Method forward

detrsmpl/models/utils/transformer.py:308–353

Forward function for `Transformer`. Args: x (Tensor): Input query with shape [bs, c, h, w] where c = embed_dims. mask (Tensor): The key_padding_mask used for encoder and decoder, with shape [bs, h, w]. query_embed (Tensor):

(self, x, mask, query_embed, pos_embed)

        self._is_init = True

    def forward(self, x, mask, query_embed, pos_embed):
        """Forward function for `Transformer`.

        Args:
            x (Tensor): Input query with shape [bs, c, h, w] where
                c = embed_dims.
            mask (Tensor): The key_padding_mask used for encoder and decoder,
                with shape [bs, h, w].
            query_embed (Tensor): The query embedding for decoder, with shape
                [num_query, c].
            pos_embed (Tensor): The positional encoding for encoder and
                decoder, with the same shape as `x`.

        Returns:
            tuple[Tensor]: results of decoder containing the following tensor.

                - out_dec: Output from decoder. If return_intermediate_dec \
                      is True output has shape [num_dec_layers, bs,
                      num_query, embed_dims], else has shape [1, bs, \
                      num_query, embed_dims].
                - memory: Output results from encoder, with shape \
                      [bs, embed_dims, h, w].
        """
        bs, c, h, w = x.shape
        # use `view` instead of `flatten` for dynamically exporting to ONNX
        x = x.view(bs, c, -1).permute(2, 0, 1)  # [bs, c, h, w] -> [h*w, bs, c]
        pos_embed = pos_embed.view(bs, c, -1).permute(2, 0, 1)
        query_embed = query_embed.unsqueeze(1).repeat(
            1, bs, 1)  # [num_query, dim] -> [num_query, bs, dim]
        mask = mask.view(bs, -1)  # [bs, h, w] -> [bs, h*w]
        memory = self.encoder(query=x,
                              key=None,
                              value=None,
                              query_pos=pos_embed,
                              query_key_padding_mask=mask)
        target = torch.zeros_like(query_embed)
        # out_dec: [num_layers, num_query, bs, dim]
        out_dec = self.decoder(query=target,
                               key=memory,
                               value=memory,
                               key_pos=pos_embed,
                               query_pos=query_embed,
                               key_padding_mask=mask)
        out_dec = out_dec.transpose(1, 2)
        memory = memory.permute(1, 2, 0).reshape(bs, c, h, w)
        return out_dec, memory


@TRANSFORMER.register_module()