| 80 | |
| 81 | class DecoderLayer(nn.Module): |
| 82 | def __init__(self, self_attention, cross_attention, d_model, d_ff=None, |
| 83 | dropout=0.1, activation="relu"): |
| 84 | super(DecoderLayer, self).__init__() |
| 85 | d_ff = d_ff or 4 * d_model |
| 86 | self.self_attention = self_attention |
| 87 | self.cross_attention = cross_attention |
| 88 | self.conv1 = nn.Conv1d(in_channels=d_model, out_channels=d_ff, kernel_size=1) |
| 89 | self.conv2 = nn.Conv1d(in_channels=d_ff, out_channels=d_model, kernel_size=1) |
| 90 | self.norm1 = nn.LayerNorm(d_model) |
| 91 | self.norm2 = nn.LayerNorm(d_model) |
| 92 | self.norm3 = nn.LayerNorm(d_model) |
| 93 | self.dropout = nn.Dropout(dropout) |
| 94 | self.activation = F.relu if activation == "relu" else F.gelu |
| 95 | |
| 96 | def forward(self, x, cross, x_mask=None, cross_mask=None): |
| 97 | x = x + self.dropout(self.self_attention( |