Input and output folders in submission

I have a question about input and output folders during submission. Should I create them like what they are in the local inference folder and include them in the container? There is no problem when I do test in my local environment, but after submission, it always exposes the error that fails in one or multiple cases. Therefore, I am not sure whether the data is read correctly and implemented by model. Thanks

You don't need to create the input and output folders when preparing the Docker image for submission. Instead, follow the guidelines and directory structure outlined here. Additionally, do not use the inference file you use for local testing. Instead, use the inference file provided here.