Dynamic quantization for deep neural network inference system and method

A method for dynamically quantizing feature maps of a received image. The method includes convolving an image based on a predicted maximum value, a predicted minimum value, trained kernel weights and the image data. The input data is quantized based on the predicted minimum value and predicted maxim...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Swami, Pramod Kumar, Eppa, Praveen, Desappan, Kumar, Mathew, Manu
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!