AI Suite: Difference between revisions
Jump to navigation
Jump to search
No edit summary |
|||
| Line 5: | Line 5: | ||
[[File:aiflow.png|center|800px]] | [[File:aiflow.png|center|800px]] | ||
==Creating | ==Creating your own model== | ||
Follow these steps to create an AI model based on a [[Region-based Convolutional Neural Network (Inference Overlay)|RCNN]]. | Follow these steps to create an AI model based on a [[Region-based Convolutional Neural Network (Inference Overlay)|RCNN]]. | ||
# 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 | # 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 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]] | # 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]]. | # 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}} | # Then import the [[ONNX]] back into the {{software}} and 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]] | ||
Revision as of 13:23, 8 October 2026
This functionality is currently in BETA.
Read more about Beta features.
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.
- 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 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 and 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
- Apply a custom-created or existing ONNX model to other projects using the Inference Overlay. For example: How to detect foliage using an Inference Overlay