Neural Network (Inference Overlay): Difference between revisions

From Tygron Preview Support Wiki
Jump to navigation Jump to search
Line 8: Line 8:


===Supported Convolution Types===
===Supported Convolution Types===
* Image Classification
# Image Classification
** Classifies a picture
** Classifies a picture
** Predicts probability of object
** Predicts probability of object
* Detection (with masks and bounding boxes)
# Detection (with masks and bounding boxes)
** Detects up to several objects in a picture
** Detects up to several objects in a picture
** Predicts probabilities of objects and where they are located
** Predicts probabilities of objects and where they are located

Revision as of 15:16, 8 October 2024

Selecting a Neural Network in the Inference Overlay Wizard

A Neural Network in the Tygron Platform is a pre-trained convolution network[1] that can be used by an AI Inference Overlay to classify or detect patterns and 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]).

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.

Supported Convolution Types

  1. Image Classification
    • Classifies a picture
    • Predicts probability of object
  1. Detection (with masks and bounding boxes)
    • Detects up to several objects in a picture
    • Predicts probabilities of objects and where they are located

See also

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)