MrBlankness / LightM-UNet

Pytorch implementation of "LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation"
https://arxiv.org/abs/2403.05246
Apache License 2.0
254 stars 24 forks source link

Looking for problem solutions #4

Open FORGATABLE opened 5 months ago

FORGATABLE commented 5 months ago

When I train my dataset, I've found this problem. I'm looking for some ways to solve this !! ![Uploading

屏幕截图 2024-03-18 212943
MarkonH commented 5 months ago

Hi! I've encountered the same issue. Have you managed to resolve it?

pwaver commented 5 months ago

Same problem. Other projects using causal conv1d seem to have a similar problem, such as https://github.com/hustvl/Vim/issues/34. However the workarounds in those threads such as requiring "causal_conv1d==1.1.0" do not work for me.

FORGATABLE commented 5 months ago

Same problem. Other projects using causal conv1d seem to have a similar problem, such as hustvl/Vim#34. However the workarounds in those threads such as requiring "causal_conv1d==1.1.0" do not work for me.

I've seen this solution and tried that, it didn't work for me too. I got only way is waiting for author's reply....

Li-4 commented 5 months ago

I used pip to install causal_conv1d and mamba-ssm without specifying the version.

FORGATABLE commented 5 months ago

I used pip to install causal_conv1d and mamba-ssm without specifying the version.

Did you meet this problem with this way?

HashmatShadab commented 5 months ago
conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.7 -c pytorch -c nvidia
pip install packaging
pip install causal-conv1d==1.1.1
pip install mamba-ssm==1.1.4
pip install torchinfo timm numba
pip install monai==1.3.0

This worked for me

MrBlankness commented 5 months ago

When I train my dataset, I've found this problem. I'm looking for some ways to solve this !! ![Uploading 屏幕截图 2024-03-18 212943

Is your issue resolved? If not, could you please provide the package versions you are currently using in your virtual environment?

pwaver commented 5 months ago

Worked for me as well.

On Mar 21, 2024, at 6:44 AM, Malik Hashmat @.***> wrote:

conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.7 -c pytorch -c nvidia pip install packaging pip install causal-conv1d==1.1.1 pip install mamba-ssm==1.1.4 pip install torchinfo timm numba pip install monai==1.3.0 This worked for me

— Reply to this email directly, view it on GitHub https://github.com/MrBlankness/LightM-UNet/issues/4#issuecomment-2011903359, or unsubscribe https://github.com/notifications/unsubscribe-auth/AHMBV6WAJDZ3ORWAGESL5D3YZK2ZLAVCNFSM6AAAAABE3TF636VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAMJRHEYDGMZVHE. You are receiving this because you commented.

FORGATABLE commented 5 months ago

When I train my dataset, I've found this problem. I'm looking for some ways to solve this !! ![Uploading 屏幕截图 2024-03-18 212943

Is your issue resolved? If not, could you please provide the package versions you are currently using in your virtual environment?

I already solve that problem. But there is another problem like below! 屏幕截图 2024-03-30 094459

SoloTillDawn commented 5 months ago

当我训练数据集时,我发现了这个问题。我正在寻找一些方法来解决这个问题! ![正在上传屏幕截图 2024-03-18 212943

您的问题解决了吗?如果没有,您能否提供package您当前在虚拟环境中使用的版本?

我已经解决了这个问题。但还有一个问题,如下所示! 屏幕截图 2024-03-30 094459

Hello, I have the same problem as you. Have you solved the problem you encountered? mamba