Calculate PDF of the bivariate Gaussian distribution. Args: sigma_matrix (ndarray): with the shape (2, 2) grid (ndarray): generat

Propagate the latent features throughout the sequence. Args: feats dict(list[tensor]): Features from previous branches. Each

MATLAB psf2otf function. Borrowed from https://github.com/aboucaud/pypher/blob/master/pypher/pypher.py. Input: psf : h x w numpy

Get the distribution q(x_t | x_0). :param x_start: the [N x C x ...] tensor of noiseless inputs. :param t: the number of diff

Quantize an array of (-inf, inf) to [0, levels-1]. Args: arr (ndarray): Input array. min_val (scalar): Minimum value to be clippe

Quantize flow to [0, 255]. After this step, the size of flow will be much smaller, and can be dumped as jpeg images. Args: flow

R1 regularization for discriminator. The core idea is to penalize the gradient on real data alone: when the generator distribution pro

Randomly crop a patch from the give image.

Read image worker. Args: path (str): Image path. key (str): Image key. compress_level (int): Compress level when encoding

Reduce loss as specified. Args: loss (Tensor): Elementwise loss tensor. reduction (str): Options are 'none', 'mean' and 'sum'.

Reload the optimizers and schedulers for resumed training. Args: resume_state (dict): Resume state.

Set random seeds.

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portions

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portions

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portions

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portions of

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portions of

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portions

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized port

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized port

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portions of

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized port

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portio

swap the features from the dictionary.

Input: pch_res: n x c x pch_size x pch_size, float index_infos: (h_start, h_end, w_start, w_end)

Update learning rate. Args: current_iter (int): Current iteration. warmup_iter (int)： Warm-up iter numbers. -1 for no

Apply wavelet blur to the input tensor.

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

Args: windows: (num_windows*b, window_size, window_size, c) window_size (int): Window size h (int): Height of image

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

Load yaml file or string. Args: f (str): File path or a python string. Returns: dict: Loaded dict.

Format logging message. Args: log_vars (dict): It contains the following keys: epoch (int): Epoch number.