Convert rotations given as axis/angle to quaternions. Args: axis_angle: Rotations given as a vector in axis angle form,

This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring o

Build convolution layer. Args: cfg (None or dict): The conv layer config, which should contain: - type (str): Layer type.

Build padding layer. Args: cfg (dict): The padding layer config, which should contain: - type (str): Layer type.

Returns list of utf-8 byte and a mapping to unicode strings. We specifically avoids mapping to whitespace/control characters the bpe code bar

Convert a camera-to-world matrix to a tuple of translation and rotation input: c2w: 4x4 matrix output: tuple of translation and rotation

Calculate the candidate quad faces. Args: edges (np.ndarray): [E, 2] edge indices face2edge (np.ndarray): [T, 3] face to edg

Calculate the direction of each candidate quad face. Args: vertices (np.ndarray): [N, 3] 3-dimensional vertices quads (np.nd

Calculate the distortion of each candidate quad face. Args: vertices (np.ndarray): [N, 3] 3-dimensional vertices quads (np.n

Calculate the smoothness of each candidate quad face connection. Args: quad2adj (np.ndarray): [Q, 8] adjacent quad faces of each qua

Compute the inverse of each 3x3 intrinsics matrix in a batch.

Compute the inverse of each 4x4 (or 3x4) SE3 matrix in a batch. If `R` and `T` are provided, they must correspond to the rotation and transl

Modify camera intrinsics to follow a different convention. Coordinates of the center of the top-left pixels are by default: - (0.5, 0.5)

Map (x, y) -> color in (R, G, B). 1) Normalize x,y to [0,1]. 2) Combine them into a single scalar c in [0,1]. 3) Use matplotlib's col

Normalize the translation vectors and compute the angle between them.

Normalize the translation vectors and compute the angle between them.

Normalize the translation vectors and compute the angle between them.

Compute connected faces of a mesh. Args: faces (torch.Tensor): [T, 3] triangular face indices edges (torch.Tensor, optional)

Compute edges of a mesh. Args: faces (torch.Tensor): [T, 3] triangular face indices Returns: edges (torch.T

Compute face angles of a triangular mesh Args: vertices (np.ndarray): [..., N, 3] 3-dimensional vertices faces (np.ndarray):

Compute face angles of a triangular mesh Args: vertices (torch.Tensor): [..., N, 3] 3-dimensional vertices faces (torch.Tens

compute TBN matrix for each face Args: pos (torch.Tensor): shape (..., N_pos, 3), positions faces_pos (torch.Tensor): shape(T, 3)

Copy/paste/tweak model's weights to our Dinov2WithRegisters structure.

Instead of storing the entire correlation pyramid, we compute each level's correlation volume, sample it immediately, then discard it

Create a normalized UV grid of shape (width, height, 2). The grid spans horizontally and vertically according to an aspect ratio, ensuri

Compute the edge mask of a depth map. The edge is defined as the pixels whose neighbors have a large difference in depth. Args:

Read depth data from file, return as numpy array.

Convert a depth map to camera coordinates. Args: depth_map (np.ndarray): Depth map of shape (H, W). intrinsic (np.ndarray):

Args: - depthmap (HxW array): - camera_intrinsics: a 3x3 matrix Returns: pointmap of absolute coordinates (HxWx3 arra

Args: - depthmap (HxW array): - camera_intrinsics: a 3x3 matrix Returns: pointmap of absolute coordinates (HxWx3 arra

DINOv2 ViT-L/14 model with registers (optionally) pretrained on the LVD-142M dataset.

Apply disk blur to an image using FFT convolution. Args: image (np.ndarray): Input image, can be grayscale or color. radius

Generate disk kernel with given radius. Args: radius (int): Radius of the disk (in pixels). Returns: np.ndarray

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

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

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). Comment by Ross Wightman: This is the same as the D

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). Comment by Ross Wightman: This is the same as the D

Return the rotation matrices for one of the rotations about an axis of which Euler angles describe, for each value of the angle given. A

Return the rotation matrices for one of the rotations about an axis of which Euler angles describe, for each value of the angle given. A

Extract features from images.

Flattens a nested dictionary into a single-level dictionary, with keys as tuples.