search

CompImg / LST-AI

LST-AI - Deep Learning Ensemble for Accurate MS Lesion Segmentation
https://doi.org/10.1016/j.nicl.2024.103611
MIT License
18 stars 4 forks source link

Strange error #10

Closed sj-choi closed 6 months ago

sj-choi commented 6 months ago

I encountered the following error after a successful LST-AI installation. Can anyone help me resolve this issue?

Installing collected packages: LST-AI Running setup.py develop for LST-AI Successfully installed LST-AI-1.0.0 (py38) xubuntu@xubuntu-VirtualBox:~/LST-AI$ cd .. (py38) xubuntu@xubuntu-VirtualBox:~$ lst -h Illegal instruction (core dumped)

Thank you, -SC

jqmcginnis commented 6 months ago

Hi @sj-choi

Can you please share the entire output from the installation?

Can you please provide more information regarding your platform? Are you installing this in a virtual box?

sj-choi commented 6 months ago

Yes, I successfully installed LST-AI on one of my VirtualBox VMs, Xubuntu 18.04 LTS, on a Windows 11 host. I processed a few examples successfully and the results were great. Then, I decided to install LST-AI on another VirtualBox VM on a Windows 10 host. The installation appeared to be successful. However, when I tried to check if it worked well on the VM on Windows 10 using the command 'lst -h' it issued the error message "Illegal instruction (core dumped)." I also tried to use 'lst' command to process actual cases that worked with the VM on Windows 11. The process issued the same error message, "Illegal instruction (core dumped)." This is an infrequent error message. Both Windows 11 and Windows 10 hosts are equipped with an identical Intel CPU. They are not very old and were purchased at a similar time. As far as I understand, the error message is related to an unsupported CPU.

In summary, both are equipped with identical Intel CPUs (Intel(R) Xeon(R) W-2123 CPU @ 3.60GHz). One installation on Xubuntu VM on Windows 11 works and another installation on identical Xubuntu VM on Windows 10 host does not work. But I doubt that this is the issue. Is there any known installation trouble on VirtualBox VMs? Any help or guidance would be greatly appreciated. All the best. -SC

