Neural Network: Difference between revisions

From Tygron Preview Support Wiki
Jump to navigation Jump to search
No edit summary
Tag: New redirect
 
(5 intermediate revisions by one other user not shown)
Line 1: Line 1:
A Neural Network in the {{software}} is a pre-trained network that can be used by an [[Inference Overlay]] to classify or detect patterns and features given one or more input [[Overlay]]s.
#REDIRECT [[Neural Network (Inference Overlay)]]
Neural Networks are stored in the {{software}} as data [[item]]s with a reference to an [[ONNX]]-file (Open Neural Network Exchange format).
 
Input and output for neural networks is handled using data tensors. These tensors are multi-dimensional data arrays. They are automatically identified when selecting or adding a new Neural Network.
 
Whether a Neural Network classifies or detects objects given an input depends on its inference model. Such a model consists using AI-software, such as PyTorch.
 
{{article end
|seealso=
* [[Inference Overlay]]  
* [[ONNX]]
}}

Latest revision as of 14:30, 8 October 2024