image_size = p['data']['image_size'] if image_size == 256: channel_mult = (1, 1, 2, 2, 4, 4) elif image_size == 64: chann

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

Calculation of the statistics used by the FID. Params: -- files : List of image files paths -- model : Instance of inception m

Calculation of the statistics used by the FID. Params: -- files : List of image files paths -- model : Instance of inception m

Calculates the FID of two paths

Calculates the FID of two paths

Numpy implementation of the Frechet Distance. The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1) and X_2 ~ N(mu_2, C_2

Numpy implementation of the Frechet Distance. The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1) and X_2 ~ N(mu_2, C_2

Computes the PRD curve for discrete distributions. This function computes the PRD curve for the discrete distribution eval_dist with respect to t

Computes PRD data from sample embeddings. The points from both distributions are mixed and then clustered. This leads to a pair of histograms of

tensordot(x, y, 1).

tensordot(x, y, 1).

tensordot(x, y, 1).

tensordot(x, y, 1).

Fused `tf.nn.conv2d()` followed by `downsample_2d()`. Padding is performed only once at the beginning, not between the operations. The fused

Fused `tf.nn.conv2d()` followed by `downsample_2d()`. Padding is performed only once at the beginning, not between the operations. The fused

Sample x_{t-1} from the model using DDIM. Same usage as p_sample().

Generate samples from the model using DDIM. Same usage as p_sample_loop().

Use DDIM to sample from the model and yield intermediate samples from each timestep of DDIM. Same usage as p_sample_loop_pro

Build pretrained Inception model for FID computation The Inception model for FID computation uses a different set of weights and has a slight

Build pretrained Inception model for FID computation The Inception model for FID computation uses a different set of weights and has a slight

Get activation functions from the config file.

Calculates the activations of the pool_3 layer for all images. Params: -- files : List of image files paths -- model : Instanc

Calculates the activations of the pool_3 layer for all images. Params: -- files : List of image files paths -- model : Instanc

Create the divergence function of `fn` using the Hutchinson-Skilling trace estimator.

Create the divergence function of `fn` using the Hutchinson-Skilling trace estimator.

Apply the model and return all of the intermediate tensors. :param x: an [N x C x ...] Tensor of inputs. :param timesteps: a

Create a function to compute the unbiased log-likelihood estimate of a given data point. Args: sde: A `sde_lib.SDE` object that represent

Compute an unbiased estimate to the log-likelihood in bits/dim. Args: model: A score model. data: A PyTorch tensor.

Expands a 1-dimensional tensor so that its last dimensions match the target size. Args: data (torch.Tensor): A 1-dimensional ten

input: x_s, s, t output: x_t

Generate samples from the model. :param device: if specified, the device to create the samples on. If not spec

Generate samples from the model and yield intermediate samples from each timestep of diffusion. Returns a generator over dicts, wher

Computes max. F_beta and max. F_{1/beta} for precision/recall pairs. Computes the maximum F_beta and maximum F_{1/beta} score over all pairs of p