| On this page |
Overview ¶
This node edits an APEX rig to apply effects from the ML Deformer to the posed character.
This node can use a trained ML model to deform the skin of a character. Internally, the ML model predicts weights to combine the residual blend shapes to apply a correction to the rest skin.
Note
APEX Add ML Deformer assumes the model was trained on a data set that was created with the help of ML Pose Serialize using its default settings. These settings are Mode set to Subskeleton and Include World Rotation turned on. Also, Joint Group needs to match the joint group used with ML Pose Serialize to create the training data set. These requirements would be met if the ML Train Deformer recipe was used for training.
Inputs ¶
CharacterStream
An APEX Packed Character to insert ML-driven Deformation.
Blend Shapes
The blend shapes used in combination with the weights output by the ML model to adapt the rest mesh. The first blend shape is always applied with a fixed weight of 1, the remaining blend shapes weighted by the outputs of the ML model, in the same order.
Parameters ¶
Model File
The trained model in ONNX format that inputs a serialized pose and outputs a tuple of weights for the residual blend poses.
Execution Provider
推論に使用するONNX実行プロバイダを決定します。 デフォルトでは、このノードは、利用可能な最適なプロバイダを選択し、GPUアクセラレーションの使用を優先します。
Automatic
現在のシステムに最適なプロバイダを選択します。 このオプションは、CUDAがインストールされている場合はCUDAを優先し、プラットフォームに応じてDirectML/CoreMLをフォールバックとして使用し、GPUプロバイダが利用できない場合はCPU推論を実行します。
CPU
CPUを使用して推論を実行します。
CUDA
CUDA/cuDNNを使用して推論を実行します。 CUDAおよびcuDNNは、NVIDIAで用意されているパッケージを使用してインストールしなければなりません。
DirectML
Windowsでのみ利用可能です。 Windows Direct Machine Learningライブラリを使用して推論を実行します。
CoreML
MacOSでのみ利用可能です。 AppleのCore MLライブラリを使用して推論を実行します。
Joint Group
The joint group to serialize the pose for inclusion into the data set on which Model File was trained.
Enforce Joint Limits
When on, then the specified joint limits are applied to a pose before it goes into the model.
Joint Limits
Specify the name of a dictionary attribute that contains joint limits.
Blend Shapes Source
Packed Residual
The Blend Shapes input is expected to consists of packed primitives. Each packed primitive is expected to contain a residual blend shape, which is a blend shape that has the capture shape subtracted from it.
Direct
Directly use the blend shapes provided on the Blend Shapes Input
| See also |
