beomus

/

layoutxlm

like 1

Hi @beomus !

I'm trying to create a Spanish finetuned version of layouxlm for token classification, like you did for Japanese. Even though the data seems correclty pre-processed, I get a "ValueError: cannot reshape array of size 1908 into shape (1,512,4)" when attempting train the layoutxlm-base model with this data.

I'm struggling to find examples on how to fine-tune this model. Would you mind to share with me how you did it?

Thank you very much in advance.