About 'Mix Embedding' in paper.
lcxrocks opened this issue · comments
Chauncey commented
In your paper, you mentioned that you 'add two mix embeddings to the visual tokens to implicitly differentiate the two mixing groups' and 'use different mix embeddings for the 4 stages of the encoder', which is in section 2.3. However, it appears to me that there isn't such mix embedding in the function forward_encoder
of models_mixmim.py
. So, if it's my silly mistake that I didn't find it, would you kindly point it out to me? Thanks!