Reference for ultralytics/models/sam/modules/encoders.py

def __init__(
    self,
    img_size: int = 1024,
    patch_size: int = 16,
    in_chans: int = 3,
    embed_dim: int = 768,
    depth: int = 12,
    num_heads: int = 12,
    mlp_ratio: float = 4.0,
    out_chans: int = 256,
    qkv_bias: bool = True,
    norm_layer: Type[nn.Module] = nn.LayerNorm,
    act_layer: Type[nn.Module] = nn.GELU,
    use_abs_pos: bool = True,
    use_rel_pos: bool = False,
    rel_pos_zero_init: bool = True,
    window_size: int = 0,
    global_attn_indexes: Tuple[int, ...] = (),
) -> None:
    """
    Args:
        img_size (int): Input image size.
        patch_size (int): Patch size.
        in_chans (int): Number of input image channels.
        embed_dim (int): Patch embedding dimension.
        depth (int): Depth of ViT.
        num_heads (int): Number of attention heads in each ViT block.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool): If True, add a learnable bias to query, key, value.
        norm_layer (nn.Module): Normalization layer.
        act_layer (nn.Module): Activation layer.
        use_abs_pos (bool): If True, use absolute positional embeddings.
        use_rel_pos (bool): If True, add relative positional embeddings to the attention map.
        rel_pos_zero_init (bool): If True, zero initialize relative positional parameters.
        window_size (int): Window size for window attention blocks.
        global_attn_indexes (list): Indexes for blocks using global attention.
    """
    super().__init__()
    self.img_size = img_size

    self.patch_embed = PatchEmbed(
        kernel_size=(patch_size, patch_size),
        stride=(patch_size, patch_size),
        in_chans=in_chans,
        embed_dim=embed_dim,
    )

    self.pos_embed: Optional[nn.Parameter] = None
    if use_abs_pos:
        # Initialize absolute positional embedding with pretrain image size.
        self.pos_embed = nn.Parameter(torch.zeros(1, img_size // patch_size, img_size // patch_size, embed_dim))

    self.blocks = nn.ModuleList()
    for i in range(depth):
        block = Block(
            dim=embed_dim,
            num_heads=num_heads,
            mlp_ratio=mlp_ratio,
            qkv_bias=qkv_bias,
            norm_layer=norm_layer,
            act_layer=act_layer,
            use_rel_pos=use_rel_pos,
            rel_pos_zero_init=rel_pos_zero_init,
            window_size=window_size if i not in global_attn_indexes else 0,
            input_size=(img_size // patch_size, img_size // patch_size),
        )
        self.blocks.append(block)

    self.neck = nn.Sequential(
        nn.Conv2d(
            embed_dim,
            out_chans,
            kernel_size=1,
            bias=False,
        ),
        LayerNorm2d(out_chans),
        nn.Conv2d(
            out_chans,
            out_chans,
            kernel_size=3,
            padding=1,
            bias=False,
        ),
        LayerNorm2d(out_chans),
    )

def __init__(
    self,
    embed_dim: int,
    image_embedding_size: Tuple[int, int],
    input_image_size: Tuple[int, int],
    mask_in_chans: int,
    activation: Type[nn.Module] = nn.GELU,
) -> None:
    """
    Encodes prompts for input to SAM's mask decoder.

    Args:
      embed_dim (int): The prompts' embedding dimension
      image_embedding_size (tuple(int, int)): The spatial size of the
        image embedding, as (H, W).
      input_image_size (int): The padded size of the image as input
        to the image encoder, as (H, W).
      mask_in_chans (int): The number of hidden channels used for
        encoding input masks.
      activation (nn.Module): The activation to use when encoding
        input masks.
    """
    super().__init__()
    self.embed_dim = embed_dim
    self.input_image_size = input_image_size
    self.image_embedding_size = image_embedding_size
    self.pe_layer = PositionEmbeddingRandom(embed_dim // 2)

    self.num_point_embeddings: int = 4  # pos/neg point + 2 box corners
    point_embeddings = [nn.Embedding(1, embed_dim) for _ in range(self.num_point_embeddings)]
    self.point_embeddings = nn.ModuleList(point_embeddings)
    self.not_a_point_embed = nn.Embedding(1, embed_dim)

