Return file-like object for 'name'. name is a string for the file name within the ZIP file, or a ZipInfo object. mode should

Load a model from a checkpoint file. ### Parameters: - `pretrained_model_name_or_path`: path to the checkpoint file or repo

check if `key` in arguments, else append default value `key=value` to argument list

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

Get image space UV grid, ranging in [0, 1]. >>> image_uv(10, 10): [[[0.05, 0.05], [0.15, 0.05], ..., [0.95, 0.05]], [[0.05, 0.15],

Applies Rotary Position Embedding with Multimodal Sections to the query and key tensors (https://qwenlm.github.io/blog/qwen2-vl/). Explanation:

Convert batched points (xyz) to (xyz1).

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

This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch, num_key_value_heads, seqlen, he

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 >=

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 >=

Link the output of each node to the input of the next node.

Checks if 'input_tensor' contains inf or nan values and clamps extreme values. Args: input_tensor (torch.Tensor): The loss tenso

Args: extrinsics: (..., 4, 4) extrinsics matrices. intrinsics: (..., 3, 3) intrinsics matrices. uv: (..., n_rays, 2) uv c

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

Unproject a batch of depth maps to 3D world coordinates. Args: depth_map (np.ndarray): Batch of depth maps of shape (S, H, W, 1) or

Given color, sigma and z_vals (linear depth of the sampling points), render the volume. NOTE: By default, color and sigma should have one le

Create a logger that writes to a log file and stdout.

Args: - depthmap (HxW array): - camera_intrinsics: a 3x3 matrix - camera_pose: a 4x3 or 4x4 cam2world matrix Returns:

Calculate 3D RoPE indices for a single image. Args: image_grid_thw: Temporal, height, width dimensions of the image grid

Importance sample z values. NOTE: By default, weights should have one less sample than z_vals, in correspondence with the intervals. If

Laplacian smooth with cotangent weights Args: vertices (torch.Tensor): shape (..., N, 3) faces (torch.Tensor): shape (T, 3)

Recover the depth map and FoV from a point map with unknown z shift and focal. Note that it assumes: - the optical center is at the cent

This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch, num_key_value_heads, seqlen, he

Rotates half the hidden dims of the input.

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

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

Computes the inverse of a batch of SE(3) matrices.