FYI, I share the whole installation output below: (py38) xubuntu@xubuntu-VirtualBox:~$ git clone https://github.com/CompImg/LST-AI/ Cloning into 'LST-AI'... remote: Enumerating objects: 380, done. remote: Counting objects: 100% (33/33), done. remote: Compressing objects: 100% (22/22), done. remote: Total 380 (delta 14), reused 12 (delta 11), pack-reused 347 Receiving objects: 100% (380/380), 32.76 MiB | 16.26 MiB/s, done. Resolving deltas: 100% (183/183), done. (py38) xubuntu@xubuntu-VirtualBox:~$ cd LST-AI (py38) xubuntu@xubuntu-VirtualBox:~/LST-AI$ pip install -e . Obtaining file:///home/xubuntu/LST-AI Preparing metadata (setup.py) ... done Requirement already satisfied: numpy<1.24.4 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from LST-AI==1.0.0) (1.24.3) Requirement already satisfied: pillow in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from LST-AI==1.0.0) (10.2.0) Requirement already satisfied: scipy>=1.9.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from LST-AI==1.0.0) (1.10.1) Requirement already satisfied: scikit-image>=0.21.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from LST-AI==1.0.0) (0.21.0) Requirement already satisfied: tensorflow>=2.13 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from LST-AI==1.0.0) (2.13.1) Requirement already satisfied: nibabel in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from LST-AI==1.0.0) (5.2.0) Requirement already satisfied: requests in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from LST-AI==1.0.0) (2.26.0) Requirement already satisfied: networkx>=2.8 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from scikit-image>=0.21.0->LST-AI==1.0.0) (3.1) Requirement already satisfied: imageio>=2.27 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from scikit-image>=0.21.0->LST-AI==1.0.0) (2.34.0) Requirement already satisfied: tifffile>=2022.8.12 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from scikit-image>=0.21.0->LST-AI==1.0.0) (2023.7.10) Requirement already satisfied: PyWavelets>=1.1.1 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from scikit-image>=0.21.0->LST-AI==1.0.0) (1.4.1) Requirement already satisfied: packaging>=21 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from scikit-image>=0.21.0->LST-AI==1.0.0) (21.0) Requirement already satisfied: lazy_loader>=0.2 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from scikit-image>=0.21.0->LST-AI==1.0.0) (0.3) Requirement already satisfied: absl-py>=1.0.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (2.1.0) Requirement already satisfied: astunparse>=1.6.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (1.6.3) Requirement already satisfied: flatbuffers>=23.1.21 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (23.5.26) Requirement already satisfied: gast<=0.4.0,>=0.2.1 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (0.4.0) Requirement already satisfied: google-pasta>=0.1.1 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (0.2.0) Requirement already satisfied: grpcio<2.0,>=1.24.3 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (1.62.0) Requirement already satisfied: h5py>=2.9.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (3.1.0) Requirement already satisfied: keras<2.14,>=2.13.1 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (2.13.1) Requirement already satisfied: libclang>=13.0.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (16.0.6) Requirement already satisfied: opt-einsum>=2.3.2 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (3.3.0) Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (4.25.3) Requirement already satisfied: setuptools in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (50.3.1.post20201107) Requirement already satisfied: six>=1.12.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (1.15.0) Requirement already satisfied: tensorboard<2.14,>=2.13 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (2.13.0) Requirement already satisfied: tensorflow-estimator<2.14,>=2.13.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (2.13.0) Requirement already satisfied: termcolor>=1.1.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (1.1.0) Requirement already satisfied: typing-extensions<4.6.0,>=3.6.6 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (4.5.0) Requirement already satisfied: wrapt>=1.11.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (1.12.1) Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorflow>=2.13->LST-AI==1.0.0) (0.34.0) Requirement already satisfied: importlib-resources>=1.3 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from nibabel->LST-AI==1.0.0) (6.1.2) Requirement already satisfied: urllib3<1.27,>=1.21.1 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from requests->LST-AI==1.0.0) (1.26.6) Requirement already satisfied: certifi>=2017.4.17 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from requests->LST-AI==1.0.0) (2021.10.8) Requirement already satisfied: charset-normalizer~=2.0.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from requests->LST-AI==1.0.0) (2.0.3) Requirement already satisfied: idna<4,>=2.5 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from requests->LST-AI==1.0.0) (3.2) Requirement already satisfied: wheel<1.0,>=0.23.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from astunparse>=1.6.0->tensorflow>=2.13->LST-AI==1.0.0) (0.35.1) Requirement already satisfied: zipp>=3.1.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from importlib-resources>=1.3->nibabel->LST-AI==1.0.0) (3.6.0) Requirement already satisfied: pyparsing>=2.0.2 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from packaging>=21->scikit-image>=0.21.0->LST-AI==1.0.0) (3.0.4) Requirement already satisfied: google-auth<3,>=1.6.3 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorboard<2.14,>=2.13->tensorflow>=2.13->LST-AI==1.0.0) (2.28.1) Requirement already satisfied: google-auth-oauthlib<1.1,>=0.5 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorboard<2.14,>=2.13->tensorflow>=2.13->LST-AI==1.0.0) (1.0.0) Requirement already satisfied: markdown>=2.6.8 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorboard<2.14,>=2.13->tensorflow>=2.13->LST-AI==1.0.0) (3.3.4) Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorboard<2.14,>=2.13->tensorflow>=2.13->LST-AI==1.0.0) (0.7.2) Requirement already satisfied: werkzeug>=1.0.1 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from tensorboard<2.14,>=2.13->tensorflow>=2.13->LST-AI==1.0.0) (2.0.1) Requirement already satisfied: cachetools<6.0,>=2.0.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from google-auth<3,>=1.6.3->tensorboard<2.14,>=2.13->tensorflow>=2.13->LST-AI==1.0.0) (4.2.2) Requirement already satisfied: pyasn1-modules>=0.2.1 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from google-auth<3,>=1.6.3->tensorboard<2.14,>=2.13->tensorflow>=2.13->LST-AI==1.0.0) (0.2.8) Requirement already satisfied: rsa<5,>=3.1.4 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from google-auth<3,>=1.6.3->tensorboard<2.14,>=2.13->tensorflow>=2.13->LST-AI==1.0.0) (4.7.2) Requirement already satisfied: requests-oauthlib>=0.7.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from google-auth-oauthlib<1.1,>=0.5->tensorboard<2.14,>=2.13->tensorflow>=2.13->LST-AI==1.0.0) (1.3.0) Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.14,>=2.13->tensorflow>=2.13->LST-AI==1.0.0) (0.4.8) Requirement already satisfied: oauthlib>=3.0.0 in /home/xubuntu/anaconda3/envs/py38/lib/python3.8/site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<1.1,>=0.5->tensorboard<2.14,>=2.13->tensorflow>=2.13->LST-AI==1.0.0) (3.1.1) Installing collected packages: LST-AI Running setup.py develop for LST-AI Successfully installed LST-AI-1.0.0 (py38) xubuntu@xubuntu-VirtualBox:~/LST-AI$ cd .. (py38) xubuntu@xubuntu-VirtualBox:~$ lst -h Illegal instruction (core dumped) (py38) xubuntu@xubuntu-VirtualBox:~$

sj-choi commented 6 months ago

I've verified the installation of "HD-BET" and "greedy" using the provided commands as directed, and they appears to be installed without issues. However, I'm encountering an "Illegal Instruction" error message when running "lst."

sj-choi commented 6 months ago

I was unable to determine the solution to the problem I encountered with my VirtualBox virtual machine (VM). While it functions on some VMs, it fails on others. I created additional VMs using VMware, all of which operate smoothly. I'm uncertain as to why all VMware VMs function well, while only a handful of VirtualBox VMs do. It's likely more effective to run LST-AI on native Linux machines rather than on VMs. If, like me, you need to operate LST-AI on a VM, I would advise using VMware instead of VirtualBox.

jqmcginnis commented 6 months ago

@sj-choi Sorry I have been so unresponsive the last two weeks, we had some deadlines to work on. Thank you for reporting back, I am sure this is going to be helpful for other users with VM issues :)