Class TransformerDecoder

semantic_sam/body/transformer_blocks.py:105–151

class TransformerDecoder(nn.Module):
    def __init__(self, decoder_layer, num_layers, norm=None, return_intermediate=False):
        super().__init__()
        self.layers = _get_clones(decoder_layer, num_layers)
        self.num_layers = num_layers
        self.norm = norm
        self.return_intermediate = return_intermediate

    def forward(
        self,
        tgt,
        memory,
        tgt_mask: Optional[Tensor] = None,
        memory_mask: Optional[Tensor] = None,
        tgt_key_padding_mask: Optional[Tensor] = None,
        memory_key_padding_mask: Optional[Tensor] = None,
        pos: Optional[Tensor] = None,
        query_pos: Optional[Tensor] = None,
    ):
        output = tgt

        intermediate = []

        for layer in self.layers:
            output = layer(
                output,
                memory,
                tgt_mask=tgt_mask,
                memory_mask=memory_mask,
                tgt_key_padding_mask=tgt_key_padding_mask,
                memory_key_padding_mask=memory_key_padding_mask,
                pos=pos,
                query_pos=query_pos,
            )
            if self.return_intermediate:
                intermediate.append(self.norm(output))

        if self.norm is not None:
            output = self.norm(output)
            if self.return_intermediate:
                intermediate.pop()
                intermediate.append(output)

        if self.return_intermediate:
            return torch.stack(intermediate)

        return output.unsqueeze(0)


class TransformerEncoderLayer(nn.Module):