Patch divisibility logic fails when unique patch size value is same as check value about gandlf HOT 9 CLOSED

Thanks for the question, @smcch! Can you provide your configuration file?

from gandlf.

model.zip

from gandlf.

I think I isolated the problem. Can you please try with patch size of [32,32,32] to see if training begins? I'll put a PR with fix soon.

from gandlf.

log.txt

Now I get this error.... Thanks a lot !

from gandlf.

Hey, the model should still be generated. Can you check the output folder?

from gandlf.

This is my folder structure:

/experiment_1/
data_dir/
model_dir/
output_dir/
model.yaml
train.csv

the command line:
python gandlf_run -c ./experiment_1/model.yaml -i ./experiment_1/train.csv -m ./experiment_1/model_dir/ -t True -d cuda

from gandlf.

What is present in the model_dir and output_dir?

from gandlf.

model_dir:

• data_testing.pkl
• data_trainAndVal.pkl
• data_training.csv
• data_training.pkl
• data_validation.csv
• data_validation.pkl
• densenet_best.onnx
• densenet_best.pth
• logs_testing.csv
• logs_training.csv
• logs_validation.csv
• output_testing/
• output_validation/
• parameters.pkl

output_dir is empty

from gandlf.

• densenet_best.onnx
• densenet_best.pth

These are your models, which seem to be generated as expected. Closing this issue, please open a new one in case you are having problems. All the best!

from gandlf.