How to train an Autoencoder object without loading complete image data into memory?

In function
autoenc = trainAutoencoder(X)
X could be a Matrix or cell containing matrix. is there any alternative of training the autoenc with image database, where cell X just contain the location/address of image not the complete data? Also is it possible to include some custom image read function to manipulate/modify actual image data while reading/loading it?

Risposte (0)

Categorie

Scopri di più su Deep Learning Toolbox in Centro assistenza e File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by