Uniform Skeleton

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

find the quaternion used to rotate v0 to v1

q0 : tensor of quaternions t: tensor of powers

Importance-sample timesteps for a batch. :param batch_size: the number of timesteps. :param device: the torch device to save

Set requies_grad for all the networks. Args: nets (nn.Module | list[nn.Module]): A list of networks or a single network.

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

Compute training losses for a single timestep. :param model: the model to evaluate loss on. :param x_start: the [N x C x ...

Update the reweighting using losses from a model. Sub-classes should override this method to update the reweighting using los

Get a numpy array of weights, one per diffusion step. The weights needn't be normalized, but must be positive.

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

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

Generate samples from the model using DDIM. Same usage as p_sample_loop().

Convert Euler angles to quaternions.

Convert Euler angles to quaternions.

Convert axis-angle rotations (aka exponential maps) to quaternions. Stable formula from "Practical Parameterization of Rotations Using the Ex

query (batch, query_dim) key (batch, seq_len, key_dim)

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

x: B, T, D

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

x: B, T, D

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

x: B, T, D