Low-level ML nodes

Houdini has a family of low-level nodes that support the creation of a wide variety of ML setups. These can be used to create entire new ML setups from scratch and also incorporate existing models, training scripts, and data sets into Houdini.

The most important of these low-level nodes are listed below:

Data Set Preprocessing:

Principal Component Analysis

Linear Solver

Raw Data Set Input/Output:

ROP Geometry Raw Output

Raw Import

Model Training:

Python Virtual Environment

Python Script

Inference:

ONNX Inference (SOP)

ONNX Inference (COP)

Machine Learning

General Support ¶

Supervised ML pipeline tools ¶

ML Recipes ¶

Animation and character-specific ML tools ¶

Volume-specific ML tools ¶

Image-specific ML tools ¶

Reference ¶