A DiT-styled Mamba model with ZigZag scan.

r"""Calculate Fréchet inception distance (FID_) which is used to access the quality of generated images. .. math:: FID = \|\mu - \mu_w\|^2

Module that never leaves evaluation mode.

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

r"""Calculate Fréchet inception distance (FID_) which is used to access the quality of generated images. .. math:: FID = \|\mu - \mu_w\|^

Inference parameters that are passed to the main model in order to efficienly calculate and store the context during inference.

Sampler class for the transport model

ODE solver class

r"""Calculate Fréchet inception distance (FID_) which is used to access the quality of generated images. .. math:: FID = \|\mu - \mu_w\|^

The final layer of DiT.

Inception-v1 I3D architecture. The model is introduced in: Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset Joa

r"""Calculate the Inception Score (IS) which is used to access how realistic generated images are. .. math:: IS = exp(\mathbb{E}_x KL(p(y

r""" Calculates Kernel Inception Distance (KID) which is used to access the quality of generated images. Given by .. math:: KID = MMD

Embeds class labels into vector representations. Also handles label dropout for classifier-free guidance.

Example: >>> import torch >>> _ = torch.manual_seed(123) >>> from torchmetric_prdc import PRDC >>> prdc = PRDC(ne

2D Image to Patch Embedding

Flip the video clip along the horizontal direction with a given probability Args: p (float): probability of the clip being flipped. D

Temporally crop the given frame indices at a random location. Args: size (int): Desired length of frames will be seen in the model.

Embeds scalar timesteps into vector representations.

Convert tensor data type from uint8 to float, divide value by 255.0 and permute the dimensions of clip tensor

First scale to the specified size in equal proportion to the short edge, then center cropping

SDE solver class

The CachedWheelsCommand plugs into the default bdist wheel, which is ran by pip when it cannot find an existing wheel (which is currently the

The CachedWheelsCommand plugs into the default bdist wheel, which is ran by pip when it cannot find an existing wheel (which is currently the

Embeds class labels into vector representations. Also handles label dropout for classifier-free guidance.

First use the short side for cropping length, center crop video, then resize to the specified size

load video according to the csv file. Args: target_video_len (int): the number of video frames will be load. align_transform (cal

Uses the CLIP transformer encoder for text (from Hugging Face)

Linear Coupling Plan

Slide along the long edge, with the short edge as crop size. And resie to the desired size.

Which type of output the model predicts.

Normalize the video clip by mean subtraction and division by standard deviation Args: mean (3-tuple): pixel RGB mean std (3-t

Which type of path to use.

class for VP path flow matching

Which type of weighting to use.