Timothée Lesort

Hi @ranarag , Thanks for you PR ! :) Sorry for not looking at your PR earlier. If I understand correctly you want to reproduce an existing scenario from 'https://github.com/GT-RIPL/CODA-Prompt'...

Hi @Areeb2735 , thanks for your question. We do not remap the class values in class incremental, but we usually extend the output layer size. You can use the loss...

Hi @kirk86 , Thanks for the issue. > --> here should it be taskset or dataset_train? I would do it based on `dataset_val` to avoid overfitting when sampling. But it...

I think using the flag --help might be the more intuitive solution. I don't know how easy it is achievable but it could work like this: `sequoia --help` displays all...

I don't know what is possible to do with the `simple_parsing` lib but I think that `argparse` library might do all of this