considered
N/A
Additional context
Add any other context or screenshots about the feature request here.
changed the title [-]Segment Anything from google: Network implementation. Does someone started already?[/-][+]Segment Anything from META: Network implementation. Does someone started already?[/+]on Apr 13, 2023
changed the title [-]Segment Anything from META: Network implementation. Does someone started already?[/-][+]Segment Anything from META: Network implementation. Has someone started already?[/+]on Apr 13, 2023
Could someone please provide a little more details about the expected outcome of the implementation?
Should the users be able to infer and/or fine-tune the SAM model on custom datasets?
Thank you
Hi @yashika-git, yes first I think we should enable users to load the existing pre-trained weights, also I think they could infer and fine-tune the model on their custom datasets.
Hi @KumoLiu, I have a very naive question: What exactly needs to be done to integrate SAM with MONAI? Does it involve modifying SAM's codebase to utilize MONAI's existing code, such as MONAI's networks and layers?
I apologize for the naive question; I'm a beginner in open source and am eager to learn through contributions.
Activity
[-]Segment Anything from google: Network implementation. Does someone started already?[/-][+]Segment Anything from META: Network implementation. Does someone started already?[/+][-]Segment Anything from META: Network implementation. Does someone started already?[/-][+]Segment Anything from META: Network implementation. Has someone started already?[/+]yashika-git commentedon Nov 24, 2023
@wyli, @ericspod,
Is the implementation of Segment Anything still required?
If yes, can I try working on this?
KumoLiu commentedon Nov 27, 2023
Hi @yashika-git, yes, welcome to your contribution.
Please refer to the CONTRIBUTION GUIDE as well.
yashika-git commentedon Nov 28, 2023
Thanks, I've started to look how it can be implemented.
yashika-git commentedon Dec 19, 2023
Could someone please provide a little more details about the expected outcome of the implementation?
Should the users be able to infer and/or fine-tune the SAM model on custom datasets?
Thank you
KumoLiu commentedon Dec 20, 2023
Hi @yashika-git, yes first I think we should enable users to load the existing pre-trained weights, also I think they could infer and fine-tune the model on their custom datasets.
yashika-git commentedon Dec 25, 2023
Hi @KumoLiu, I have a very naive question: What exactly needs to be done to integrate SAM with MONAI? Does it involve modifying SAM's codebase to utilize MONAI's existing code, such as MONAI's networks and layers?
I apologize for the naive question; I'm a beginner in open source and am eager to learn through contributions.
KumoLiu commentedon Dec 27, 2023
Hi @yashika-git, For existing parts that can be replaced by the MONAI, you should use the components of MONAI as much as possible.
[Attention block] relative positional embedding (#7346)
[Attention block] relative positional embedding (Project-MONAI#7346)