Add config for ConvNeXt Backbone.

Solve `min sum_i w_i * (a * x_i + b - y_i ) ^ 2`, where `a` and `b` are scalars, with respect to `a` and `b` using least squares. ### Parame

Align `depth_src` to `depth_tgt` with given constant weights. ### Parameters: - `depth_src: torch.Tensor` of shape (..., N) - `depth

Align `depth_src` to `depth_tgt` with given constant weights using IRLS.

Align `depth_src` to `depth_tgt` with given constant weights. ### Parameters: - `depth_src: torch.Tensor` of shape (..., N) - `dept

### Parameters: - `points_src: torch.Tensor` of shape (..., N, 3) - `points_tgt: torch.Tensor` of shape (..., N, 3) - `weight: torch.

Align `points_src` to `points_tgt` with respect to a Z-axis shift. ### Parameters: - `points_src: torch.Tensor` of shape (..., N, 3)

Align `points_src` to `points_tgt` with respect to a Z-axis shift. ### Parameters: - `points_src: torch.Tensor` of shape (..., N, 3)

r""" Returns: `dict` of attention processors: A dictionary containing all attention processors used in the model with

Args: inputs: A float tensor of arbitrary shape. The predictions for each example. targets: A float tensor with t

Similar to `build_detection_train_loader`, with default batch size = 1, and sampler = :class:`InferenceSampler`. This sampler coordinates all

Args: coords: [B, T, N, 3] intr: [B, T, 3, 3]

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

Compute global affine transform (scale * pointmap + shift = points) using least-squares fitting with optional weights and mask. Args:

Apply depth of field effect to an image. Args: img (numpy.ndarray): (H, W, 3) input image. depth (numpy.ndarray): (H, W) dep

Compute the DICE loss, similar to generalized IOU for masks Args: inputs: A float tensor of arbitrary shape. The pred

r""" Disable sliced VAE decoding. If `enable_slicing` was previously enabled, this method will go back to computing decoding in one st

r""" Disable tiled VAE decoding. If `enable_tiling` was previously enabled, this method will go back to computing decoding in one step

Draw annotations/segmentaions in Detectron2 Dataset format. Args: dic (dict): annotation/segmentation data of one image,

Args: soft_mask (ndarray): float array of shape (H, W), each value in [0, 1]. color: color of the mask. Refer to `mat

Returns: dict: has a key "segm", whose value is a dict of "AP" and "AP50".

Args: flow (numpy): A 2-dim array that stores x and y change in optical flow threshold_factor (float): Prob of di

make sure the poses in on window are de-normalized by the first frame, where the first frame transformation is the Identity Matrix. args

Expects a two dimensional flow image of shape. Args: flow_uv (np.ndarray): Flow UV image of shape [H,W,2] clip_flow (float,

r""" The forward method of the `Attention` class. Args: hidden_states (`torch.Tensor`): The hidden states

Patchifies and embeds the input tensor(s). Args: x (List[torch.Tensor] | torch.Tensor): The input tensor(s) to be patchi

r""" Args: text_embeds (`torch.Tensor`): Input text embeddings. Expected shape: (batch_size, seq_length, embedding