search

georgian-io / Multimodal-Toolkit

Multimodal model for text and tabular data with HuggingFace transformers as building block for text data
https://multimodal-toolkit.readthedocs.io
Apache License 2.0
587 stars 84 forks source link

No category embedding? #5

Closed wangbingnan136 closed 1 year ago

wangbingnan136 commented 3 years ago

I found that the multimodal-toolkit do not have embedding,it just use onehot encoding to deal with category,which leading to the too high dimension and caused memory error.If any one can help??

akashsaravanan-georgian commented 1 year ago

You can try using the Label encoding option (set encoding_type="label").