[Nengo-DL]: Why is the output of `converter.net.all_nodes` different upon inclusion/exclusion of kernel regularizer?

[zerone]

@xchoo

I’ll have to double check with the NengoDL dev on Monday to see if this is an oversight or bug, or perhaps there’s another way to use the data generator with the sim.fit function within NengoDL

Here’s where I learned how to do batch training, maybe this will help you get some context.

@xchoo

This means that the way the code is written, it might fail on the second “run” of a cell (only in a Jupyter notebook though), because on subsequent runs, the Input layer gets named "input_2" then "input_3", etc.

It fails exactly as you mentioned, so I need to restart the kernel and run it afresh. Labeling the layers will help.

@xchoo

It’s likely that in NengoDL, when passing the “input layers” to the TensorFlow backend, it’s only considering the purely output nodes as input layers, and thus, the TensorFlow backend is only expecting inputs data definitions for those nodes.

Got your point. Thanks! BTW, I guess this following small question was missed in details probably.

@zerone

One extra small question though, does making nengo_dl.configure_settings(stateful=False) during training affect the training process in any way?

Please let me know.