chabisik/cppbasedann
1
0
Förgrening 0
Kod Ärenden Pull-förfrågningar Släpp Wiki Aktiviteter

Adding ANN print function

Bläddra i källkod
This commit is contained in:
chabisik 2022-01-09 14:56:35 +01:00
förälder 26ae13b72e
incheckning 639694d05c
3 ändrade filer med 44 tillägg och 46 borttagningar
Show stats Download patch file Download diff file Expand all files Collapse all files

6
main.cpp
Visa fil

@ -4,7 +4,7 @@
#include "myclasses.h" #include "myclasses.h"
#include <vector> #include <vector>
#include <iterator>
using namespace std; using namespace std;
@ -26,6 +26,8 @@ int main(int argc, char *argv[])
n0.activate(it); n0.activate(it);
cout << "is = " << n0.get_output() << endl;*/ cout << "is = " << n0.get_output() << endl;*/
Network(4, 5);
Network network(4, 5);
network.print();
return 0; return 0;
} }

75
myclasses.cpp
Visa fil

@ -6,13 +6,12 @@
using namespace std; using namespace std;
Neuron::Neuron(int prev_layer_size, Activ activ_function) Neuron::Neuron(int prev_layer_size)
{ {
for(int i(1) ; i<=prev_layer_size ; i++) for(int i(1) ; i<=prev_layer_size ; i++)
{ {
weights.push_front(Tools::get_random(0.0, 1.0)); weights.push_front(Tools::get_random(0.0, 1.0));
} }
activ = activ_function;
bias = 0.1; bias = 0.1;
output = 0.0; output = 0.0;
derror = 0.0; derror = 0.0;
@ -23,16 +22,16 @@ void Neuron::set_output(float value)
output = value; output = value;
} }
void Neuron::activate(forward_list<Neuron>::iterator &prev_layer_it) void Neuron::activate(forward_list<Neuron>::iterator &prev_layer_it, Activ activ_function)
{ {
set_output(bias); output = bias;
for(forward_list<float>::iterator it(weights.begin()) ; it!=weights.end() ; ++it) for(forward_list<float>::iterator it(weights.begin()) ; it!=weights.end() ; ++it)
{ {
output += (*it) * ((*prev_layer_it).output); output += (*it) * ((*prev_layer_it).output);
prev_layer_it++; prev_layer_it++;
} }
switch(activ) switch(activ_function)
{ {
case RELU: case RELU:
output = (output > 0.0) ? output : 0.0; output = (output > 0.0) ? output : 0.0;
@ -66,13 +65,13 @@ Network::Network(int n_layers, int n_neurons)
{ {
if(i==1) if(i==1)
{ {
current_layer.push_front( Neuron(0, LINEAR) ); current_layer.push_front( Neuron(0) );
}else if(i==n_layers) }else if(i==n_layers)
{ {
current_layer.push_front( Neuron(n_neurons, SIGMOID) ); current_layer.push_front( Neuron(n_neurons) );
}else }else
{ {
current_layer.push_front( Neuron(n_neurons, RELU) ); current_layer.push_front( Neuron(n_neurons) );
} }
} }
layers.push_back(current_layer); layers.push_back(current_layer);
@ -90,13 +89,13 @@ Network::Network(const std::vector<int> &n_neurons, Activ h_activ, Activ o_activ
{ {
if(i==0) if(i==0)
{ {
current_layer.push_front( Neuron(0, LINEAR) ); current_layer.push_front( Neuron(0) );
}else if(i==n_neurons.size()-1) }else if(i==n_neurons.size()-1)
{ {
current_layer.push_front( Neuron(n_neurons[i-1], o_activ) ); current_layer.push_front( Neuron(n_neurons[i-1]) );
}else }else
{ {
current_layer.push_front( Neuron(n_neurons[i-1], h_activ) ); current_layer.push_front( Neuron(n_neurons[i-1]) );
} }
} }
layers.push_back(current_layer); layers.push_back(current_layer);
@ -112,50 +111,48 @@ void Network::print()
cout << "#>>==========================================<<#" << endl; cout << "#>>==========================================<<#" << endl;
cout << ">> Number of layers : " << layers.size() << endl; cout << ">> Number of layers : " << layers.size() << endl;
cout << "------------------------------------------------" << endl; cout << "------------------------------------------------" << endl;
int layer_counter = 0;
int prev_layer_size_temp = 0, params_counter = 0;
for(list<forward_list<Neuron>>::iterator it1(layers.begin()) ; it1!=layers.end() ; ++it1) for(list<forward_list<Neuron>>::iterator it1(layers.begin()) ; it1!=layers.end() ; ++it1)
{ {
layer_counter++;
int current_layer_size = 0; int current_layer_size = 0;
for(forward_list<Neuron>::iterator it2(it1) ; it2!=it1.end() ; ++it2) for(forward_list<Neuron>::iterator it2(it1->begin()) ; it2!=it1->end() ; ++it2)
{ {
current_layer_size++; current_layer_size++;
} }
if(i==0) if(layer_counter==1)
{
prev_layer_size_temp = current_layer_size;
}
else
{
params_counter += (prev_layer_size_temp+1)*current_layer_size;
prev_layer_size_temp = current_layer_size;
}
if(layer_counter==1)
{ {
cout << ">> Input layer" << endl; cout << ">> Input layer" << endl;
cout << "size : " << layers << endl; cout << "size : " << current_layer_size << endl;
cout << "neurons' outputs : "; cout << "neurons' outputs : ";
temp = network->layers_first_neurons[i]; for(forward_list<Neuron>::iterator it2(it1->begin()) ; it2!=it1->end() ; ++it2){it2->get_output();}
while(temp != NULL) cout << endl;
{ }else if(layer_counter==layers.size())
cout << ("%f ", temp->output);
temp = temp->same_layer_next_neuron;
}
cout << ("\n");
}else if(i==layers.size()-1)
{ {
cout << (">> Output layer\n"); cout << (">> Output layer\n");
cout << ("size : %d\n", network->neurons_per_layer[i]); cout << "size : " << current_layer_size << endl;
cout << ("neurons' outputs : "); cout << ("neurons' outputs : ");
temp = network->layers_first_neurons[i]; for(forward_list<Neuron>::iterator it2(it1->begin()) ; it2!=it1->end() ; ++it2){it2->get_output();}
while(temp != NULL) cout << endl;
{
cout << ("%f ", temp->output);
temp = temp->same_layer_next_neuron;
}
cout << ("\n");
}else }else
{ {
cout << (">> Hidden layer %d\n", i); cout << ">> Hidden layer " << layer_counter-1 << endl;
cout << ("size : %d\n", network->neurons_per_layer[i]); cout << "size : " << current_layer_size << endl;
} }
cout << ("------------------------------------------------\n"); cout << "------------------------------------------------" << endl;
} }
cout << ("Number of parameters : "); cout << "Number of parameters : ";
for(i=1 ; i<network->n_layers ; i++) cout << params_counter << endl;
{
n_params += network->neurons_per_layer[i] * (network->neurons_per_layer[i-1] + 1);
}
cout << ("%d\n", n_params);
cout << "#>>==========================================<<#" << endl << endl; cout << "#>>==========================================<<#" << endl << endl;
} }

