I’m trying to use fast.ai’s training loop and all utilities on problem where I have pretrained embeddings (trained using StarSpace model) for some entities and labels that I want to predict. The input is a table with two columns: embedding vector | label
I’m wondering what’s the most natural way to fit such data into fast.ai. In particular, should I treat embedding as an input (essentially a single feature) to the model or should I incorporate embeddings directly into the model (and set them to be frozen) and have only embedding index as an input?
I tried feeding embedding vectors as inputs (stored in Pandas dataframe) but I ran into issues with numpy -> tensor conversion somewhere deep in the ItemList/Databunch code. I’m wondering if I’m climbing the wrong hill here.