Expand the tensor `v` to the dim `dims`. Args: `v`: a PyTorch tensor with shape [N]. `dim`: a `int`. Returns: a P

r"""Returns the mean of the scalars that were accumulated for the given statistic between the last two calls to `update()`, or NaN if

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

Compute lambda_t = log(alpha_t) - log(sigma_t) of a given continuous-time label t in [0, T].

Compute sigma_t of a given continuous-time label t in [0, T].

Compute log(alpha_t) of a given continuous-time label t in [0, T].

Convert the model to the noise prediction model or the data prediction model.

Write text to stdout (and a file) and optionally flush.

Load model from file. Args: path (str): file path

Create a linear module.

r"""Returns the standard deviation of the scalars that were accumulated for the given statistic between the last two calls to `update(

Performs a single optimization step. Args: closure (callable, optional): A closure that reevaluates the model and

hdfs capable to check whether a file_path is exists

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

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

r"""Copies current values of the internal counters to the user-visible state and resets them for the next round. If `keep_previous=Tr

Zero out the parameters of a module and return it.

Wrapper for the underlying `conv2d()` and `conv_transpose2d()` implementations.

Flush, close possible files, and remove stdout/stderr mirroring.

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

Compute the intermediate time steps for sampling. Args: skip_type: A `str`. The type for the spacing of the time steps. We support

Compute the continuous-time label t in [0, T] of a given half-logSNR lambda_t.

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