x_list contains a list of tensors to nest together and run

x_list contains a list of tensors to nest together and run

x_list contains a list of tensors to nest together and run

x_list contains a list of tensors to nest together and run

x_list contains a list of tensors to nest together and run

x_list contains a list of tensors to nest together and run

Forward function for testing. Args: inputs (list[Tensor]): List of multi-level img features. img_metas (list[dict]):

Args: imgs (List[Tensor]): the outer list indicates test-time augmentations and inner Tensor should have a shape

Placeholder for Forward function for training.

This function generates a 2D positional embedding from given coordinates using sine and cosine functions. Args: - xy: The coordinates to

This function initializes a grid and generates a 2D positional embedding using sine and cosine functions. It is a wrapper of get_2d_sincos_po

This function generates a 2D positional embedding from a given grid using sine and cosine functions. Args: - embed_dim: The embedding di

Get the order of the arguments of a function.

Get the order of the arguments of a function.

Gets the device of the specified variable x if it is a tensor, or falls back to a default CPU device otherwise. Allows overriding by prov

Computes the 2D coordinates of the centers of image patches, normalized to the range [-1, +1]. The center of each patch is exactly halfway be

Computes the 2D coordinates of the centers of image patches, normalized to the range [-1, +1]. The center of each patch is exactly halfway be

Args: intrinsics: (..., 3, 3) intrinsics matrices. width: width of the image. height: height of the image. Retur

Calculate the 3D rope index based on image and video's temporal, height and width in LLM. Explanation: Each embedding se

Calculate the target shape based on the given aspect ratio. Args: aspect_ratio: Target aspect ratio

Given all tracks in one sample (b), compute a (N,3) array of RGB color values in [0,255]. The color is determined by the (x,y) position in th

:param w: pixels :param h: pixels :param vmin: min value :param vmax: max value :param cmap_name: :param label :return:

Calculate lr decay rate for different ViT blocks. Args: name (string): parameter name. lr_decay_rate (float): base lr decay r

Calculate lr decay rate for different ViT blocks. Args: name (string): parameter name. lr_decay_rate (float): base lr decay r

Calculate lr decay rate for different ViT blocks. Args: name (string): parameter name. lr_decay_rate (float): base lr decay r

Convert batched points (xyz) to (xyz1).

Get a quad mesh regarding image pixel uv coordinates as vertices and image grid as faces. Args: width (int): image width hei

Get a mesh regarding image pixel uv coordinates as vertices and image grid as faces. Args: *image_attrs (np.ndarray): image attribut

User-friendly inference function ### Parameters - `image`: input image tensor of shape (B, 3, H, W) or (3, H, W) - `

This method is called the the thread or process is started, to initialize any resources that is only held in the thread or process.