ml-jku / DeepRC

DeepRC: Immune repertoire classification with attention-based deep massive multiple instance learning

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Datasets issue (?)

MathiasHilfiker opened this issue · comments

commented

I'm trying to run the examples as in README, but I continue getting the error:

KeyError: "Samples ['' '' '' ... '' '' ''] could not be found in hdf5 file. Please add the samples and re-create the hdf5 file or remove the sample keys from the used samples of the metadata file."

This happens with all the datasets I tried in the "Training DeepRC on pre-defined datasets" section. Instead, when I try running the code in the "Training DeepRC on a custom dataset" section, on the example dataset deeprc/datasets/example_dataset, I get:

ValueError: not enough values to unpack (expected 6, got 0)

The versions of the libraries I'm using are the same as yours, what am I missing?

Me too. Did you find a solution yourself?

commented

I solved the first problem by installing the older version (261d2b6).
Instead, for the second error, I haven't still found a solution

Hi! Thanks for the notice!

Regarding KeyError: "Samples ['' '' '' ... '' '' ''] could not be found in hdf5 file: As advised via email, please use the older version for now. Either the latest release v.0.0.5 or the corresponding commit 261d2b6 should work. I will fix this in a new release as soon as I have time but it might take a bit. You can install the release version using pip3 install --no-dependencies https://github.com/ml-jku/DeepRC/archive/refs/tags/v0.0.5.tar.gz or pip3 install https://github.com/ml-jku/DeepRC/archive/refs/tags/v0.0.5.tar.gz.

Regarding the second error: Is this the ValueError? Could you please open a separate issue with a more detailed description of the program output/error message @MathiasHilfiker ? It seems to be not related to the KeyError, if I understood correctly?