Saving weights after each epoch

[nikos-kekatos]

It does not seem to exist a default option with Deep Learning Toolbox in Matlab.

Workaround
One way to see the weights after every epoch is to set the network to only train one epoch at a time, and then to use the 'getwb' command.

Caveat
We will not get the same performance as N_epochs=100 and N_loop=1 since the method train reinitialises internal training parameters at each call.

• Look at checkpointPath.
• Check references: [1],[2],[3]