Convert torch Tensors into image numpy arrays. After clamping to (min, max), image values will be normalized to [0, 1]. For different tensor

Get the root logger. The logger will be initialized if it has not been initialized. By default a StreamHandler will be added. If `log_file` i

Parse losses dict for different loss variants. Args: losses (dict): Loss dict. Returns: loss (float): Sum of

Build loss. Args: cfg (dict): Configuration for building loss.

Build component. Args: cfg (dict): Configuration for building component.

Set requires_grad for all the networks. Args: nets (nn.Module | list[nn.Module]): A list of networks or a single network.

Make layers by stacking the same blocks. Args: block (nn.module): nn.module class for basic block. num_blocks (int): number of bl

Build backbone. Args: cfg (dict): Configuration for building backbone.

Warp an image or a feature map with optical flow. Args: x (Tensor): Tensor with size (n, c, h, w). flow (Tensor): Tensor with siz

Apply function. This function is to register an equalized learning rate hook in an ``nn.Module``. Args: module (

Compute the output image given the features. Args: lqs (tensor): Input low quality (LQ) sequence with shape (n, t

Evaluation function. Args: output (Tensor): Model output with shape (n, c, h, w). gt (Tensor): GT Tensor with shape (

Obtain image path list (including sub-folders) from a given folder. Args: path (str | :obj:`Path`): Folder path. Returns

Reorder images to 'HWC' order. If the input_order is (h, w), return (h, w, 1); If the input_order is (c, h, w), return (h, w, c); If the

Build a dataset from config dict. It supports a variety of dataset config. If ``cfg`` is a Sequential (list or dict), it will be a concatenat

Build model. Args: cfg (dict): Configuration for building model. train_cfg (dict): Training configuration. Default: None.

Forward function in discriminator training step. In this function, we compute the prediction for each data batch (real or fake). Mean

Get `nn.ModuleDict` to fit the `MMDistributedDataParallel` interface. Args: module (MMDistributedDataParallel | nn.Module

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataload

Initialize network weights. Args: modules (nn.Module): Modules to be initialized. scale (float): Scale initialized weights, espec

Get the device of a module. Args: module (nn.Module): A module contains the parameters. Returns: torch.device: The device of

L1 loss. Args: pred (Tensor): Prediction Tensor with shape (n, c, h, w). target ([type]): Target Tensor with shape (n, c, h, w).

Normalize the input image. Args: img (Tensor): Input image. Returns: Tensor: Normalized image.

Convert objects of various python types to :obj:`torch.Tensor`. Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`, :class:`S

Concat or Add two tensors. Args: x1 (Tensor): The first input tensor. x2 (Tensor): The second input tensor.

Apply spatial transform (flip, rotate) to the images. Args: imgs (torch.Tensor): The images to be transformed/ mode (

Build module function. Args: cfg (dict): Configuration for building modules. registry (obj): ``registry`` object. default

r"""Equalized Learning Rate. This trick is proposed in: Progressive Growing of GANs for Improved Quality, Stability, and Variation The g

Default initialization of network weights for image generation. By default, we use normal init, but xavier and kaiming might work better for

Parse the package dependencies listed in a requirements file but strips specific versioning information. Args: fname (str): path to r

Pearson Linear Correlation Coefficient

Restore the predicted alpha to the original shape. The shape of the predicted alpha may not be the same as the shape of original inpu

Save predicted alpha to file. Args: pred_alpha (np.ndarray): The predicted alpha matte of shape (H, W). meta (list[di

Generate the mesh grid, centering at zero. Args: kernel_size (int): The size of the kernel. Returns: x_grid (ndarray): x-coo

Evaluation function. Args: runner (``mmcv.runner.BaseRunner``): The runner. results (dict): Model forward results.

Evaluate predicted alpha matte. The evaluation metrics are determined by ``self.test_cfg.metrics``. Args: pred_alpha (np

Extract patch from a given bbox. Args: bbox (torch.Tensor | numpy.array): Bbox with (top, left, h, w). If `img` has batch dim

Extract feature patches. The feature map will be padded automatically to make sure the number of patches is equal to `(H / stride) *

Calculate the rotated sigma matrix (two dimensional matrix). Args: sig_x (float): Standard deviation along the horizontal direction.

Get 1-channel unknown area tensor from the 3 or 1-channel trimap tensor. Args: trimap (Tensor): Tensor with shape (N, 3, H, W) or (N, 1,

Reshape image-style feature to columns. This function is used for unfold feature maps to columns. The details of this function can be

Initialize a model from config file. Args: config (str or :obj:`mmcv.Config`): Config file path or the config object.

Down-sample by pixel unshuffle. Args: x (Tensor): Input tensor. scale (int): Scale factor. Returns: Tensor: Output t

Create a polynomial kernel.

Inference image with the model. Args: model (nn.Module): The loaded model. img (str): File path of input image. Returns:

Save visualization results. Args: img (torch.Tensor): Tensor with shape of (n, 3, h, w). filename (str): Path to save

Scatter function. Args: inputs (Tensor): Input Tensor. kwargs (dict): Args for ``mmcv.parallel.scatte

Spearman Rank Order Correlation Coefficient

Length of the dataset. Returns: int: Length of the dataset.

Create a all-zero rectangle hole in the image. Args: img (np.ndarray): Source image. start_point (tuple[int]): The to

Get parameters for affine transformation. Returns: paras (tuple): Params to be passed to the affine transformation.

Calculate Gram matrix. Args: x (torch.Tensor): Tensor with shape of (n, c, h, w). Returns: torch.Tensor: Gra

Save the image. Args: meta (list[dict]): Meta data, such as path of target file. Default: None. These dictionarie