Finds the python class with the given name and constructs it with the given arguments.

Compute the log-likelihood of a continuous Gaussian distribution. :param x: the targets :param means: the Gaussian mean Tensor. :

r"""2D convolution with optional up/downsampling. Padding is performed only once at the beginning, not between the operations. Args:

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

Takes in a list of tuples of (src, dst) paths and copies files. Will create all necessary directories.

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

Create a ScheduleSampler from a library of pre-defined samplers. :param name: the name of the sampler. :param diffusion: the diffusion

Builds a single .npz file from a folder of .png samples.

Sample x_{t+1} from the model using DDIM reverse ODE.

r"""Downsample a batch of 2D images using the given 2D FIR filter. By default, the result is padded so that its shape is a fraction of the input.

r"""Filter a batch of 2D images using the given 2D FIR filter. By default, the result is padded so that its shape matches the input. User-spe

Convert the seconds to human readable string with days, hours, minutes and seconds.

motion_v: [batch_size, motion_v_dim]

The [`Transformer2DModel`] forward method. Args: hidden_states (`torch.LongTensor` of shape `(batch size, num latent pix

Forward pass of Latte, but also batches the unconditional forward pass for classifier-free guidance.

Forward pass of Latte, but also batches the unconditional forward pass for classifier-free guidance.

Similar to `fvd2048_128f`, but we sample each 8-th frame

Given a type name string (or an object having a __name__ attribute), return matching Numpy and ctypes types that have the same size in bytes.

r""" Copy from torch.nn.utils.clip_grad_norm_ Clips gradient norm of an iterable of parameters. The norm is computed over all gradients

Get the directory path of the module containing the given object name.

Get a pre-defined beta schedule for the given name. The beta schedule library consists of beta schedules which remain similar in the l

Return the fully-qualified name of a top-level function.

r"""Register an import hook that is called whenever a persistent object is being unpickled. A typical use case is to patch the pickled source

r"""Initializes `torch_utils.training_stats` for collecting statistics across multiple processes. This function must be called after `tor

Create a linear module.

List all files recursively in a given directory while ignoring given file and directory names. Returns list of tuples containing both absolute and