From Spinach Documentation Wiki
Revision as of 13:03, 6 August 2019 by Kuprov (talk | contribs) (Arguments)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Generates a training library, trains a network and writes it into a file with the specified number. If the specified file exists, the function will load that network file and continue training.




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

  trsets      - sizes of independent randomly generated 
                training libraries to sequentially train
                against. [160k 160k 160k 160k 160k 160k] 
                works well on a Tesla V100 card.

  file_number - the network object will be saved into a
                file with this number as the name, this
                file also serves as a restart checkpoint.

Four more fields are required in the parameters structure:

 parameters.layer_sizes - number of neurons per layer, a
                          row vector where the number of
                          elements is the number of hid-
                          den layers desired.
 parameters.lastlayer   - activation function to use in 
                          the output layer ('tansig' or
 parameters.method      - training algorithm ('trainscg'
                          is recommended).

 parameters.nobias      - if set to 1, the network would
                          not have bias vectors


This function writes a .mat file with the network object.


The example below will train a single network using the parameters given in the netset_params.m file for the network ensemble optimized for any peak width.

	% Load training set parameters

	% Specify the sizes of training databases to train against
	trsets=[160e4 160e4 160e4 160e4];

	% Run the network training for a a single network

The function will save the the network into 111.mat file.


A CUDA capable NVidia GPU is required.

See also

deer_lib_gen.m, netset_params.m, deernet.m, netset_curate.m, process_using.m

Version 2.4, authors: Ilya Kuprov, Steve Worswick