Inference
The Inference node applies a .cat file supplied by the CopyCat node to create the effect modeled by the network across the input image.
See CopyCat for more information.
Inputs and Controls
Connection Type |
Connection Name |
Function |
Input |
Input |
The image to which the CopyCat .cat file is applied. |
Control (UI) |
Knob (Scripting) |
Default Value |
Function |
Inference Tab |
|||
Local GPU |
gpuName |
N/A |
Displays the GPU used for rendering when Use GPU if available is enabled. Local GPU displays Not available when: • Use CPU is selected as the default blink device in the Preferences. • no suitable GPU was found on your system. • it was not possible to create a context for processing on the selected GPU, such as when there is not enough free memory available on the GPU. You can select a different GPU, if available, by navigating to the Preferences and selecting an alternative from the default blink device dropdown. Note: Selecting a different GPU requires you to restart Nuke before the change takes effect. |
Use GPU if available |
useGPUIfAvailable |
enabled |
When enabled, rendering occurs on the Local GPU specified, if available, rather than the CPU. Note: Enabling this option with no local GPU allows the script to run on the GPU whenever the script is opened on a machine that does have a GPU available.
|
Model File |
modelFile |
N/A |
The path to the CopyCat .cat file you want to use to apply the effect modeled by the network. You can enter the file path manually or click the directory icon to browse to the .cat file's location. |
Optimize for Speed and Memory |
inferencePrecision |
disabled |
When enabled, use 16-bit half-float precision instead of Nuke's standard 32-bit float precision. Enabling this control produces results more quickly, uses less GPU memory, and can handle larger images, but can result in artifacts with some trained networks. Note: This control is hidden when Use GPU if available is disabled. |