Can you provide a pre-trained model for testing?

[anubisthetyrant]

Need a pre-trained model.

[vanossj]

Thanks for your interest. The model was released on MHub.ai. I have updated the README

[anubis-tyrant]

Any idea why it gets stuck in here?

1. DicomImporter (0:00) 1/1
2. NiftiConverter (0:03) 1/1
3. NNUnetRunner [ ] 0/1 eta ~?
4. BamfProcessorRunner
5. DsegConverter
6. DataOrganizer

Always gets stuck in the 3rd portion, and does not show any progress. Waited for 2 hours.
What is it doing?

[vanossj]

Hmmm, I'm running into the same thing. @jithenece can you take a look?

Here's my code:
Downloaded an example CT scan from the TCGA-KIRC using idc-index

from idc_index import index
from pathlib import Path

Path("example_data").mkdir(exist_ok=True)

client = index.IDCClient()
client.download_from_selection(
    seriesInstanceUID=["1.3.6.1.4.1.14519.5.2.1.6450.4004.318185778053926832345567953536"],
    downloadDir="example_data",
)

Then ran the docker container with the following command

mkdir example_output
export in=$(pwd)/example_data
export out=$(pwd)/example_output

docker run --rm -t --gpus all -v $in:/app/data/input_data -v $out:/app/data/output_data mhubai/bamf_nnunet_ct_kidney

[vanossj]

For the previous example, that would finish in about 10 minutes, but not produce output because of a different issue (referenced).

This example below runs successfully. If you are having issues, try running mhub with the --stop-on-error and --print flags and post them here.

Download example series

from idc_index import index
from pathlib import Path

Path("example_data").mkdir(exist_ok=True)

client = index.IDCClient()
client.download_from_selection(
    seriesInstanceUID=["1.3.6.1.4.1.14519.5.2.1.6450.4004.318185778053926832345567953536"],
    downloadDir="example_data",
)

run container

mkdir example_output
export in=$(pwd)/example_data
export out=$(pwd)/example_output

docker run --rm -t --gpus all -v $in:/app/data/input_data -v $out:/app/data/output_data mhubai/bamf_nnunet_ct_kidney