9
myclasses.h
Visa fil

@ -8,22 +8,21 @@
enum Activ enum Activ
{ {
RELU, TANH, SIGMOID, LINEAR RELU, TANH, SIGMOID, LINEAR, SOFTMAX
}; };
class Neuron class Neuron
{ {
public: public:
Neuron(int prev_layer_size, Activ activ_function); Neuron(int prev_layer_size); //prev_layer_size = number of weights
void set_output(float value); void set_output(float value);
float get_output();//to be deleted float get_output();//to be deleted
void activate(std::forward_list<Neuron>::iterator &prev_layer_it); void activate(std::forward_list<Neuron>::iterator &prev_layer_it, Activ activ_function=LINEAR);
private: private:
std::forward_list<float> weights; std::forward_list<float> weights;
float bias; float bias;
float output; float output;
float derror; float derror;
Activ activ;
}; };
@ -32,7 +31,7 @@ class Network
public: public:
Network(int n_layers, int n_neurons); Network(int n_layers, int n_neurons);
Network(const std::vector<int> &n_neurons, Activ h_activ=RELU, Activ o_activ=SIGMOID); Network(const std::vector<int> &n_neurons, Activ h_activ=RELU, Activ o_activ=SIGMOID);
void print() const; void print();
bool forward(const std::vector<float> &input, const std::vector<float> &target); bool forward(const std::vector<float> &input, const std::vector<float> &target);
bool backward(); bool backward();
private: private: