class TemporalSubSampling

Class for doing sub-sampling over a sequence.

Inheritance:

Public Fields

int k_w

Kernel size

int d_t

Time translation after one application of the kernel

real* weights

weights[i] means kernel-weights for the i-th component of output frames.

real* der_weights

Derivatives associated to weights

real* biases

biases[i] is the bias for the i-th component of output frames

real* der_biases

Derivatives associated to biases

Public Methods

TemporalSubSampling(int input_frame_size, int k_w_=2, int d_t_=2)

Create a sub-sampling layer

Inherited from GradientMachine:

Public Fields

int n_inputs

int n_outputs

Parameters* params

Parameters* der_params

Sequence* beta

Public Methods

virtual void iterInitialize()

virtual void forward(Sequence* inputs)

virtual void backward(Sequence* inputs, Sequence* alpha)

virtual void setPartialBackprop(bool flag=true)

virtual void frameForward(int t, real* f_inputs, real* f_outputs)

virtual void frameBackward(int t, real* f_inputs, real* beta_, real* f_outputs, real* alpha_)

virtual void loadXFile(XFile* file)

virtual void saveXFile(XFile* file)

Inherited from Machine:

Public Fields

Sequence* outputs

Public Methods

virtual void reset()

virtual void setDataSet(DataSet* dataset_)

Inherited from Object:

Public Fields

Allocator* allocator

Public Methods

void addOption(const char* name, int size, void* ptr, const char* help="")

void addIOption(const char* name, int* ptr, int init_value, const char* help="")

void addROption(const char* name, real* ptr, real init_value, const char* help="")

void addBOption(const char* name, bool* ptr, bool init_value, const char* help="")

void addOOption(const char* name, Object** ptr, Object* init_value, const char* help="")

void setOption(const char* name, void* ptr)

void setIOption(const char* name, int option)

void setROption(const char* name, real option)

void setBOption(const char* name, bool option)

void setOOption(const char* name, Object* option)

void load(const char* filename)

void save(const char* filename)

void* operator new(size_t size, Allocator* allocator_=NULL)

void* operator new(size_t size, Allocator* allocator_, void* ptr_)

void operator delete(void* ptr)

Documentation

Class for doing sub-sampling over a sequence.

Then, for each component of output frames, it takes its associated input component and it computes the convolution of the input sequence with a kernel of size k_w, over the time, where the weights of the kernel are equals.

Note that, depending of the size of your kernel, several (last) frames of the input seqience could be lost.

Note also that no non-linearity is applied in this layer.

int k_w

Kernel size

int d_t

Time translation after one application of the kernel

real* weights

weights[i] means kernel-weights for the i-th component of output frames. weights[i] contains only one weight.

real* der_weights

Derivatives associated to weights

real* biases

biases[i] is the bias for the i-th component of output frames

real* der_biases

Derivatives associated to biases

TemporalSubSampling(int input_frame_size, int k_w_=2, int d_t_=2)

Create a sub-sampling layer

This class has no child classes.

Author:

Ronan Collobert (collober@idiap.ch)

Alphabetic index HTML hierarchy of classes or Java