kyegomez/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
PythonMIT
Issues
- 0
[BUG] `heads` parameter is defined but not used in `VisionEncoderMambaBlock`
#21 opened by MelihDarcanxyz - 2
[BUG] Inconsistent Tensor Dimensions
#20 opened by MelihDarcanxyz - 4
[BUG]
#12 opened by Leilei-Huang-work - 5
[BUG] Matrix size is not right
#4 opened by qiaw99 - 6
[BUG] RuntimeError: Expected size for first two dimensions of batch2 tensor to be: [1, 256] but got: [1, 196].
#15 opened by MIOS9 - 2
- 3
Matrix operation
#2 opened by Lucien66 - 4
forward-backward ssm
#3 opened by swarajnanda2021 - 5
[BUG] Cannot import name 'SSM' from 'zeta.nn'
#5 opened by MarioPaps - 3
- 1
- 1
[BUG] TypeError: unhashable type: 'list'
#13 opened by uchiha99999