Log in
Kye Gomez

Kye Gomez/VisionMamba

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images

265/240

Issues looking for funding

Issues regarding the initial linear layer for x and z
no-issue-activity

#25 opened in kyegomez/VisionMamba

2
Fund
Matrix dimensions do not match
no-issue-activity

#24 opened in kyegomez/VisionMamba

2
Fund
[BUG] ImportError When Trying to Import Vision Mamba After Installation
bug
no-issue-activity

#16 opened in kyegomez/VisionMamba

5
Fund
the pre-training parameter file of the model
no-issue-activity

#26 opened in kyegomez/VisionMamba

3
Fund
Thank you for your excellent work. I have a question regarding equation 6 in the paper: \( T_l = V_{im}(T_{l-1}) + T_{l-1} \). Why do you still add \( T_{l-1} \) when this addition process is already included in \( V_{im} \)?
no-issue-activity

#23 opened in kyegomez/VisionMamba

2
Fund
readme
no-issue-activity

#14 opened in kyegomez/VisionMamba

3
Fund
[BUG] Cannot import name 'SSM' from 'zeta.nn'
bug
no-issue-activity

#5 opened in kyegomez/VisionMamba

9
Fund
[BUG] heads is not an argument in Vim
bug

#34 opened in kyegomez/VisionMamba

2
Fund
the pre-training parameter file of the model
no-issue-activity

#27 opened in kyegomez/VisionMamba

1
Fund
Kye Gomezkyegomez/VisionMamba
Creatorkyegomez
Stars385
LicenseMIT License
RepositoryGitHub
Websitediscord.gg