MyCaffe  1.12.2.41
Deep learning software for Windows C# programmers.
MyCaffe.solvers Namespace Reference

The MyCaffe.solvers namespace contains all solver classes, including the base Solver. More...

Classes

class  AdaDeltaSolver
 Use AdaDelta Solver which has gradient based optimization like SGD. More...
 
class  AdaGradSolver
 Use AdaGrad Solver based optimization like SGD that tries to find rarely seen features. More...
 
class  AdamSolver
 Use Adam Solver which uses gradient based optimization like SGD that includes 'adaptive momentum estimation' and can be thought of as a generalization of AdaGrad. More...
 
class  AdamWSolver
 Use AdamW Solver which uses gradient based optimization like Adam with a decoupled weight decay. More...
 
class  LBFGSSolver
 Optimizes the parameters of a Net using L-BFGS. This implementation is based on minFunc, by Marc Schmidt. More...
 
class  NesterovSolver
 Use Nesterov's accelerated gradient Solver, which is similar to SGD, but the error gradient is computed on the weights with added momentum. More...
 
class  RmsPropSolver
 Use RmsProp Solver which uses gradient based optimization like SGD. More...
 
class  SGDSolver
 Stochastic Gradient Descent solver with momentum updates weights by a linear combination of the negative gradient and the previous weight update. More...
 
class  Solver
 An interface for classes that perform optimization on Nets - this class serves as the base class for all solvers. More...
 

Detailed Description

The MyCaffe.solvers namespace contains all solver classes, including the base Solver.