Uses of Class
org.deeplearning4j.nn.api.FwdPassType

Packages that use FwdPassType

Package	Description
org.deeplearning4j.nn.api
org.deeplearning4j.nn.graph
org.deeplearning4j.nn.multilayer

Uses of FwdPassType in org.deeplearning4j.nn.api

Methods in org.deeplearning4j.nn.api that return FwdPassType

Modifier and Type	Method and Description
static FwdPassType	FwdPassType.valueOf(String name) Returns the enum constant of this type with the specified name.
static FwdPassType[]	FwdPassType.values() Returns an array containing the constants of this enum type, in the order they are declared.

Uses of FwdPassType in org.deeplearning4j.nn.graph

Methods in org.deeplearning4j.nn.graph with parameters of type FwdPassType

Modifier and Type	Method and Description
protected Map<String,org.nd4j.linalg.api.ndarray.INDArray>	ComputationGraph.ffToLayerActivationsDetached(boolean train, FwdPassType fwdPassType, boolean storeLastForTBPTT, int layerIndex, int[] excludeIdxs, org.nd4j.linalg.api.ndarray.INDArray[] features, org.nd4j.linalg.api.ndarray.INDArray[] fMask, org.nd4j.linalg.api.ndarray.INDArray[] lMask, boolean clearLayers) Feed-forward through the network - returning all array activations detached from any workspace.
protected Map<String,org.nd4j.linalg.api.ndarray.INDArray>	ComputationGraph.ffToLayerActivationsInWS(boolean train, int layerIndex, int[] excludeIdxs, FwdPassType fwdPassType, boolean storeLastForTBPTT, org.nd4j.linalg.api.ndarray.INDArray[] input, org.nd4j.linalg.api.ndarray.INDArray[] fMask, org.nd4j.linalg.api.ndarray.INDArray[] lMask, boolean clearInputs) Feed-forward through the network - if workspaces are used, all returned activations will be present in workspace WS_ALL_LAYERS_ACT. Note: if using workspaces for training, requires that WS_ALL_LAYERS_ACT is open externally.
protected org.nd4j.linalg.api.ndarray.INDArray[]	ComputationGraph.outputOfLayersDetached(boolean train, FwdPassType fwdPassType, int[] layerIndexes, org.nd4j.linalg.api.ndarray.INDArray[] features, org.nd4j.linalg.api.ndarray.INDArray[] fMask, org.nd4j.linalg.api.ndarray.INDArray[] lMasks, boolean clearLayerInputs, boolean detachedInputs) Provide the output of the specified layers, detached from any workspace.

Uses of FwdPassType in org.deeplearning4j.nn.multilayer

Methods in org.deeplearning4j.nn.multilayer with parameters of type FwdPassType

Modifier and Type	Method and Description
protected List<org.nd4j.linalg.api.ndarray.INDArray>	MultiLayerNetwork.ffToLayerActivationsDetached(boolean train, FwdPassType fwdPassType, boolean storeLastForTBPTT, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray fMask, org.nd4j.linalg.api.ndarray.INDArray lMask, boolean clearInputs) Feed-forward through the network - returning all array activations in a list, detached from any workspace.
protected List<org.nd4j.linalg.api.ndarray.INDArray>	MultiLayerNetwork.ffToLayerActivationsInWs(int layerIndex, FwdPassType fwdPassType, boolean storeLastForTBPTT, org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray fMask, org.nd4j.linalg.api.ndarray.INDArray lMask) Feed-forward through the network at training time - returning a list of all activations in a workspace (WS_ALL_LAYERS_ACT) if workspaces are enabled for training; or detached if no workspaces are used. Note: if using workspaces for training, this method requires that WS_ALL_LAYERS_ACT is open externally. If using NO workspaces, requires that no external workspace is open Note that this method does NOT clear the inputs to each layer - instead, they are in the WS_ALL_LAYERS_ACT workspace for use in later backprop.
protected org.nd4j.linalg.api.ndarray.INDArray	MultiLayerNetwork.outputOfLayerDetached(boolean train, FwdPassType fwdPassType, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray featureMask, org.nd4j.linalg.api.ndarray.INDArray labelsMask) Provide the output of the specified layer, detached from any workspace.