[spam] [personal] perceiver model notes
k
gmkarl at gmail.com
Tue Jan 18 05:46:59 PST 2022
forward function of perceivermodel, when conditioned with only
input_preprocessor and decoder, pseudocode:
# step 1
inputs and dimension info = input_preprocessor(inputs)
# step 2
encoder_outputs = self.encoder(
self.embeddings(batch_size)
inputs
)
# step 3
decoder_outputs = decoder(
decoder.decoder_query(inputs),
z=encoder_outputs[0]
)
# logits would be additionally processed through output_postprocessor
if one were provided
return decoder_outputs.logits
More information about the cypherpunks
mailing list