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

Add MAXIM model #924

Open
innat opened this issue Oct 14, 2022 · 8 comments
Open

Add MAXIM model #924

innat opened this issue Oct 14, 2022 · 8 comments

Comments

@innat
Copy link
Contributor

innat commented Oct 14, 2022

Short Description

MAXIM: Multi-Axis MLP for Image Processing: I think it's a follow-up work of MaxViT from google. It shows a great performance on the following low-vision task, i.e. for OCR.

image3

It looks useful for real world problem (blurry, haze, rain-drop). Such problems are very acute for vision project. So, such solutions might weight quick adaptation of kcv in industrial projects (alike).

Papers

Existing Implementations

cc. @vztu

@tanzhenyu
Copy link
Contributor

Open this up for contribution

@innat
Copy link
Contributor Author

innat commented Oct 28, 2022

cc @sayakpaul

@innat innat mentioned this issue Dec 15, 2022
@IMvision12
Copy link
Contributor

IMvision12 commented Dec 28, 2022

I'm working on integrating the maxim model and referencing the original flax implementation. I have one question: do we need weights as well? @tanzhenyu

@tanzhenyu
Copy link
Contributor

I'm working on integrating the maxim model and referencing the original flax implementation. I have one question: do we need weights as well? @tanzhenyu

Yes, we need the weights. The development cycle would be similar to ViT: #1014, add the model and port the weights, also add the conversion scripts for porting the weights

@bhack
Copy link
Contributor

bhack commented Dec 28, 2022

Yes, we need the weights. The development cycle would be similar to ViT: #1014, add the model and port the weights, also add the conversion scripts for porting the weights

I hope we could standardize a bit the model contribution process after we will handle:

#954

@IMvision12
Copy link
Contributor

I'm working on integrating the maxim model and referencing the original flax implementation. I have one question: do we need weights as well? @tanzhenyu

Yes, we need the weights. The development cycle would be similar to ViT: #1014, add the model and port the weights, also add the conversion scripts for porting the weights

Okay will add the conversion script too!!

@innat
Copy link
Contributor Author

innat commented Dec 29, 2022

@IMvision12
Have you checked ?
https://github.com/sayakpaul/maxim-tf

@IMvision12
Copy link
Contributor

IMvision12 commented Dec 29, 2022

@IMvision12 Have you checked ? https://github.com/sayakpaul/maxim-tf

Oh we have tf implementation for maxim, because when I saw on paper with code there was only official flax implementation
will refer that too thx for the info @innat.
Also as we already have weights ported to TF and uploaded by @sayakpaul on TF-Hub do we still require the conversion script? @tanzhenyu

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

Successfully merging a pull request may close this issue.

5 participants