r""" Norm layer modified to incorporate arbitrary continuous embeddings. Parameters: embedding_dim (`int`): The size of each embeddin

r""" Norm layer modified to incorporate timestep embeddings. Parameters: embedding_dim (`int`): The size of each embedding vector.

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Construct the CLS token, mask token, position and patch embeddings.

r""" A feed-forward layer. Parameters: dim (`int`): The number of channels in the input. dim_out (`int`, *optional*): The num

r""" GELU activation function with tanh approximation support with `approximate="tanh"`. Parameters: dim_in (`int`): The number of ch

r""" Norm layer adaptive layer norm zero (adaLN-Zero). Parameters: embedding_dim (`int`): The size of each embedding vector.

r""" The approximate form of Gaussian Error Linear Unit (GELU). For more details, see section 2: https://arxiv.org/abs/1606.08415. Parame

r""" A basic Transformer block. Parameters: dim (`int`): The number of channels in the input and output. num_attention_heads

This class turns `pixel_values` of shape `(batch_size, num_channels, height, width)` into the initial `hidden_states` (patch embeddings) of s

This corresponds to the Block class in the original implementation.

This class turns `pixel_values` of shape `(batch_size, num_channels, height, width)` into the initial `hidden_states` (patch embeddings) of s

The residual connection is defined in Dinov2Layer instead of here (as is the case with other models), due to the layernorm applied before eac

r""" A variant of the gated linear unit activation function from https://arxiv.org/abs/2002.05202. Parameters: dim_in (`int`): The nu

r""" A gated self-attention dense layer that combines visual features and object features. Parameters: query_dim (`int`): The number

Fully connected ResNet Block class. Args: size_in (int): input dimension size_out (int): output dimension size_h (int):

A generalized nn.Sequential container for normalizing flows.

r""" GroupNorm layer modified to incorporate timestep embeddings. Parameters: embedding_dim (`int`): The size of each embedding vecto

Construct the CLS token, mask token, position and patch embeddings.

An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.

r""" Groups all features Parameters ---------

PointNet-based encoder network with ResNet blocks for each point. Number of input points are fixed. Args: c_dim (int): dimen

r"""Propigates the features of one set to another Parameters ---------- mlp : list Pointnet module parameters bn : bool

r"""Pointnet set abstrction layer Parameters ---------- npoint : int Number of features radius : float Radius of ball

r"""Pointnet set abstrction layer with multiscale grouping Parameters ---------- npoint : int Number of features radii : list

r""" Groups with a ball query of radius Parameters --------- radius : float32 Radius of ball nsample : int32 Maxi

apply PC^2 / PCL token to decoder