espnet.nets.pytorch_backend.rnn.attentions.AttAdd

source

class espnet.nets.pytorch_backend.rnn.attentions.AttAdd(eprojs, dunits, att_dim, han_mode=False)

Bases: Module

Additive attention

• Parameters:
  • eprojs (int) – # projection-units of encoder
  • dunits (int) – # units of decoder
  • att_dim (int) – attention dimension
  • han_mode (bool) – flag to swith on mode of hierarchical attention and not store pre_compute_enc_h

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(enc_hs_pad, enc_hs_len, dec_z, att_prev, scaling=2.0)

AttAdd forward

• Parameters:
  • enc_hs_pad (torch.Tensor) – padded encoder hidden state (B x T_max x D_enc)
  • enc_hs_len (list) – padded encoder hidden state length (B)
  • dec_z (torch.Tensor) – decoder hidden state (B x D_dec)
  • att_prev (torch.Tensor) – dummy (does not use)
  • scaling (float) – scaling parameter before applying softmax
• Returns: attention weighted encoder state (B, D_enc)
• Return type: torch.Tensor
• Returns: previous attention weights (B x T_max)
• Return type: torch.Tensor

reset()

reset states