Class SelfAtt module includes a MultiHeadAttention module. In its forward function, the self.mhatt receives 6 parameters (q, k, values, relative_geometry_weights, attention_mask, attention_weights). However, there are 5 parameters in MultiHeadAttention's forward function (queries, keys, values,box_relation_embed_matrix, attention_mask, attention_weights). Is this an error? Should it replace MultiHeadAttention with MultiHeadBoxAttention?
Class SelfAtt module includes a MultiHeadAttention module. In its forward function, the self.mhatt receives 6 parameters (q, k, values, relative_geometry_weights, attention_mask, attention_weights). However, there are 5 parameters in MultiHeadAttention's forward function (queries, keys, values,box_relation_embed_matrix, attention_mask, attention_weights). Is this an error? Should it replace MultiHeadAttention with MultiHeadBoxAttention?