hypnettorch - Hypernetworks in PyTorch
This package provides functionalities to easily work with hypernetworks in PyTorch. A hypernetwork 
is a neural network with parameters 
that generates the parameters 
of another neural network 
, called main network. These two network types require specialized implementations. For instance, a main network must have the ability to receive its own weights as additional input to the forward method (see subpackage mnets). A collection of different hypernetwork implementations can be found in subpackage hnets.
Installation
See here.
Usage
Check out the tutorials, especially the getting started tutorial.
You can also check out example implementations that make use of hypnettorch.