Crops Mask and Image by using Box. Will try to grow Box to better fit target size Parameters ---------- box img mask_img

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

Invoke ``evaluate`` method of each metric and collect the metrics dictionary. Different from `Evaluator.evaluate`, this function does not

Transpose a PIL image accordingly if it has an EXIF Orientation tag. From https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOp

Forward Function. Args: pred (Tensor): of shape (N, C, H, W). Predicted tensor. target (Tensor): of shape (N, C, H, W

Forward tensor. Returns result of simple forward. Args: inputs (torch.Tensor): batch input tensor collated by :at

Generate Gaussian noise. Args: img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32. sigma (float): Noise scale

Add Gaussian noise (PyTorch version). Args: img (Tensor): Shape (b, c, h, w), range[0, 1], float32. scale (float | Tensor): Noise

Generate poisson noise. Ref: https://github.com/scikit-image/scikit-image/blob/main/skimage/util/noise.py#L37-L219 Args: img (Numpy ar

Generate a batch of poisson noise (PyTorch version) Args: img (Tensor): Input image, shape (b, c, h, w), range [0, 1], float32. sc

Get the Gaussian filter coefficients in one dimension (x or y direction). Args: kernel_size (int): Kernel filter size in

Support two kinds of name matching: 1. matching name from **first-level** submodule. 2. matching name by `re.fullmatch`. Args:

Get target label. Args: input (Tensor): Input tensor. target_is_real (bool): Whether the target is real or fake.

Check whether input is a splitable variable. Args: var (Any): The input variable to check. Returns: bool: Whether input vari

Prepare for metrics before evaluation starts. Some metrics use pretrained model to extract feature. Some metrics use pretrained model

Prepare for the sampler for metrics whose sampling mode are different. For generative models, different metric need image generated wi

Pass `data_batch` from dataloader and `predictions` (generated results) to corresponding `metrics`. Args: data_samples (S

Calculate factor corresponding to quality Args: quality(float): Quality for jpeg compression. Returns: float: Compression fac

Randomly generate bivariate isotropic or anisotropic Gaussian kernels. In the isotropic mode, only `sigma_x_range` is used. `sigma_y_range` and `r

Randomly generate bivariate generalized Gaussian kernels. In the isotropic mode, only `sigma_x_range` is used. `sigma_y_range` and `rotation_range

Randomly generate bivariate plateau kernels. In the isotropic mode, only `sigma_x_range` is used. `sigma_y_range` and `rotation_range` is ignored.

Resize an image to a specific size. Args: image (Image): The image to resize. size (Tuple[int, int]): The size to resize the

T is numer of frames processed in a single step (center frame + N previous/next frames that come before/after it): T = 2N + 1. The paper aut

Set label of ``gt_label``.

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

convert input data to tensor, and then set or change key-value pairs in ``data_field`` by parameter ``data``. Args: data

Convert data into numpy arrays of dtype. Args: img (Tensor | np.ndarray): Input data. dtype (np.dtype): Set the data type of the