ISubGVQA.models.question_decoder

Classes

QuestionDecoder

Module Contents

class ISubGVQA.models.question_decoder.QuestionDecoder(n_instructions, ninp, nhead, nhid, nlayers, dropout=0.1)

Bases: torch.nn.Module

model_type = 'Transformer'

num_queries

query_embed

coarse_decoder

generate_square_subsequent_mask(sz): Generate a square mask for the sequence. The masked positions are filled with float(‘-inf’). Unmasked positions are filled with float(0.0). https://pytorch.org/docs/stable/_modules/torch/nn/modules/transformer.html#Transformer.generate_square_subsequent_mask

forward(memory)