Get current momentums. Returns: list[float] | dict[str, list[float]]: Current momentums of all param groups. If t

Denoise at the final step, which is equivalent to solve the ODE from lambda_s to infty by first-order discretization.

Dequantize an array. Args: arr (ndarray): Input array. min_val (scalar): Minimum value to be clipped. max_val (scalar): M

Recover from quantized flow. Args: dx (ndarray): Quantized dx. dy (ndarray): Quantized dy. max_val (float): Maximum value

The adaptive step size solver based on singlestep DPM-Solver. Args: x: A pytorch tensor. The initial value at time `t_T`.

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). We follow the implementation https://github.com/

Placeholder for extract features from images.

calcuate the f-score value. Args: precision (float | torch.Tensor): The precision value. recall (float | torch.Tensor): The recal

Convert flow map to RGB image. Args: flow (ndarray): Array of optical flow. color_wheel (ndarray or None): Color wheel used to ma

Read an optical flow map. Args: flow_or_path (ndarray or str): A flow map or filepath. quantize (bool): whether to read quantized

Format the results into dir (standard format for Cityscapes evaluation). Args: results (list): Testing results of the dat

Forward function.

Forward function.

Generate config from config str. Args: cfg_str (str): Config str. file_format (str): Config file format corresponding

Fused bias leaky ReLU function. This function is introduced in the StyleGAN2: http://arxiv.org/abs/1912.04958 The bias term comes from t

Generate regular square grid of points in [0, 1] x [0, 1] coordinate space. Args: num_grid (int): The number of grids to sample, one

Get annotation by index. Args: idx (int): Index of data. Returns: dict: Annotation info of specified index.

Get class names of current dataset. Args: classes (Sequence[str] | str | None): If classes is None, use default C

Get the git hash of the current repo. Args: fallback (str, optional): The fallback string when git hash is unavailable. Defau

Get ground truth segmentation maps for evaluation.

Get the order of each step for sampling by the singlestep DPM-Solver. We combine both DPM-Solver-1,2,3 to use all the function evalua

Get class palette (RGB) of a dataset.

Sample points for testing. Find ``num_points`` most uncertain points from ``uncertainty_map``. Args: seg_logits (Tensor)

Sample points for training. Sample points in [0, 1] x [0, 1] coordinate space based on their uncertainty. The uncertainties are calcu

Get the position from a period list. It will return the index of the right-closest number in the period list. For example, the cumulative_per

Get priority value. Args: priority (int or str or :obj:`Priority`): Priority. Returns: int: The priority value.

Get the type and mode of points sampler. Args: sampler_type (str): The type of points sampler. The valid value are "D-FPS", "

Get spatial resolution of input feature map considering exporting to onnx mode. Args: x (torch.Tensor): Input tensor, shape (N, C, H,

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

Get the total training step/epoch.

This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches

Convert a grayscale image to BGR image. Args: img (ndarray): The input image. Returns: ndarray: The converted BGR image.

Hue distortion.

Inplace normalize an image with mean and std. Args: img (ndarray): Image to be normalized. mean (ndarray): The mean to be used fo

Pad the given image to a certain shape or pad on all sides with specified padding mode and padding value. Args: img (ndarray): Image

Import modules from the given list of strings. Args: imports (list | str | None): The given module names to be imported. allow_fa

imgs: list, N images of size WxHxC

Infer abbreviation from the class name. When we build a norm layer with `build_norm_layer()`, we want to preserve the norm type in variable n

Infer abbreviation from the class name. This method will infer the abbreviation to map class types to abbreviations. Rule 1: If the clas

Infer the scope of registry. The name of the package where registry is defined will be returned. Example: # in mmdet/mod

Inference image(s) with the segmentor. Args: model (nn.Module): The loaded segmentor. imgs (str/ndarray or list[str/ndarray]): Ei