FluxNLPModels.jl
Compatibility
Julia ≥ 1.6.
How to install
This module can be installed with the following command:
pkg> add FluxNLPModels
Synopsis
FluxNLPModels exposes neural network models as optimization problems conforming to the NLPModels API. FluxNLPModels is an interface between Flux.jl's classification neural networks and NLPModels.jl.
A FluxNLPModel
gives the user access to:
- The values of the neural network variables/weights
w
; - The value of the objective/loss function
L(X, Y; w)
atw
for a given minibatch(X,Y)
; - The gradient
∇L(X, Y; w)
of the objective/loss function atw
for a given minibatch(X,Y)
.
In addition, it provides tools to:
- Switch the minibatch used to evaluate the neural network;
- Retrieve the current minibatch ;
- Measure the neural network's loss at the current
w
.
Bug reports and discussions
If you encounter any bugs or have suggestions for improvement, please open an issue. For general questions or discussions related to this repository and the JuliaSmoothOptimizers organization, feel free to start a discussion here.