Hi, I noticed that the provided Docker command is set up to map the results file using the -v option. docker run --gpus all -v ./results:/App_mlcube/results my_image:latest However, it seems like there's something missing. The command maps the output directory to obtain the prediction results, but what about the input file mapping? Shouldn't there be another -v option to map the input data directory into the Docker container? This command only maps the results directory. Shouldn't we also include something like this for the input data?

Created by Mengye Lyu mylyu
Hi Mengye, The command lines provided were just examples, as mentioned here (https://www.synapse.org/Synapse:syn55249552/wiki/627701). You can specify your input data using a different argument, such as: docker run --gpus all -v ./data/Testingdata:/Appmlcube/data/Testingdata -v ./results/segpred:/Appmlcube/results/segpred myimage Thank you, Kind Regards, LISA 2024 Challenge Organizers

Clarifying Docker Commands for Input and Output File Mapping page is loading…