Apply inverse log transform: sign(y) * (exp(|y|) - 1) Args: y: Input tensor Returns: Transformed tensor

Convert rotations given as rotation matrices to quaternions. Args: matrix: Rotation matrices as tensor of shape (..., 3, 3). Re

UV with left-top corner as (-width / diagonal, -height / diagonal) and right-bottom corner as (width / diagonal, height / diagonal)

Args: boxes (Boxes, RotatedBoxes or ndarray): either a :class:`Boxes`, or an Nx4 numpy array of XYXY_ABS format f

Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first, as ten

r"""Masked mean `reduce_masked_mean(x, mask)` computes the mean of a tensor :attr:`input` over a mask :attr:`mask`, returning .. math::

Args: img: same as in __init__

Processes specialized tokens with shape (1, 2, X, C) for multi-frame processing: 1) Uses the first position (index=0) for the first frame onl

args: x: H W

Weighted Procrustes Analysis in PyTorch (batched). Args: X: (B, 1, N, 3), source point cloud. Y: (B, T, N, 3), target po

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

Applies 1D rotary position embeddings along one dimension. Args: tokens: Input token features. positions: Position in

Apply positional embedding to tensor x.

Convert different format of boxes to an NxB array, where B = 4 or 5 is the box dimension.

Create a grayscale version of the original image. The colors in masked area, if given, will be kept.

Derive the desired score numbers from summarized COCOeval. Args: coco_eval (None or COCOEval): None represents no predic

Evaluate the coco results using COCOEval API.

Randomly modifies given color to produce a slightly different color than the color given. Args: color (tuple[double]): a

Get COCO API "tasks" (i.e. iou_type) from COCO-format predictions.

Activate pose parameters with specified activation functions. Args: pred_pose_enc: Tensor containing encoded pose parameters [transl

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

Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you need a l

Inverse to pose_encoding_to_camera

Compute the loss for the FrontTracker model.

Custom interpolate to avoid INT_MAX issues in nn.functional.interpolate.

collect all tensor from all GPUs args: x: shape (mini_batch, ...) returns: shape (mini_batch * num_gpu, ...)

Args: binary_mask (ndarray): numpy array of shape (H, W), where H is the image height and W is the image width. E

Args: box_coord (tuple): a tuple containing x0, y0, x1, y1 coordinates, where x0 and y0 are the coordinates of th

Args: segment: numpy array of shape Nx2, containing all the points in the polygon. color: color of the polygon. Refer

Draw semantic segmentation predictions/labels. Args: sem_seg (Tensor or ndarray): the segmentation of shape (H, W).

world_tracks: B T N 3 this is the coarse 3d tracks in world coordinate (coarse 3d tracks) dyn_prob: B T N this is the dynamic probabilit

The same as tf.gather_nd but batched gather is not supported yet. indices is an k-dimensional integer tensor, best thought of as a (k-1)-dimensio

This function generates a 1D positional embedding from a given grid using sine and cosine functions. Args: - embed_dim: The embedding di

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

Get 2D RoPE from grid. Args: embed_dim: (`int`): The embedding dimension size, corresponding to hidden_size_head. grid (`np.

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

this will perform the index select, cat the tensors, and provide the attn_bias from cache

Returns: ndarray: the visualized image of shape (H, W, 3) (RGB) in uint8 type. The shape is scale

vis_gt: [B, T, N] 0/1 binary tensor n: [B, N] int tensor, the n-th visible time index to get (1-based) Returns: [B, N] tensor of time in

Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).

Calculate element-wise Huber loss between x and y

cam_pts: (B, T, N, 3) graph_matrix: (B, 1, N) dyn_weight: (B, T, N) K: number of keyframes to select (including start and end) R

Compute the loss of 3D tracking problem

This function generates a 1D positional embedding from a given grid using sine and cosine functions. Args: - embed_dim: The embedding di

UV with left-top corner as (-width / diagonal, -height / diagonal) and right-bottom corner as (width / diagonal, height / diagonal)

This function convert the pose encoding into `intrinsic` and `extrinsic` Args: poses_pred: B T 8 Return: Intrinsic B T