Houdini 22.0 Nodes Copernicus nodes

ML Computer Vision Inference Copernicus node

Apply a model trained using the ML Train Computer Vision TOP.

Since 22.0

This node can be used to apply an ONNX model trained using the ML Train Computer Vision TOP to detect and mask objects in an input image. The Detection Type menu must match the corresponding parameter on the training node that produced the model used with this node.

Parameters

Model

Model File

The ONNX model file to use for inference, produced by a training run using the ML Train Computer Vision TOP.

Reload Model

Forces a reload of the .onnx file.

Detection Type

Determines the detection type used for inference. This must match the detection type used during training.

Objects

Only detects the bounding boxes around object with no keypoints or masks.

Masks

Detects objects and their segmentation masks.

Keypoints

Detects objects and key tracking points in their bounding boxes.

Minimum Confidence

The minimum confidence value for detect objects. Detections below this threshold will be discard.

Inference Resolution

Determines whether inference should use the native resolution of the input volume, or be performd a custom resolution specified using the Custom Resolution parameter.

Custom Resolution

If Inference Resolution is set to Custom Resolution, this parameter determines the resolution for inference. The input volume is up or down- sampled as needed.

Object Definitions

Classes

The number of object classes in the inference dataset.

Class Name

The human-readable name for the object class, set as the “name” attribute for instances of the class during inference.

Class Color

The display color of the object class, used to color the bounding primitives produced during inference.

Keypoints

The number of keypoints in the datasets. These values are common to all training images.

Keypoint Name

The human-readable name for the keypoint.

Keypoint Color

The display color of the keypoint for visualization output.

Pre-Process

Color Transform

The color transformation to apply to the input image before processing.

OCIO

Use OpenColorIO to transform colors from the Original Space to the target space (To Space). See Color management in Houdini for more information.

None (Raw)

Don’t apply any color transformation.

Original Space

The space that the input color is in.

To Space

The output color space to which the input color transforms.

Pixel Mean

The mean value to use when tranforming input colors into the inference color space.

Pixel Deviation

The standard deviation value to use when transforming input colors into the inference color space.

Bounding Boxes

Class Attribute

When this parameter is enabled, a primitive attribute with the specified name is created for each detected object containing the object class.

Name Attribute

When this parameter is enabled, a primitive attribute with the specified name is created for each detected object containing the object name.

Score Attribute

When this parameter is enabled, a primitive attribute with the specified name is created for each detect object containing the detection confidence score.

Set Point Colors

When this toggle is enabled, detect object primitives have their point colors set to the color value associated with the object class.

Masks

Refine Masks

When this toggle is enabled, additional post processing is enabled on masks to smooth out their edges.

Threshold

The minimum mask value threshold for applying the refinement operation.

Step Size

The distance between refinement sample points.

Fitting Error

The allowed error when fitting curves to the mask shape during refinement.

Keypoints

Class Attribute

When this parameter is enabled, a point attribute with the specified name is created for each keypoint containing the keypoint class number.

Name Attribute

When this parameter is enabled, a point attribute with the specified name is created for each keypoint containing the keypoint name.

Score Attribute

When this parameter is enabled, a point attribute with the specified name is created for each keypoint containing the keypoint score.

Set Keypoint Colors

When this toggle is enabled, keypoints have their point colors set to the color value associated with the keypoint type.

Advanced

Execution Provider

Determines which ONNX execution provider to use for inference. By default, the node attempts to pick the best available provider and prefers to use GPU acceleration.

Automatic

Chooses the best provider for the current system. This option prioritizes CUDA if installed, DirectML/CoreML as a fallback depending on the platform, and CPU inference if no GPU provider is available.

CPU

Perform inference using on the CPU.

CUDA

Perform inference using CUDA/cuDNN. CUDA and cuDNN must be installed using the packages provided by NVIDIA.

DirectML

Only available on Windows. Performs inference using the Windows Direct Machine Learning library.

CoreML

Only available on macOS. Performs inference using Apple’s Core ML library.

Device ID

This parameter can be used to specify which GPU to use for inference when multiple GPUs are available. It has no effect when using CPU inference.

Copernicus nodes