Process one batch of data and predictions. Args: data_batch (Sequence[dict]): A batch of data from the dataloader

Process an image. Args: gt (Torch | np.ndarray): GT image. pred (Torch | np.ndarray): Pred image. mask (T

Process an image. Args: gt (Torch | np.ndarray): GT image. pred (Torch | np.ndarray): Pred image. mask (T

Calculate R1 gradient penalty for WGAN-GP. R1 regularizer comes from: "Which Training Methods for GANs do actually Converge?" ICML'2018

Randomly add JPG compression artifacts. Args: img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32. quality_rang

Number of real images need for current device.

Register all modules in mmagic into the registries. Args: init_default_scope (bool): Whether initialize the mmagic default scope.

Utility function to remove the background of a logo

Constructs a ResNet-101 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-18 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Convert a RGB image to grayscale image. Args: img (ndarray): The input image. keepdim (bool): If False (by default), then return

Launch validation. The evaluation process consists of four steps. 1. Prepare pre-calculated items for all metrics by calling :meth

Stitching multiple images, all imgs must have the same size imgs : [img1,img2,img3,img4] splice_shape: (2,2)

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