Daniel Rasmussen

There's two sides to this though, because I also find it irritating that every time I close Nengo it asks me if I want to save (as 99% of the...

It's not the best integration (I don't think debugging or anything like that will work), but if you just want to be able to run nengo scripts from eclipse, then...

`Conv2D` was removed in the nengo-loihi 0.6.0 release, so you will have to downgrade `nengo-loihi` to 0.5.0 (`pip install "nengo-loihi

You can make the layer non-trainable by passing trainable=False to the constructor (that's a general Keras feature, not something specific to keras-spiking). But allowing a single tau value would be...

Hmm I'm not positive whether modifying tau_var.trainable after the initial build would have an effect or not, you'd have to experiment. But yeah trainable=False wouldn't work for that case.

2. (Homogeneous time constant) can now be done by setting `tau_constraint=keras_spiking.constraints.Mean()`

Yes, the spiking activation layers can be used with any other layer types. In that example you linked you could replace the `Dense` layers with `Conv2D` layers (and remove the...

 Screen capture attached. You can't really see the border between my monitors, but basically it's right at the left edge of the overlay box. As I drag the Marvel...