Init. Args: eval_env: Batched environment to run evals on. eval_policy_fn: Function returning the policy from the policy parameters.

Return the length of current dataset.

Compute the entire variational lower-bound, measured in bits-per-dim, as well as other related quantities. :param model: the

Check input folder or file. Args: input_path (str): input folder or file path. allowed_suffix (List[str], optional):

This function converts target class indices to one-hot vectors, given the number of classes. Args: targets (Tensor): The ground truth

Sample x_{t+1} from the model using DDIM reverse ODE.

Evaluate the results. Args: runner (:obj:`mmcv.Runner`): The underlined training runner. results (list): Output result

Forward function. Args: inputs (tuple): Input data. kwargs (dict): Args for ``mmcv.parallel.scatter_g

h: B, T, D emb: B, D

motion: B, T, D

x: B, T, D

x: B, T, D xf: B, N, L

x: B, T, D xf: B, N, L

Forward function of loss. Args: pred (torch.Tensor): The prediction. target (torch.Tensor): The learning target of the