Package com.googlecode.fannj
Class Fann
java.lang.Object
com.googlecode.fannj.Fann
- Direct Known Subclasses:
FannShortcut
,FannSparse
A standard fully connected back-propagation neural network.
Not thread safe.
A Java binding to the Fast Artificial Neural Network (FANN) native library.This class invokes native code. You must call close() to prevent memory leakage.
- See Also:
-
Field Summary
Fields -
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionprotected void
void
close()
Frees allocated memory.protected static com.sun.jna.Pointer
fann_create_from_file
(String configuration_file) protected static com.sun.jna.Pointer
fann_create_shortcut_array
(int numLayers, int[] layers) protected static com.sun.jna.Pointer
fann_create_sparse_array
(float connection_rate, int numLayers, int[] layers) protected static com.sun.jna.Pointer
fann_create_standard_array
(int numLayers, int[] layers) protected static void
fann_destroy
(com.sun.jna.Pointer ann) protected static float
fann_get_MSE
(com.sun.jna.Pointer ann) protected static com.sun.jna.Pointer
fann_get_neuron
(com.sun.jna.Pointer ann, int layer, int neuron) protected static int
fann_get_num_input
(com.sun.jna.Pointer ann) protected static int
fann_get_num_output
(com.sun.jna.Pointer ann) protected static int
fann_get_total_neurons
(com.sun.jna.Pointer ann) protected static com.sun.jna.Pointer
fann_run
(com.sun.jna.Pointer ann, float[] input) protected static int
protected static void
fann_set_activation_function
(com.sun.jna.Pointer ann, int activation_function, int layer, int neuron) protected static void
fann_set_activation_steepness
(com.sun.jna.Pointer ann, float steepness, int layer, int neuron) void
finalize()
Callclose()
on garbage collection to catch memory leaks.int
int
int
float[]
run
(float[] input) Run the ANN on a set of inputs.boolean
Save this FANN to a file.
-
Field Details
-
ann
protected com.sun.jna.Pointer ann
-
-
Constructor Details
-
Fann
protected Fann() -
Fann
Load an existing FANN definition from a file- Parameters:
file
-
-
Fann
Create a new ANN with the provided layers.- Parameters:
layers
-
-
-
Method Details
-
addLayers
-
getNumInputNeurons
public int getNumInputNeurons() -
getNumOutputNeurons
public int getNumOutputNeurons() -
getTotalNumNeurons
public int getTotalNumNeurons() -
save
Save this FANN to a file.- Parameters:
file
-- Returns:
- true on success
-
run
public float[] run(float[] input) Run the ANN on a set of inputs.- Parameters:
input
- length == numInputNeurons- Returns:
- the output of the ANN. (length = numOutputNeurons)
-
close
public void close()Frees allocated memory.
You must call this method when you are finished to prevent memory leaks. -
finalize
Callclose()
on garbage collection to catch memory leaks. -
fann_create_standard_array
protected static com.sun.jna.Pointer fann_create_standard_array(int numLayers, int[] layers) -
fann_create_sparse_array
protected static com.sun.jna.Pointer fann_create_sparse_array(float connection_rate, int numLayers, int[] layers) -
fann_create_shortcut_array
protected static com.sun.jna.Pointer fann_create_shortcut_array(int numLayers, int[] layers) -
fann_get_MSE
protected static float fann_get_MSE(com.sun.jna.Pointer ann) -
fann_run
protected static com.sun.jna.Pointer fann_run(com.sun.jna.Pointer ann, float[] input) -
fann_destroy
protected static void fann_destroy(com.sun.jna.Pointer ann) -
fann_get_num_input
protected static int fann_get_num_input(com.sun.jna.Pointer ann) -
fann_get_num_output
protected static int fann_get_num_output(com.sun.jna.Pointer ann) -
fann_get_total_neurons
protected static int fann_get_total_neurons(com.sun.jna.Pointer ann) -
fann_set_activation_function
protected static void fann_set_activation_function(com.sun.jna.Pointer ann, int activation_function, int layer, int neuron) -
fann_set_activation_steepness
protected static void fann_set_activation_steepness(com.sun.jna.Pointer ann, float steepness, int layer, int neuron) -
fann_get_neuron
protected static com.sun.jna.Pointer fann_get_neuron(com.sun.jna.Pointer ann, int layer, int neuron) -
fann_create_from_file
-
fann_save
-