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?

回答(0 个)

类别

帮助中心File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

Community Treasure Hunt

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

Start Hunting!

Translated by