Output tensor (Inference Overlay)

An Output tensor is a multi-dimensional data array that serves as output for Neural Networks. Generally these output tensors are results of the operations applied by the convolution neural network on the input tensors. Depending on the type of neural network, multiple type of output tensors can be generated.

An output tensor link in the Inference Overlay Wizard.

In the Tygron Platform, the following output tensors are supported:

• BOXES
• LABELS
• MASKS
• SCORES

Notes

• The Inference Overlay wizard will report an issue when a result type is referenced by a tensor link but is not yet added to the Inference Overlay.

---

Inference Overlay

Group

Model attributes

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