| | |
|---|
| | | return x, tgt_mask, x_self_attn, x_src_attn |
|---|
| | | |
|---|
| | | |
|---|
| | | class ContexutalBiasDecoder(nn.Module): |
|---|
| | | class ContextualBiasDecoder(nn.Module): |
|---|
| | | def __init__( |
|---|
| | | self, |
|---|
| | | size, |
|---|
| | |
|---|
| | | normalize_before=True, |
|---|
| | | ): |
|---|
| | | """Construct an DecoderLayer object.""" |
|---|
| | | super(ContexutalBiasDecoder, self).__init__() |
|---|
| | | super(ContextualBiasDecoder, self).__init__() |
|---|
| | | self.size = size |
|---|
| | | self.src_attn = src_attn |
|---|
| | | if src_attn is not None: |
|---|
| | |
|---|
| | | ), |
|---|
| | | ) |
|---|
| | | self.dropout = nn.Dropout(dropout_rate) |
|---|
| | | self.bias_decoder = ContexutalBiasDecoder( |
|---|
| | | self.bias_decoder = ContextualBiasDecoder( |
|---|
| | | size=attention_dim, |
|---|
| | | src_attn=MultiHeadedAttentionCrossAtt( |
|---|
| | | attention_heads, attention_dim, src_attention_dropout_rate |
|---|
