mead-ml / mead-baseline

Deep-Learning Model Exploration and Development for NLP
Apache License 2.0
243 stars 73 forks source link

minor mod to support loading all features #913

Closed dpressel closed 2 years ago

dpressel commented 2 years ago

there is a potential issue with this approach, having to do with lengths of the models. If there are multiple vectors with different lengths, this could be an issue, or if there are any scalars. A simple way to handle this should be to use the "primary feature" but its not clear if thats being preserved here. for now its coded like it is