train_one_net.m

Trains a network and writes a file with the specified number. If the specified file exists, the function will load that network file and continue training.

Syntax

   train_one_net(parameters,batch_size,file_number)

Parameters

   parameters  - library and network specification struc-
                 ture (see deer_lib_gen.m)

   batch_size  - the number of training examples randomly 
                 generated at each iteration; must fit in
                 memory

   file_number - the network object will be saved into a
                 file with this number as the name

Outputs

This function writes a MAT file with the network object and the parameters structure.

Notes

1. A strong NVidia GPU is required - at least a Titan V
2. If the file pre-exists, the network will be loaded and used as the initial guess.

See also

deer_lib_gen.m, deernet.m, dist_range.m, elexsys2deernet.m, process_using.m, Neural network module, Built-in_experiments

Version 2.8, authors: Ilya Kuprov, Steve Worswick, Jake Keeley, Tajwar Choudhury