unreal.NearestNeighborTrainingModel

class unreal.NearestNeighborTrainingModel(outer: Object | None = None, name: Name | str = 'None')

Bases: MLDeformerTrainingModel

Nearest Neighbor Training Model

C++ Source:

  • Plugin: NearestNeighborModel

  • Module: NearestNeighborModelEditor

  • File: NearestNeighborTrainingModel.h

Editor Properties: (see get_editor_property/set_editor_property)

  • kmeans_results (Array[int32]): [Read-Write]

  • part_sample_deltas (Array[float]): [Read-Write]

  • sample_bone_rotations (Array[float]): [Read-Write] The bone rotations in bone (local) space for this sample. This is updated after SetCurrentSampleIndex is called and is 6 floats per bone (2 columns of 3x3 rotation matrix).

  • sample_curve_values (Array[float]): [Read-Write] The curve weights. This is updated after SetCurrentSampleIndex is called.

  • sample_deltas (Array[float]): [Read-Write] The delta values per vertex for this sample. This is updated after SetCurrentSampleIndex is called. Contains an xyz (3 floats) for each vertex.

get_kmeans_anim_num_frames(skeleton_id) → int32

Get Kmeans Anim Num Frames

Parameters:

skeleton_id (int32) –

Return type:

int32

get_kmeans_num_anims() → int32

Get Kmeans Num Anims

Return type:

int32

get_kmeans_num_clusters() → int32

Get Kmeans Num Clusters

Return type:

int32

get_mesh_index_buffer() → Array[int32]

Get Mesh Index Buffer

Return type:

Array[int32]

get_nearest_neighbor_model() → NearestNeighborModel

Get Nearest Neighbor Model

Return type:

NearestNeighborModel

get_part_num_neighbors(part_id) → int32

Get Part Num Neighbors

Parameters:

part_id (int32) –

Return type:

int32

get_part_vertex_map(part_id) → Array[int32]

Get Part Vertex Map

Parameters:

part_id (int32) –

Return type:

Array[int32]

get_unskinned_vertex_positions() → Array[float]

Get Unskinned Vertex Positions

Return type:

Array[float]

kmeans_cluster_poses(part_id) → int32

Kmeans Cluster Poses

Parameters:

part_id (int32) –

Return type:

int32

property kmeans_results: None

[Read-Write]

Type:

(Array[int32])

property part_sample_deltas: None

[Read-Write]

Type:

(Array[float])

sample_kmeans_anim(skeleton_id) → bool

Sample Kmeans Anim

Parameters:

skeleton_id (int32) –

Return type:

bool

sample_kmeans_frame(frame) → bool

Sample Kmeans Frame

Parameters:

frame (int32) –

Return type:

bool

sample_part(part_id, index) → int32

Sample Part

Parameters:

  • part_id (int32) –

  • index (int32) –

Return type:

int32

set_sampler_part_data(part_id) → int32

Set Sampler Part Data

Parameters:

part_id (int32) –

Return type:

int32

train() → int32

Main training function, with implementation in python.

Return type:

int32

update_nearest_neighbor_data() → int32

Update Nearest Neighbor Data

Return type:

int32