Create a 1D, 2D, or 3D convolution module.

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

Create a linear module.

texture = [bs, 64, self.patch_size, self.patch_size]

Zero out the parameters of a module and return it.

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

Subsample texture

Ancestral sampling with Euler method steps.

Create scalp basis

A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr

Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be

Create average texture for hairstyle calculation

Upload embeddings of textual descriptions for hairstyle idx

Create a 1D, 2D, or 3D average pooling module.

Compute the barycentric coordinates of point p with respect to the triangle defined by points a, b, and c.

https://github.com/MPI-IS/mesh/blob/master/mesh/geometry/barycentric_coordinates_of_projection.py

Map 2D UV meshgrid points to 3D positions and face index using barycentric interpolation with NumPy. Return a tensor of the same shape as the

Split a list into n (roughly) equal-sized chunks

Zero out the parameters of a module and return it.