search

EGO4D / episodic-memory

MIT License
108 stars 60 forks source link

Add SentenceTransformer to NLQ #26

Open miguelmartin75 opened 2 years ago

miguelmartin75 commented 2 years ago

Caveat: since SentenceTransformer reduces the input features from [B, T] -> [B, 768], I don't pass the token embeddings to the shared feature_encoder

satwikkottur commented 2 years ago

Thanks @miguelmartin75 for this PR.

Two comments:

  1. Can we have choices for --predictor flag in options.py? Since we're adding addition predictors, would be nice to restrict that set.
  2. Between st and sentence_transformer (or even sent_transformer), I prefer the latter for readability. Thoughts?