Class Adam
java.lang.Object
ai.beestream.jitnn.nn.optim.Optimizer
ai.beestream.jitnn.nn.optim.Adam
Adam (Kingma and Ba) with L2 weight decay, or AdamW (decoupled decay) via
adamW(List, float, float); with
amsgrad, AMSGrad's running maximum of the second moment (Reddi et al.).-
Field Summary
-
Constructor Summary
ConstructorsConstructorDescriptionAdam with PyTorch's defaults: betas 0.9 and 0.999, eps 1e-8, no weight decay.Adam(List<Tensor> params, float lr, float beta1, float beta2, float eps, float weightDecay, boolean decoupled) Adam with the given hyper-parameters;decoupledmakes the weight decay AdamW's.Adam(List<Tensor> params, float lr, float beta1, float beta2, float eps, float weightDecay, boolean decoupled, boolean amsgrad) Adam with the given hyper-parameters;decoupledmakes the weight decay AdamW's,amsgraduses AMSGrad's maximum of the second moment. -
Method Summary
Methods inherited from class Optimizer
clipGradNorm, learningRate, loadScalars, loadStateDict, saveScalars, setLearningRate, stateDict, takeStats, zeroGrad
-
Constructor Details
-
Adam
-
Adam
-
Adam
-
-
Method Details
-
adamW
-
step
-
state
-