DeMambaNet: Deformable Convolution and Mamba Integration Network for High-Precision Segmentation of Ambiguously Defined Dental Radicular Boundaries

Methods

Figure 1: Structure of the DeMambaNet.

Install

• Compile CUDA operators

cd ./ops_dcnv3
sh ./make.sh
# unit test (should see all checking is True)
python test.py

• You can also install the operator using .whl files DCNv3-1.0-whl

• For mamba: MAMBA-SSM and causal conv1d need to be installed, you can view the original github to install.

• This code uses versions of torch and cuda

pip install -r requirements.txt

test DeMambaNet

python build_sam_feat_seg_model.py