| 51 | |
| 52 | |
| 53 | class Encoder(nn.Module): |
| 54 | def __init__(self, attn_layers, conv_layers=None, norm_layer=None): |
| 55 | super(Encoder, self).__init__() |
| 56 | self.attn_layers = nn.ModuleList(attn_layers) |
| 57 | self.conv_layers = nn.ModuleList(conv_layers) if conv_layers is not None else None |
| 58 | self.norm = norm_layer |
| 59 | |
| 60 | def forward(self, x, attn_mask=None): |
| 61 | # x [B, L, D] |
| 62 | attns = [] |
| 63 | if self.conv_layers is not None: |
| 64 | for attn_layer, conv_layer in zip(self.attn_layers, self.conv_layers): |
| 65 | x, attn = attn_layer(x, attn_mask=attn_mask) |
| 66 | x = conv_layer(x) |
| 67 | attns.append(attn) |
| 68 | x, attn = self.attn_layers[-1](x) |
| 69 | attns.append(attn) |
| 70 | else: |
| 71 | for attn_layer in self.attn_layers: |
| 72 | x, attn = attn_layer(x, attn_mask=attn_mask) |
| 73 | attns.append(attn) |
| 74 | |
| 75 | if self.norm is not None: |
| 76 | x = self.norm(x) |
| 77 | |
| 78 | return x, attns |
| 79 | |
| 80 | |
| 81 | class DecoderLayer(nn.Module): |