andruekonst / constrainet Goto Github PK

The ConstraiNetLayer you proposed is very good. I tried to add it to the neural network, but I found that this layer seems to be calculated only through CPU. Doesn't ConstraiNetLayer support CUDA and GPU?
Another question is that numpy is used to define constraints in the ConstraiNetLayer layer. Will this cause the data format conversion between numpy and tensor to consume a lot of time? Because I found the following warning in my calculation example:
UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor.
Forgive me for not having deep mathematical knowledge :)

Hi,

I am interested in your work and I was wondering if you could point me to an example where ConstraiNet is used for a constraint of the neural network that is based on the input to the network.

I want to use your method to ensure a constraint Ax<=b is met, however, the A matrix depends on the input whereas b is fixed.

Thanks,
Arnaud