r""" Reshape the tensor from `[batch_size, seq_len, dim]` to `[batch_size, seq_len, heads, dim // heads]` `heads` is the number of hea

Apply rotary embeddings to input tensors using the given frequency tensor. This function applies rotary embeddings to the given query or key

r""" Prepare the attention mask for the attention computation. Args: attention_mask (`torch.Tensor`): The

r""" Normalize the encoder hidden states. Requires `self.norm_cross` to be specified when constructing the `Attention` class.

r""" Reshape the tensor from `[batch_size, seq_len, dim]` to `[batch_size // heads, seq_len, dim * heads]`. `heads` is the number of h

r""" Encode a batch of images into latents. Args: x (`torch.Tensor`): Input batch of images. return_dict (`bo

Precompute the frequency tensor for complex exponentials (cis) with given dimensions. This function calculates a frequency tensor with compl

xyz can be (B T N 3) or (B T 3 H W) or (B N 3)

xyz can be (B T N 3) or (B T 3 H W) or (B N 3)

r""" Compute the attention scores. Args: query (`torch.Tensor`): The query tensor. key (`torch.Tensor`): The

Args: filepath (str): a string that contains the absolute path, including the file name, where the visualized ima

Wrapper for grid_sample, uses pixel coordinates

r"""Sample spatio-temporal features `sample_features5d(input, coords)` works in the same way as :func:`sample_features4d` but for spatio-temp

r""" Set the attention processor to use. Args: processor (`AttnProcessor`): The attention processor to us

Depending on the brightness_factor, gives a lighter or darker color i.e. a color with less or more saturation than the original color

logits: Tensor of arbitrary shape targets: same shape as logits balance_weight: scaling the loss reduction: 'mean', 'sum', or 'none'

Generate a bivariate isotropic or anisotropic Gaussian kernel. In the isotropic mode, only `sig_x` is used. `sig_y` and `theta` is ignored. Ar

Unproject a depth map to a point cloud in COLMAP convention. Args: metric_depth: (B, H, W) depth map, meters. intrinsics:

RoPE for video tokens with 3D structure. Args: embed_dim: (`int`): The embedding dimension size, corresponding to hidden_size_he

Cat x with a positional encoding of x with scales 2^[min_deg, max_deg-1]. Instead of computing [sin(x), cos(x)], we use the trig identity cos

This function will generate tracks by camera transform Args: queries: B T N 4 c2w_traj: B T 4 4

r"""Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distributi

If trunc is None, solve `min sum_i w_i * |a * x_i - y_i|`, otherwise solve `min sum_i min(trunc, w_i * |a * x_i - y_i|)`. w_i must be >=

This function will generate tracks by camera transform Args: queries: B T N 3 scale_est: 1 1 shi

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

Args: classes (list[int] or None): scores (list[float] or None): class_names (list[str] or None): is_crowd (list[

Args: x_data (list[int]): a list containing x values of all the points being drawn. Length of list should match t

Args: text (str): class label position (tuple): a tuple of the x and y coordinates to place text on image.

r""" Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in sev

r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and en

This function generates 1D positional embeddings from a grid. Args: embed_dim (`int`): The embedding dimension `D` pos (`tor

This function is used to get the points on the grid args: H: the height of the grid. W: the width of the grid. T: the

Args: rgb (bool): whether to return RGB colors or BGR colors. maximum (int): either 255 or 1 Returns: ndarray: a vect

Compute the bounding boxes around the provided masks The masks should be in format [N, H, W] where N is the number of masks, (H, W) are the spatia

Args: pose_encoding: A tensor of shape `BxNxC`, containing a batch of `BxN` `C`-dimensional pose encodings.

Scatter the minimum value along the given dimension of `input` into `src` at the indices specified in `index`.

NOTE: this interface is experimental. Args: input_shape: shapes (channels and stride) of the input features t

Implementation of the forward pass through the DPT head. This method processes a specific chunk of frames from the sequence.

Return an activation function given a string

Return an activation function given a string

Apply basic activation function to pose parameters. Args: pose_enc: Tensor containing encoded pose parameters act_type: Acti

r"""Sample a tensor using bilinear interpolation `bilinear_sampler(input, coords)` samples a tensor :attr:`input` at coordinates :attr:`coord

This function generates 1D positional embeddings from a grid. Args: embed_dim (`int`): The embedding dimension `D` pos (`num

Creates 2D sinusoidal positional embeddings. Args: embed_dim (`int`): The embedding dimension. grid_size (`int`)

r""" This function generates 2D sinusoidal positional embeddings from a grid. Args: embed_dim (`int`): The embedding dimension.