oa::ml::flow

Module published by the oa::ml module.

MdRust public API

Public Types

Public Functions

pub fn euler_step( state: &Matrix, velocity: &Matrix, delta_time: f32, ) -> Result<Matrix>

pub fn linear_match( clean: &Matrix, noise: &Matrix, time: &Matrix, ) -> Result<FlowMatchBatch>

pub fn masked_mse( prediction: &Matrix, target: &Matrix, mask: &Matrix, ) -> Result<Matrix>

Function Documentation

pub fn euler_step(
	state: &Matrix,
	velocity: &Matrix,
	delta_time: f32
) -> Result<Matrix>

Advance one explicit Euler step: state + velocity * delta_time. Errors Returns an error unless state and velocity are matching nonempty same-engine F32 matrices, delta_time is finite, and recording succeeds.

pub fn linear_match(
	clean: &Matrix,
	noise: &Matrix,
	time: &Matrix
) -> Result<FlowMatchBatch>

Construct x(t) = clean + t * (noise - clean) and v = noise - clean. A rank-one time vector matching the batch dimension expands across every non-batch axis. Scalars and ordinarily broadcastable time shapes are also accepted. Errors Returns an error unless every input is same-engine F32, clean and noise are matching and nonempty, time broadcasts to them, and recording succeeds.

pub fn masked_mse(
	prediction: &Matrix,
	target: &Matrix,
	mask: &Matrix
) -> Result<Matrix>

Compute mean squared error over broadcast-selected valid elements. The mask contributes its values to the denominator. An all-zero mask returns exact zero by clamping the denominator to one. Target and mask are detached; reverse mode differentiates only prediction. Errors Returns an error unless prediction and target are matching nonempty same-engine F32 matrices, mask is same-engine F32 and broadcastable to prediction, and recording succeeds.