18 Jan
2022
18 Jan
'22
10:53 p.m.
so a perceiver model is: input -> preprocessor -> encoder [required] -> decoder [processes encoded and unencoded input together] -> postprocessor -> output let's see how the encoder is constructed in PerceiverModel.__init__: self.embeddings = PerceiverEmbeddings() self.encoder = PerceiverEncoder(kv_dim) So most of the functionality of a perceiver model is in the PerceiverEncoder class.