    self.mask_input_size = (4 * image_embedding_size[0], 4 * image_embedding_size[1])
    self.mask_downscaling = nn.Sequential(
        nn.Conv2d(1, mask_in_chans // 4, kernel_size=2, stride=2),
        LayerNorm2d(mask_in_chans // 4),
        activation(),
        nn.Conv2d(mask_in_chans // 4, mask_in_chans, kernel_size=2, stride=2),
        LayerNorm2d(mask_in_chans),
        activation(),
        nn.Conv2d(mask_in_chans, embed_dim, kernel_size=1),
    )
    self.no_mask_embed = nn.Embedding(1, embed_dim)

def __init__(self, num_pos_feats: int = 64, scale: Optional[float] = None) -> None:
    """Initializes a position embedding using random spatial frequencies."""
    super().__init__()
    if scale is None or scale <= 0.0:
        scale = 1.0
    self.register_buffer("positional_encoding_gaussian_matrix", scale * torch.randn((2, num_pos_feats)))

    # Set non-deterministic for forward() error 'cumsum_cuda_kernel does not have a deterministic implementation'
    torch.use_deterministic_algorithms(False)
    torch.backends.cudnn.deterministic = False

def __init__(
    self,
    dim: int,
    num_heads: int,
    mlp_ratio: float = 4.0,
    qkv_bias: bool = True,
    norm_layer: Type[nn.Module] = nn.LayerNorm,
    act_layer: Type[nn.Module] = nn.GELU,
    use_rel_pos: bool = False,
    rel_pos_zero_init: bool = True,
    window_size: int = 0,
    input_size: Optional[Tuple[int, int]] = None,
) -> None:
    """
    Args:
        dim (int): Number of input channels.
        num_heads (int): Number of attention heads in each ViT block.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool): If True, add a learnable bias to query, key, value.
        norm_layer (nn.Module): Normalization layer.
        act_layer (nn.Module): Activation layer.
        use_rel_pos (bool): If True, add relative positional embeddings to the attention map.
        rel_pos_zero_init (bool): If True, zero initialize relative positional parameters.
        window_size (int): Window size for window attention blocks. If it equals 0, then
            use global attention.
        input_size (tuple(int, int), None): Input resolution for calculating the relative
            positional parameter size.
    """
    super().__init__()
    self.norm1 = norm_layer(dim)
    self.attn = Attention(
        dim,
        num_heads=num_heads,
        qkv_bias=qkv_bias,
        use_rel_pos=use_rel_pos,
        rel_pos_zero_init=rel_pos_zero_init,
        input_size=input_size if window_size == 0 else (window_size, window_size),
    )

    self.norm2 = norm_layer(dim)
    self.mlp = MLPBlock(embedding_dim=dim, mlp_dim=int(dim * mlp_ratio), act=act_layer)

    self.window_size = window_size

def __init__(
    self,
    dim: int,
    num_heads: int = 8,
    qkv_bias: bool = True,
    use_rel_pos: bool = False,
    rel_pos_zero_init: bool = True,
    input_size: Optional[Tuple[int, int]] = None,
) -> None:
    """
    Initialize Attention module.

    Args:
        dim (int): Number of input channels.
        num_heads (int): Number of attention heads.
        qkv_bias (bool):  If True, add a learnable bias to query, key, value.
        rel_pos_zero_init (bool): If True, zero initialize relative positional parameters.
        input_size (tuple(int, int), None): Input resolution for calculating the relative
            positional parameter size.
    """
    super().__init__()
    self.num_heads = num_heads
    head_dim = dim // num_heads
    self.scale = head_dim**-0.5

    self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
    self.proj = nn.Linear(dim, dim)

    self.use_rel_pos = use_rel_pos
    if self.use_rel_pos:
        assert input_size is not None, "Input size must be provided if using relative positional encoding."
        # Initialize relative positional embeddings
        self.rel_pos_h = nn.Parameter(torch.zeros(2 * input_size[0] - 1, head_dim))
        self.rel_pos_w = nn.Parameter(torch.zeros(2 * input_size[1] - 1, head_dim))

def __init__(
    self,
    kernel_size: Tuple[int, int] = (16, 16),
    stride: Tuple[int, int] = (16, 16),
    padding: Tuple[int, int] = (0, 0),
    in_chans: int = 3,
    embed_dim: int = 768,
) -> None:
    """
    Initialize PatchEmbed module.

    Args:
        kernel_size (Tuple): kernel size of the projection layer.
        stride (Tuple): stride of the projection layer.
        padding (Tuple): padding size of the projection layer.
        in_chans (int): Number of input image channels.
        embed_dim (int): Patch embedding dimension.
    """
    super().__init__()

    self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=kernel_size, stride=stride, padding=padding)