Initialize slurm distributed training environment. If argument ``port`` is not specified, then the master port will be system environment var

Check and initialize input transforms. The in_channels, in_index and input_transform must match. Specifically, when input_transform i

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Load partial pretrained model with specific prefix. Args: prefix (str): The prefix of sub-module. filename (str): Accept local fi

Build multiple branch.

Build fuse layer.

Make each layer.

Build one branch.

Make stem layer for ResNet.

Reference: https://people.sc.fsu.edu/~jburkardt/presentations /truncated_normal.pdf

Pad images according to ``self.size``.

Pad masks according to ``results['pad_shape']``.

Parse iterable values in the string. All elements inside '()' or '[]' are treated as iterable values. Args: val (str): V

Parse the raw outputs (losses) of the network. Args: losses (dict): Raw output of the network, which usually contain

Positiong embeding method. Resize the pos_embed, if the input image size doesn't match the training size. Args:

Substitute base variable placehoders to string, so that parsing would work.

Randomly sample an img_scale according to ``ratio_range`` and ``multiscale_mode``. If ``ratio_range`` is specified, a ratio will be s

Register a handler for some file extensions. Args: handler (:obj:`BaseFileHandler`): Handler to be registered. file_formats (str

Resize images with ``results['scale']``.

Resize semantic segmentation map with ``results['scale']``.

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Substitute variable strings to their actual values.

Convert image based absolute point coordinates to image based relative coordinates for sampling. Args: abs_img_points (Tensor): Image

Add all parameters of module to the params list. The parameters of the given module will be added to the list of param groups, with s

USM sharpening. borrowed from real-ESRGAN Input image: I; Blurry image: B. 1. K = I + weight * (I - B) 2. Mask = 1 if abs(I - B) > thresho

Called after every training epoch to evaluate the results.

Called after every training iter to evaluate the results.

generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1

generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1

Appends dimensions to the end of a tensor until it has target_dims dimensions. From https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusi

Placeholder for augmentation test.

Kai Zhang (github: https://github.com/cszn)

Create a 1D, 2D, or 3D average pooling module.

Scaling bboxes w.r.t the box center. Args: bboxes (ndarray): Shape(..., 4). scale (float): Scaling factor. clip_shape (tu

bgr version of rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]

initialize conv/fc bias value according to a given probability value.

Given an input and a flow-field grid, computes the output using input values and pixel locations from grid. Supported only bilinear interpolation

Brightness distortion.

Builder for attention.

Builder for feed-forward network (FFN).

Build padding layer. Args: cfg (None or dict): The padding layer config, which should contain: - type (str): Layer type.

Build pixel sampler for segmentation map.

Build plugin layer. Args: cfg (None or dict): cfg should contain: type (str): identify plugin layer type. layer a

Build segmentor.

Builder for transformer layer.

Build upsample layer. Args: cfg (dict): The upsample layer config, which should contain: - type (str): Layer type.

Calculating square distance between a and b. Args: point_feat_a (Tensor): (B, N, C) Feature vector of each point. point_feat_b (T

CAM feature classification.

Convert camel case word into snack case. Modified from `inflection lib <https://inflection.readthedocs.io/en/latest/#inflection.under

Add check points in a single line. This method is suitable for running a task on a list of items. A timer will be registered when the method

Puts each data field into a tensor/DataContainer with outer dimension batch size. Extend default_collate to add support for :type:`~mmcv.

Collect the information of the running environments.

Collect results with CPU.

Collect results under cpu mode. On cpu mode, this function will save the results on different gpus to ``tmpdir`` and collect them by the rank

Collect results with GPU.

Collect results under gpu mode. On gpu mode, this function will encode results to gpu tensors and use gpu communication for results collectio

Compute the gradient of the classifier, i.e. nabla_{x} log p_t(cond | x_t).

3x3 convolution with padding.