FPh+ddlZddlmZmZddlZddlmZmZddlmZGddejZ GddejZ Gd d ejZ y) N)TupleType)Tensornn)MLPBlockceZdZdZej dfdededededeejded d ffd Z d e d e de d e e e ffdZ xZ S)TwoWayTransformera A Two-Way Transformer module that enables the simultaneous attention to both image and query points. This class serves as a specialized transformer decoder that attends to an input image using queries whose positional embedding is supplied. This is particularly useful for tasks like object detection, image segmentation, and point cloud processing. Attributes: depth (int): The number of layers in the transformer. embedding_dim (int): The channel dimension for the input embeddings. num_heads (int): The number of heads for multihead attention. mlp_dim (int): The internal channel dimension for the MLP block. layers (nn.ModuleList): The list of TwoWayAttentionBlock layers that make up the transformer. final_attn_token_to_image (Attention): The final attention layer applied from the queries to the image. norm_final_attn (nn.LayerNorm): The layer normalization applied to the final queries. depth embedding_dim num_headsmlp_dim activationattention_downsample_ratereturnNc `t|||_||_||_||_t j|_t|D]/}|jjt||||||dk(1t||||_ t j||_y)a A transformer decoder that attends to an input image using queries whose positional embedding is supplied. Args: depth (int): number of layers in the transformer embedding_dim (int): the channel dimension for the input embeddings num_heads (int): the number of heads for multihead attention. Must divide embedding_dim mlp_dim (int): the channel dimension internal to the MLP block activation (nn.Module): the activation to use in the MLP block r)r r rrrskip_first_layer_pedownsample_rateN)super__init__r r r rr ModuleListlayersrangeappendTwoWayAttentionBlock Attentionfinal_attn_token_to_image LayerNormnorm_final_attn) selfr r r rrri __class__s uC:\Users\daisl\Desktop\realtime-object-detection\venv\Lib\site-packages\ultralytics/models/sam/modules/transformer.pyrzTwoWayTransformer.__init__s(  *" mmo uA KK  $"/'#).G)*a  *3=)]v)w&!||M:image_embeddingimage_pepoint_embeddingcd|j\}}}}|jdjddd}|jdjddd}|}|} |jD]} | || ||\}} ||z} | |z} |j | | | } || z}|j |}|| fS)a* Args: image_embedding (torch.Tensor): image to attend to. Should be shape B x embedding_dim x h x w for any h and w. image_pe (torch.Tensor): the positional encoding to add to the image. Must have same shape as image_embedding. point_embedding (torch.Tensor): the embedding to add to the query points. Must have shape B x N_points x embedding_dim for any N_points. Returns: (torch.Tensor): the processed point_embedding (torch.Tensor): the processed image_embedding r r)querieskeysquery_pekey_peqkv)shapeflattenpermuterrr )r!r&r'r(bschwr+r,layerr0r1attn_outs r$forwardzTwoWayTransformer.forwardFs$&++ Aq!)11!4<