FusionMamba

(vmamba) gcl@linux:~/project/FusionMamba-main$ python train.py
Traceback (most recent call last):
  File "/home/gcl/project/FusionMamba-main/train.py", line 150, in <module>
    train(args, training_data_loader, validate_data_loader)
  File "/home/gcl/project/FusionMamba-main/train.py", line 44, in train
    model = Net(args.channels, args.spa_channels, args.spe_channels, args.H, args.W, args.ratio).to(args.device)
  File "/home/gcl/project/FusionMamba-main/model/u2net.py", line 143, in __init__
    self.stage0 = Stage(dim0, dim1, H, W, sample_mode='down')
  File "/home/gcl/project/FusionMamba-main/model/u2net.py", line 98, in __init__
    self.fm = FusionMamba(in_channels, H, W)
  File "/home/gcl/project/FusionMamba-main/model/fusion_mamba.py", line 53, in __init__
    self.spa_mamba_layers.append(SingleMambaBlock(dim, H, W))
  File "/home/gcl/project/FusionMamba-main/model/fusion_mamba.py", line 16, in __init__
    self.block = Mamba(dim, expand=1, d_state=8, bimamba_type='v6',
TypeError: Mamba.__init__() got an unexpected keyword argument 'bimamba_type'

(vim) gcl@linux:~/project/Vim-main$ pip install -e causal_conv1d>=1.1.0
ERROR: causal_conv1d is not a valid editable requirement. It should either be a path to a local project or a VCS URL (beginning with bzr+http, bzr+https, bzr+ssh, bzr+sftp, bzr+ftp, bzr+lp, bzr+file, git+http, git+https, git+ssh, git+git, git+file, hg+file, hg+http, hg+https, hg+ssh, hg+static-http, svn+ssh, svn+http, svn+https, svn+svn, svn+file).

Building wheels for collected packages: causal_conv1d, buildtools, docopt
  Building wheel for causal_conv1d (setup.py) ... error
  error: subprocess-exited-with-error
 
  × python setup.py bdist_wheel did not run successfully.
  │ exit code: 1
  ╰─> [8 lines of output]
      
      
      torch.__version__  = 2.0.1
      
      
      running bdist_wheel
      Guessing wheel URL:  https://github.com/Dao-AILab/causal-conv1d/releases/download/v1.1.0/causal_conv1d-1.1.0+cu118torch2.0cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
      error: <urlopen error [Errno 110] Connection timed out>
      [end of output]
 
  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for causal_conv1d
  Running setup.py clean for causal_conv1d
  Building wheel for buildtools (setup.py) ... done
  Created wheel for buildtools: filename=buildtools-1.0.6-py3-none-any.whl size=512341 sha256=9007d3028630c674c7e307b34770f24e9ea07bd92e28c881bb7dec69da9377a7
  Stored in directory: /home/gcl/.cache/pip/wheels/4d/34/e6/15a50e39b0152c62c16d66d99b5fb5e2c9626f5ede50339399
  Building wheel for docopt (setup.py) ... done
  Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13706 sha256=cfb0f1d7d6e51851c687e12ee102c1ff23a35cf3418679b5e2e115263930e7cd
  Stored in directory: /home/gcl/.cache/pip/wheels/fb/99/16/e5da1ec03039a23b30a33c185596375c9ea1869029e8d89bfa
Successfully built buildtools docopt
Failed to build causal_conv1d
ERROR: Could not build wheels for causal_conv1d, which is required to install pyproject.toml-based projects

wget https://github.com/Dao-AILab/causal-conv1d/releases/download/v1.1.3.post1/causal_conv1d-1.1.3.post1+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
wget https://github.com/state-spaces/mamba/releases/download/v1.1.1/mamba_ssm-1.1.1+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
 
pip install causal_conv1d-1.1.3.post1+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl 
pip install mamba_ssm-1.1.1+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl 

vim) gcl@linux:~/project/FusionMamba-main$ python train.py
Traceback (most recent call last):
  File "/home/gcl/anaconda3/envs/vim/lib/python3.10/site-packages/mamba_ssm/modules/mamba_simple.py", line 19, in <module>
    from mamba_ssm.ops.selective_scan_interface import selective_scan_fn, mamba_inner_fn, bimamba_inner_fn, mamba_inner_fn_no_out_proj
ImportError: cannot import name 'bimamba_inner_fn' from 'mamba_ssm.ops.selective_scan_interface' (/home/gcl/anaconda3/envs/vim/lib/python3.10/site-packages/mamba_ssm/ops/selective_scan_interface.py)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/gcl/project/FusionMamba-main/train.py", line 14, in <module>
    from model.u2net import U2Net as Net
  File "/home/gcl/project/FusionMamba-main/model/u2net.py", line 5, in <module>
    from model.fusion_mamba import FusionMamba
  File "/home/gcl/project/FusionMamba-main/model/fusion_mamba.py", line 7, in <module>
    from mamba_ssm.modules.mamba_simple import Mamba
  File "/home/gcl/anaconda3/envs/vim/lib/python3.10/site-packages/mamba_ssm/__init__.py", line 4, in <module>
    from mamba_ssm.modules.mamba_simple import Mamba
  File "/home/gcl/anaconda3/envs/vim/lib/python3.10/site-packages/mamba_ssm/modules/mamba_simple.py", line 21, in <module>
    selective_scan_fn, mamba_inner_fn, bimamba_inner_fn, mamba_inner_fn_no_out_proj = None, None, None, None, None
ValueError: too many values to unpack (expected 4)