x: A list of videos each with shape [C, T, H, W]. t: [B]. context: A list of tex

x: A list of videos each with shape [C, T, H, W]. t: [B]. context: A list of text embeddings

Initialize a inference state.

Calculate the pose accuracy of PCK for each individual keypoint and the averaged accuracy across all keypoints for coordinates. Note:

Calculate the end-point error. Note: - batch_size: N - num_keypoints: K Args: pred (np.ndarray[N, K, 2]): Predicted

Calculate the normalized mean error (NME). Note: - batch_size: N - num_keypoints: K Args: pred (np.ndarray[N, K, 2])

Get final keypoint predictions from 3d heatmaps and transform them back to the image. Note: - batch size: N - num keypoints:

Get final keypoint predictions from regression vectors and transform them back to the image. Note: - batch_size: N - num_keyp

Get multi-label classification accuracy. Note: - batch size: N - label number: L Args: pred (np.ndarray[N, L, 2]): m

kps will be changed inplace

Calculate the pose accuracy of PCK for each individual keypoint and the averaged accuracy across all keypoints from heatmaps. Note: P

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Ar

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. A

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_index

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_inde

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`):

r""" Sequence-parallel causal self-attention using Ulysses all-to-all. Input x is sequence-chunked (each GPU holds padded_seq_lens/world_size

x: A list of videos each with shape [C, T, H, W]. t: [B]. context: A list of text embeddings each with s

x: A list of videos each with shape [C, T, H, W]. t: [B]. context: A list of text embeddings

Convert the 133 keypoints from pose2d to body and hands keypoints. Args: kp2ds (np.ndarray): [133, 2] Returns: List[np.ndarr

The index counter for current timestep. It will increase 1 after each scheduler step.

The index counter for current timestep. It will increase 1 after each scheduler step.

Convert a string to a boolean. Supported true values: 'yes', 'true', 't', 'y', '1' Supported false values: 'no', 'false', 'f', 'n', '0'

XLMRobertaLarge adapted from Huggingface.