Construct identity 3D rotation with the same shape

Construct 3D rotation from quaternion (the quaternion needs not to be normalized).

Test with single gpu.

Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be

Zero out the parameters of a module and return it.

Return the rotation matrices for one of the rotations about an axis of which Euler angles describe, for each value of the angle given. A

Return a tensor where each element has the absolute value taken from the, corresponding element of a, with sign taken from the corresponding

Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only de

Returns torch.sqrt(torch.max(0, x)) but with a zero subgradient where x is 0.

Collect data.

Convert rotations given as axis/angle to quaternions. Args: axis_angle: Rotations given as a vector in axis angle form,

Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [

Build multiple optimizers from configs. If `cfgs` contains several dicts for optimizers, then a dict for each constructed optimizers will be r

Collect results in cpu.

Collect results in gpu.

Compute the mean for the previous step, given a function cond_fn that computes the gradient of a conditional log probability with res

Compute what the p_mean_variance output would have been, should the model's score function be conditioned by cond_fn. See co

Create a ScheduleSampler from a library of pre-defined samplers. :param name: the name of the sampler. :param diffusion: the diffusion ob

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

Compute the log-likelihood of a Gaussian distribution discretizing to a given image. :param x: the target images. It is assumed that this

Collect trajectories of given unroll_length.

Get a pre-defined beta schedule for the given name. The beta schedule library consists of beta schedules which remain similar in the lim

Geman-McClure error function.

Load annotations from ``ann_file`` to ``data_infos``

Warpper of mse loss.

Sample x_{t-1} from the model at the given timestep. :param model: the model to sample from. :param x: the current tensor at

Generate samples from the model. :param model: the model module. :param shape: the shape of the samples, (N, C, H, W).

Generate samples from the model and yield intermediate samples from each timestep of diffusion. Arguments are the same as p_

Parse a version string into a tuple. Args: version_str (str): The version string. Returns: tuple[int | str]: The version info,

Prepare raw data for the f'{idx'}-th data.

Get the distribution q(x_t | x_0). :param x_start: the [N x C x ...] tensor of noiseless inputs. :param t: the number of dif

quaternion norm (unit quaternion represents a 3D rotation, which has norm of 1)

quaternion norm (unit quaternion represents a 3D rotation, which has norm of 1)

The (angle, axis) representation of the rotation. The axis is normalized to unit length. The angle is guaranteed to be between [0, pi].

Construct 3D identity rotation given shape