Output tensor (Inference Overlay): Difference between revisions

From Tygron Preview Support Wiki
Jump to navigation Jump to search
(Created page with "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. thumb|right|An output tensor link in the Inference Overlay Wizard. In the {{software}}, the following ou...")
 
No edit summary
 
(3 intermediate revisions by the same user not shown)
Line 1: Line 1:
An Output tensor is a multi-dimensional data array that serves as output for [[Neural Network]]s. 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 is a multi-dimensional data array that serves as output for [[Neural Network]]s. Generally these output tensors are results of the operations applied by the convolution neural network on the [[Input tensor (Inference Overlay)|input tensors]]. Depending on the type of neural network, multiple type of output tensors can be generated.


[[File:inference_overlay_wizard_tensor_link_ouput.jpg|thumb|right|An output tensor link in the Inference Overlay Wizard.]]
[[File:inference_overlay_wizard_tensor_link_ouput.jpg|thumb|right|An output tensor link in the Inference Overlay Wizard.]]
In the {{software}}, the following output tensors are supported:
In the {{software}}, the following output tensors are supported:
* BBOX
* [[Boxes result type (Inference Overlay)|BOXES]]
* LABELS
* [[Labels result type (Inference Overlay)|LABELS]]
* MASKS
* [[Masks result type (Inference Overlay)|MASKS]]
* SCORES
* [[Scores result type (Inference Overlay)|SCORES]]


{{article end
{{article end
|notes=*The inference overlay wizard will report an issue when a prequel is referenced by a tensor link and it is not yet specified for the Inference Overlay.
|notes=*The inference overlay wizard will report an issue when a result type is referenced by a tensor link and it is not yet add to the Inference Overlay.
}}
}}
{{InferenceOverlay nav}}
{{InferenceOverlay nav}}

Latest revision as of 10:19, 9 October 2024

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:

Notes

  • The inference overlay wizard will report an issue when a result type is referenced by a tensor link and it is not yet add to the Inference Overlay.