Package org.deeplearning4j.nn.conf.layers

Class AbstractLSTM.Builder<T extends AbstractLSTM.Builder<T>>

    • Field Detail

      • forgetGateBiasInit

        protected double forgetGateBiasInit
        Set forget gate bias initalizations. Values in range 1-5 can potentially help with learning or longer-term dependencies.

      • gateActivationFn

        protected IActivation gateActivationFn
        Activation function for the LSTM gates. Note: This should be bounded to range 0-1: sigmoid or hard sigmoid, for example

      • helperAllowFallback

        protected boolean helperAllowFallback
        When using CuDNN and an error is encountered, should fallback to the non-CuDNN implementatation be allowed? If set to false, an exception in CuDNN will be propagated back to the user. If false, the built-in (non-CuDNN) implementation for LSTM/GravesLSTM will be used

    • Constructor Detail

      • Builder

        public Builder()

    • Method Detail

      • forgetGateBiasInit

        public T forgetGateBiasInit​(double biasInit)
        Set forget gate bias initalizations. Values in range 1-5 can potentially help with learning or longer-term dependencies.

      • gateActivationFunction

        public T gateActivationFunction​(String gateActivationFn)
        Activation function for the LSTM gates. Note: This should be bounded to range 0-1: sigmoid or hard sigmoid, for example
        Parameters:
        gateActivationFn - Activation function for the LSTM gates

      • gateActivationFunction

        public T gateActivationFunction​(Activation gateActivationFn)
        Activation function for the LSTM gates. Note: This should be bounded to range 0-1: sigmoid or hard sigmoid, for example
        Parameters:
        gateActivationFn - Activation function for the LSTM gates

      • gateActivationFunction

        public T gateActivationFunction​(IActivation gateActivationFn)
        Activation function for the LSTM gates. Note: This should be bounded to range 0-1: sigmoid or hard sigmoid, for example
        Parameters:
        gateActivationFn - Activation function for the LSTM gates

      • helperAllowFallback

        public T helperAllowFallback​(boolean allowFallback)
        When using a helper (CuDNN or MKLDNN in some cases) and an error is encountered, should fallback to the non-helper implementation be allowed? If set to false, an exception in the helper will be propagated back to the user. If false, the built-in (non-helper) implementation for LSTM/GravesLSTM will be used
        Parameters:
        allowFallback - Whether fallback to non-helper implementation should be used