AI Suite: Difference between revisions

From Tygron Support wiki
Jump to navigation Jump to search
← Older edit
Frank@tygron.nl (talk | contribs)
Tygron, Tygron_admin, Bureaucrats, Interface administrators, Administrators
47,790 edits
No edit summary
 
(33 intermediate revisions by 3 users not shown)
Line 1: Line 1:
The Tygron AI Suite consist of a several tools that can help when using an existing [[Neural Network]] in an [[Inference Overlay]] or when creating a new one.
{{Beta functionality}}


==Steps for creating you own model==
The Tygron AI Suite provides a comprehensive set of tools to assist you in all stages of creating, training, and utilizing your own [[Region-based Convolutional Neural Network (Inference Overlay)|RCNN]] within an [[Inference Overlay]] on our dedicated [[GPU]] cloud.
In order to create your own AI model based on a [[Neural Network]] you have to follow these steps.


* Start with a definition of which objects you want to detect. For example trees, cars, solar panels, etc.
[[File:aiflow.png|center|800px]]
* Now create one or more projects (with a good variation) and manually create your training data by creating areas containing outlining these objects. See this how to how this can be done in QGIS.
 
* Devide these objects in two group a TRAIN and TEST dataset that can be exported. See thi manual.
==Creating your own model==
* After exporting follow these steps to train your [[Neural Network]] resulting in a [[ONNX]] file.
Follow these steps to create an AI model based on a [[Region-based Convolutional Neural Network (Inference Overlay)|RCNN]].
* Then import the [[ONNX]] back into the [[software]] an run it in an Inference Overlay.
 
* Finally validate the results on a different project and iterate back to a previous step if needed.
# Start with a definition of which objects you want to detect. For example trees, cars, solar panels, etc. These can also be subsets for example trees can also be subdivided into palms, pines, etc.
# Create one or more varied projects and manually define training data by outlining the target objects. Follow: [[How to create AI training data with QGIS]]
# Create two groups of objects a TRAIN and TEST dataset that can be exported. Follow: [[How to export AI Training Data]]
# After exporting you can start training your [[Region-based Convolutional Neural Network (Inference Overlay)|RCNN]] resulting in a [[ONNX]] file. Follow: [[How to train your own AI model for an Inference Overlay]].
# Import the [[ONNX]] back into the {{software}} as a [[Region-based Convolutional Neural Network (Inference Overlay)|Region-based Convolutional Neural Network]] and assign it to an [[Inference Overlay]]. For example: [[How to detect foliage using an Inference Overlay]]
# Finally validate the results on a different project and iterate back to a previous step if needed. Follow: [[How to evaluate an AI model]]
 
==Apply a model==
* Apply a custom-created or existing [[ONNX]] file as a [[Region-based Convolutional Neural Network (Inference Overlay)|Region-based Convolutional Neural Network]] for other projects with the [[Inference Overlay]]s. For example: [[How to detect foliage using an Inference Overlay]]
 
{{article end
|seealso=
* [[Inference Overlay]]
* [[Region-based Convolutional Neural Network (Inference Overlay)]]
* [[Model attributes (Inference Overlay)]]
* [[Region-based Convolutional Neural Network (Inference Overlay)|RCNN]]
* [[ONNX]]
* [[PyTorch]]
* [[Demo Training Data Project]]
|api=
* [[Api session event editor neuralnetwork add]]
* [[Api session event editor overlay set neural network]]
}}

Latest revision as of 13:29, 8 October 2026

This functionality is currently in BETA.
Read more about Beta features.


The Tygron AI Suite provides a comprehensive set of tools to assist you in all stages of creating, training, and utilizing your own RCNN within an Inference Overlay on our dedicated GPU cloud.

Creating your own model

Follow these steps to create an AI model based on a RCNN.

  1. Start with a definition of which objects you want to detect. For example trees, cars, solar panels, etc. These can also be subsets for example trees can also be subdivided into palms, pines, etc.
  2. Create one or more varied projects and manually define training data by outlining the target objects. Follow: How to create AI training data with QGIS
  3. Create two groups of objects a TRAIN and TEST dataset that can be exported. Follow: How to export AI Training Data
  4. After exporting you can start training your RCNN resulting in a ONNX file. Follow: How to train your own AI model for an Inference Overlay.
  5. Import the ONNX back into the Tygron Platform as a Region-based Convolutional Neural Network and assign it to an Inference Overlay. For example: How to detect foliage using an Inference Overlay
  6. Finally validate the results on a different project and iterate back to a previous step if needed. Follow: How to evaluate an AI model

Apply a model

See also

API Endpoints

Retrieved from "https://support.tygron.com/w/index.php?title=AI_Suite&oldid=94800"