AUGMENTATION AND LAYER FREEZING FOR NEURAL NETWORK MODEL TRAINING

AUGMENTATION AND LAYER FREEZING FOR NEURAL NETWORK MODEL TRAINING

A method for training an image processor having a neural network model is described. A first training set of images having a first image resolution is generated. A second training set of images having a second image resolution is generated. The second image resolution is larger than the first image...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LUO, Linjie, LIU, Jing, SANG, Shen, ZHI, Tiancheng
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A method for training an image processor having a neural network model is described. A first training set of images having a first image resolution is generated. A second training set of images having a second image resolution is generated. The second image resolution is larger than the first image resolution. The neural network model of the image processor is trained using the first training set of images during a first training session. The neural network model of the image processor is trained using the second training set of images during a second training session after the first training session.