I have a problem with MonaiBundle. I just started trying to use the models from the Monailabel Zoo through the MonaiBundle app. When I click on ‘run’ in ‘auto segmentation,’ I get the following error message: ‘Failed to run inference in MONAI Label Server. Message: Status: 500; Response: Internal Server Error’
Traceback (most recent call last): File “C:/Users/franb/AppData/Local/slicer.org/Slicer 5.4.0/slicer.org/Extensions-31938/MONAILabel/lib/Slicer-5.4/qt-scripted-modules/MONAILabel.py”, line 1524, in onClickSegmentation result_file, params = self.logic.infer(model, image_file, params, session_id=self.getSessionId()) File “C:/Users/franb/AppData/Local/slicer.org/Slicer 5.4.0/slicer.org/Extensions-31938/MONAILabel/lib/Slicer-5.4/qt-scripted-modules/MONAILabel.py”, line 2296, in infer result_file, params = client.infer(model, image_in, params, label_in, file, session_id) File “C:\Users\franb\AppData\Local\slicer.org\Slicer 5.4.0\slicer.org\Extensions-31938\MONAILabel\lib\Slicer-5.4\qt-scripted-modules\MONAILabelLib\client.py”, line 344, in infer raise MONAILabelClientException(MONAILabelLib.client.MONAILabelClientException: (1, ‘Status: 500; Response: Internal Server Error’)
I tried to install MONAI 1.20.rc6, but it seems like this version doesn’t exist. I couldn’t find it during the installation attempt, and I received the following message in the terminal.
Hi Professor, I just followed the instructions of this article to set up monaibundle and it works like a charm. I am using the command monailabel start_server --app apps/monaibundle --studies Desktop --conf models lung_nodule_ct_detection to start the server and can produce satisfactory results. May I know what is the purpose of Setting up an AWS EC2 Windows server in the cloud?
I am using the LIDC-IDRI dataset to do the lung nodule segmentation and the right hand side the ground truth label while the left side is the label produced by monai zoo model
If you want to get segmentation results quickly and you don’t want to buy a computer that has a GPU then you can rent virtual machines from AWS or other cloud providers. If you already have a computer with a good GPU then this is not necessary.
