Gaussian function. Args: kernel_size (int): Kernel filter size in x or y direction. Should be odd

Generate JSON files with results obtained from YOLO model predictions. Args: results (list): List of results obtained fr

Generate a random string of a given length Args: length (int): The length of the string Returns: str: The random string

Get the two-dimensional Gaussian filter matrix coefficients. Args: kernel_size (tuple[int]): Kernel filter size in the x and y

Returns the direction and anchor for the text Args: position (dict): The position of the text Returns: str: The directi

Get sampler for normal metrics. Directly returns the dataloader. Args: model (nn.Module): Model to evaluate. dataload

Get a sampler to loop input data. Args: sample_kwargs (dict): _description_ runner (Optional[Runner]): _description_ Returns

Calculate gradient penalty for wgan-gp. Args: discriminator (nn.Module): Network for the discriminator. real_data (Tensor): Real

Calculates whether need to run the discriminator step.

Calculates whether need to run the generator step.

Inflate the swin2d parameters to swin3d. The differences between swin3d and swin2d mainly lie in an extra axis. To utilize the pretra

Inflate the swin2d parameters to swin3d. The differences between swin3d and swin2d mainly lie in an extra axis. To utilize the pretra

Inflate the swin2d parameters to swin3d. The differences between swin3d and swin2d mainly lie in an extra axis. To utilize the pretra

Init constant offset.

Initialize weights for ResidualBlockNoBN. Initialization methods like `kaiming_init` are for VGG-style modules. For modules with resi

Initialize weights for PixelShufflePack.

Init weights. Args: model (nn.Module): Models to be inited. pretrained (str): Path for pretrained weights.

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

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

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Tensor): Element-wise weights. Default