r"""Compute adjusted version of `Fid Score`_. The Frechet Inception Distance between two multivariate Gaussians X_x ~ N(mu_1, sigm_1) and X_y

r"""Compute adjusted version of `Fid Score`_. The Frechet Inception Distance between two multivariate Gaussians X_x ~ N(mu_1, sigm_1) and X_y

r"""Compute adjusted version of `Fid Score`_. The Frechet Inception Distance between two multivariate Gaussians X_x ~ N(mu_1, sigm_1) and X_y

hidden_states: (B, L, D) Returns: same shape as hidden_states

x: (batch, dim, seqlen) weight: (dim, width) bias: (dim,) out: (batch, dim, seqlen)

x: (batch, dim) conv_state: (batch, dim, width) weight: (dim, width) bias: (dim,) out: (batch, dim)

x: (batch, dim) conv_state: (batch, dim, width) weight: (dim, width) bias: (dim,) out: (batch, dim)

Center cropping implementation from ADM. https://github.com/openai/guided-diffusion/blob/8fb3ad9197f16bbc40620447b2742e13458d2831/guided_diff

Calculate FID score based on accumulated extracted features from the two distributions.

Calculate FID score based on accumulated extracted features from the two distributions.

Compute metric.

Compute the ratio between d_alpha and alpha

Compute the diffusion term of the SDE Args: x: [batch_dim, ...], data point t: [batch_dim,], time vector form: s

Compute the mean of time-dependent density p_t

Compute the vector field corresponding to p_t

Sample xt from time-dependent density p_t; rng is required

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for E

u: r(B D L) delta: r(B D L) A: r(D N) B: r(B N L) C: r(B N L) D: r(D) z: r(B D L) delta_bias: r(D), fp32 ignores

r"""Pass the input through the encoder layer. Args: hidden_states: the sequence to the encoder layer (required). resi

x: (N, C, H, W) tensor of spatial inputs (images or latent representations of images), t: (N,) tensor of diffusion timesteps

member function for obtaining the drift of the probability flow ODE

Args: unsorted: numpy.ndarray of any dimensionality. k: int Returns: kth values along the designated axis.

Returns the platform name as used in wheel filenames.

Returns the platform name as used in wheel filenames.

member function for obtaining score of x_t = alpha_t * x + sigma_t * eps

Wrapper function: transfrom velocity prediction model to score Args: velocity: [batch_dim, ...] shaped tensor; velocity model outp

Generalized Hilbert ('gilbert') space-filling curve for arbitrary-sized 2D rectangular grids. Takes a discrete 2D coordinate and maps it to t

Generalized Hilbert ('gilbert') space-filling curve for arbitrary-sized 2D rectangular grids. Takes a discrete 2D coordinate and maps it to t

Args: clip (torch.tensor): Video clip to be normalized. Size is (T, C, H, W) Returns: flipped clip (torch.tensor): Size is (T

Run sampling.

Adapted from `KID Score`_

Args: clip (torch.tensor): Video clip to be normalized. Size is (T, C, H, W) mean (tuple): pixel RGB mean. Size is (3) st

Download the given URL and return a binary-mode file object to access the data.

Adapted from `KID Score`_