#include <pooling.hpp>
◆ Pooling()
Layer::Pooling::Pooling |
( |
size_t |
nf, |
|
|
size_t |
ni, |
|
|
size_t |
nj, |
|
|
size_t |
p, |
|
|
size_t |
q |
|
) |
| |
|
inline |
◆ ~Pooling()
Layer::Pooling::~Pooling |
( |
| ) |
|
|
inline |
◆ back_propagation()
Apply back propagation algorithm on the delta output vector d. Used the input vector stored in x_in_ref during feedforward. Return a reference to the computed (and stored) input delta vector. Nabla vectors must be computed here.
Implements Layer::Layer.
◆ feed_forward()
Apply the layer to the input vector x
. Vectors x_in_ref
and x_out
must be updated in consequence. Return a reference to x_out.
Implements Layer::Layer.
◆ init_nabla()
void Layer::Pooling::init_nabla |
( |
| ) |
|
|
inlineoverridevirtual |
Initialize nabla vectors which are used during gradient descent.
Implements Layer::Layer.
◆ update()
void Layer::Pooling::update |
( |
Real |
eta | ) |
|
|
inlineoverridevirtual |
Update layer parameters using gradient descent algorithm with learning rate eta.
Implements Layer::Layer.
◆ mi
size_t Layer::Pooling::mi |
◆ mj
size_t Layer::Pooling::mj |
◆ nf
size_t Layer::Pooling::nf |
◆ ni
size_t Layer::Pooling::ni |
◆ nj
size_t Layer::Pooling::nj |
The documentation for this class was generated from the following files: