AI Suite: Difference between revisions
Jump to navigation
Jump to search
No edit summary |
No edit summary |
||
| (7 intermediate revisions by 2 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. | The Tygron AI Suite consist of a several tools that can help when using an existing [[Region-based Convolutional Neural Network (Inference Overlay)|Region-based Convolutional Neural Network (RCNN)]] in an [[Inference Overlay]] or when creating a new one. | ||
== | ==Creating you own model== | ||
In order to create your own AI model based on a [[Neural Network]] you have to follow these steps. | In order to create your own AI model based on a [[Region-based Convolutional Neural Network (Inference Overlay)|RCNN]] you have to follow these steps. | ||
# 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 sub dived into palms, pines, etc. | # 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 sub dived into palms, pines, etc. | ||
# Now create one or more projects (with a good variation) and manually create your training data by creating areas | # Now create one or more projects (with a good variation) and manually create your training data by creating areas outlining these objects. Follow: [[How to create AI training data with QGIS]] | ||
# Create | # 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 [[Neural Network]] resulting in a [[ONNX]] file. Follow: [[How to train your own AI model for an Inference Overlay]]. | # 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]]. | ||
# Then import the [[ONNX]] back into the {{software}} an run it in an Inference Overlay. For example: [[How to detect foliage using an Inference Overlay]] | # Then import the [[ONNX]] back into the {{software}} an run it in 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]] | # 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 model== | ||
* When you have created your own model or by selecting an existing [[ONNX]] file you can apply it to other projects using the [[Inference Overlay]]. | * When you have created your own model or by selecting an existing [[ONNX]] file you can apply it to other projects using the [[Inference Overlay]]. For example: [[How to detect foliage using an Inference Overlay]] | ||
{{article end | {{article end | ||
|seealso= | |seealso= | ||
* [[Model attributes (Inference Overlay)]] | * [[Model attributes (Inference Overlay)]] | ||
* [[Neural Network]] | * [[Region-based Convolutional Neural Network (Inference Overlay)|RCNN]] | ||
* [[ONNX]] | * [[ONNX]] | ||
* [[PyTorch]] | * [[PyTorch]] | ||
* [[Demo Training Data Project]] | * [[Demo Training Data Project]] | ||
}} | }} | ||
Latest revision as of 16:04, 29 June 2026
The Tygron AI Suite consist of a several tools that can help when using an existing Region-based Convolutional Neural Network (RCNN) in an Inference Overlay or when creating a new one.
Creating you own model
In order to create your own AI model based on a RCNN you have to follow these steps.
- 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 sub dived into palms, pines, etc.
- Now create one or more projects (with a good variation) and manually create your training data by creating areas outlining these 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 RCNN resulting in a ONNX file. Follow: How to train your own AI model for an Inference Overlay.
- Then import the ONNX back into the Tygron Platform an run it in 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
- When you have created your own model or by selecting an existing ONNX file you can apply it to other projects using the Inference Overlay. For example: How to detect foliage using an Inference Overlay