Region-based Convolutional Neural Network (Inference Overlay): Difference between revisions

From Tygron Support wiki
Jump to navigation Jump to search
← Older editNewer edit →
Frank@tygron.nl (talk | contribs)
Tygron, Tygron_admin, Bureaucrats, Interface administrators, Administrators
46,429 edits
Maxim@tygron.com (talk | contribs)
Tygron, Tygron_admin, Bureaucrats, Administrators
5,955 edits
No edit summary
No edit summary
Line 1: Line 1:
[[File:inference_overlay_neural_network.jpg|thumb|right|Selecting a Neural Network in the [[Inference Overlay]] Wizard]]
[[File:inference_overlay_neural_network.jpg|thumb|right|Selecting a Neural Network in the [[Inference Overlay]] Wizard]]
A [[Neural Network]] in the [[Inference Overlay|AI Inference Overlay]] is a pre-trained Region-based Convolutional Neural Networks (RCNN) {{ref|Cheatsheet}} that can be used to classify or detect features given one or more input [[Overlay]]s.
A [[Neural Network]] in the [[Inference Overlay|AI Inference Overlay]] is a pre-trained Region-based Convolutional Neural Network (RCNN) {{ref|Cheatsheet}} that can be used to classify or detect features given one or more input [[Overlay]]s.
Neural Networks are stored in the {{software}} as data [[item]]s with a reference to an [[ONNX]]-file (Open Neural Network Exchange format{{ref|ONNX}}) visible via Netron{{ref|Netron}}.
Neural Networks are stored in the {{software}} as data [[item]]s with a reference to an [[ONNX]]-file (Open Neural Network Exchange format{{ref|ONNX}}) visible via Netron{{ref|Netron}}.


[[Input tensor (Inference Overlay)|Input]] and [[Output tensor (Inference Overlay)|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.
[[Input tensor (Inference Overlay)|Input]] and [[Output tensor (Inference Overlay)|output]] for neural networks are 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]]. Neural Networks can indicate what type of network they are by defining the [[Inference mode (Inference Overlay)|INFERENCE_MODE]] attribute in their metadata.
Whether a Neural Network classifies or detects objects given an input depends on its inference model. Such a model is created using AI software, such as [[PyTorch]]. Neural Networks can indicate what type of network they are by defining the [[Inference mode (Inference Overlay)|INFERENCE_MODE]] attribute in their metadata.


===Supported Convolution Types===
===Supported Convolution Types===
Line 15: Line 15:


===Parameters in Metadata===
===Parameters in Metadata===
Neural Networks can also store default parameters for Inference Overlay, such that they are setup more properly once set for an Inference Overlay. The following parameters are used:
Neural Networks can also store default parameters for Inference Overlay, such that they are set up more properly once set for an Inference Overlay. The following parameters are used:
* Producer and version
* Producer and version
* Description
* Description
Line 67: Line 67:


|api=*[[Api session items neuralnetworks]]
|api=*[[Api session items neuralnetworks]]
*[[Api session event editor neuralnetwork]]
}}
}}


{{InferenceOverlay nav}}
{{InferenceOverlay nav}}

Revision as of 07:09, 6 July 2026

Selecting a Neural Network in the Inference Overlay Wizard

A Neural Network in the AI Inference Overlay is a pre-trained Region-based Convolutional Neural Network (RCNN) [1] that can be used to classify or detect features given one or more input Overlays. Neural Networks are stored in the Tygron Platform as data items with a reference to an ONNX-file (Open Neural Network Exchange format[2]) visible via Netron[3].

Input and output for neural networks are 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 is created using AI software, such as PyTorch. Neural Networks can indicate what type of network they are by defining the INFERENCE_MODE attribute in their metadata.

Supported Convolution Types

  1. Image Classification
    • Classifies a picture using labels, in combination with a predicted probability per label
  2. Detection (with masks and bounding boxes)
    • Detects up to several features in a picture
    • Predicts probabilities of features and where they are located

Parameters in Metadata

Neural Networks can also store default parameters for Inference Overlay, such that they are set up more properly once set for an Inference Overlay. The following parameters are used:

Notes

  • Neural networks that are not referenced by an AI Inference Overlay may be removed from your project when a project is saved.

How-to's

See also

API Endpoints

References

  1. ↑ Cheatsheet ∙ Found at: https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-convolutional-neural-networks ∙ (last visited: 2024-09-21)
  2. ↑ ONNX ∙ Found at: https://onnx.ai/ ∙ (last visited: 2024-09-21)
  3. ↑ Netron ∙ Found at: https://netron.app/ ∙ (last visited: 2024-10-14)
Inference Overlay
Group
Inference
Neural Network • Input tensor • Output tensor
Model attributes
Box overlap • Inference mode • Mask threshold • Prioritize labels • Score threshold • Stride fraction
Prequels
A • B
Result types
Boxes • Labels • Masks • Scores • Debug gt instances • Center points
Neural Networks
Foliage • Solar panels
Retrieved from "https://support.tygron.com/w/index.php?title=Region-based_Convolutional_Neural_Network_(Inference_Overlay)&oldid=88648"