Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

Resize a region of interest while staying within the bounds. setting expand_up to False will prevent the ROI from expanding upwards, which i

Function: ---------- apply affine transform 'trans' to uv Parameters: ---------- @trans: 3x3 np.array tr

Zero out the parameters of a module and return it.

Init. Args: scale_factor (float): scaling mode (str): interpolation mode

Increment the stage of the conversion process.

Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas

Combine the generated image with the original image using the mask image.

encodes the image in slices.

Description of the hardware being used.

Convert a PIL Image to a Tensor. If the image is in mode `RGB` the tensor will have shape `[3, H, W]`, otherwise `[1, H, W]` for mode `L

Create a linear module.

Apply a mask to the noisy_latent. ts is a decreasing value between 1000 and 1

Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the

Save the current parameters for restoring later. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to be

Zero out the parameters of a module and return it.