The depth of the network does not match the paper

JCruan519 / VM-UNet

(ARXIV24) This is the official code repository for "VM-UNet: Vision Mamba UNet for Medical Image Segmentation".

Apache License 2.0

393 stars 12 forks source link

The depth of the network does not match the paper #19

Closed shengyu27 closed 3 months ago

shengyu27 commented 3 months ago

I have reviewed the pre training weights provided by the author and found that the depth is: Small: [2,2,27,2] (downsampling) Tiny: [2,2,9,2] (downsampling) This is not consistent with [2,2,2,2] in the paper?

JCruan519 commented 3 months ago

@shengyu27 Hello, VM-UNet only utilizes partial pre-trained weights, which you can configure in config.py.