Relintai/pmlpp
1
0
Fork 0
mirror of https://github.com/Relintai/pmlpp.git synced 2024-11-13 13:57:19 +01:00
Code Issues Packages Projects Releases Wiki Activity

Rename the GAN class in gan_old.h and cpp to GANOld.

Browse Source
This commit is contained in:
Relintai 2023-02-11 09:32:49 +01:00
parent 1bb0cab99a
commit f24bf466c8
2 changed files with 21 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
mlpp/gan/gan_old.cpp
View File

@ -14,20 +14,20 @@
#include <cmath> #include <cmath>
#include <iostream> #include <iostream>
MLPPGAN::MLPPGAN(real_t k, std::vector<std::vector<real_t>> outputSet) : MLPPGANOld::MLPPGANOld(real_t k, std::vector<std::vector<real_t>> outputSet) :
outputSet(outputSet), n(outputSet.size()), k(k) { outputSet(outputSet), n(outputSet.size()), k(k) {
} }
MLPPGAN::~MLPPGAN() { MLPPGANOld::~MLPPGANOld() {
delete outputLayer; delete outputLayer;
} }
std::vector<std::vector<real_t>> MLPPGAN::generateExample(int n) { std::vector<std::vector<real_t>> MLPPGANOld::generateExample(int n) {
MLPPLinAlg alg; MLPPLinAlg alg;
return modelSetTestGenerator(alg.gaussianNoise(n, k)); return modelSetTestGenerator(alg.gaussianNoise(n, k));
} }
void MLPPGAN::gradientDescent(real_t learning_rate, int max_epoch, bool UI) { void MLPPGANOld::gradientDescent(real_t learning_rate, int max_epoch, bool UI) {
class MLPPCost cost; class MLPPCost cost;
MLPPLinAlg alg; MLPPLinAlg alg;
real_t cost_prev = 0; real_t cost_prev = 0;
@ -68,7 +68,7 @@ void MLPPGAN::gradientDescent(real_t learning_rate, int max_epoch, bool UI) {
forwardPass(); forwardPass();
if (UI) { if (UI) {
MLPPGAN::UI(epoch, cost_prev, MLPPGAN::y_hat, alg.onevec(n)); MLPPGANOld::UI(epoch, cost_prev, MLPPGANOld::y_hat, alg.onevec(n));
} }
epoch++; epoch++;
@ -78,14 +78,14 @@ void MLPPGAN::gradientDescent(real_t learning_rate, int max_epoch, bool UI) {
} }
} }
real_t MLPPGAN::score() { real_t MLPPGANOld::score() {
MLPPLinAlg alg; MLPPLinAlg alg;
MLPPUtilities util; MLPPUtilities util;
forwardPass(); forwardPass();
return util.performance(y_hat, alg.onevec(n)); return util.performance(y_hat, alg.onevec(n));
} }
void MLPPGAN::save(std::string fileName) { void MLPPGANOld::save(std::string fileName) {
MLPPUtilities util; MLPPUtilities util;
if (!network.empty()) { if (!network.empty()) {
util.saveParameters(fileName, network[0].weights, network[0].bias, false, 1); util.saveParameters(fileName, network[0].weights, network[0].bias, false, 1);
@ -98,7 +98,7 @@ void MLPPGAN::save(std::string fileName) {
} }
} }
void MLPPGAN::addLayer(int n_hidden, std::string activation, std::string weightInit, std::string reg, real_t lambda, real_t alpha) { void MLPPGANOld::addLayer(int n_hidden, std::string activation, std::string weightInit, std::string reg, real_t lambda, real_t alpha) {
MLPPLinAlg alg; MLPPLinAlg alg;
if (network.empty()) { if (network.empty()) {
network.push_back(MLPPOldHiddenLayer(n_hidden, activation, alg.gaussianNoise(n, k), weightInit, reg, lambda, alpha)); network.push_back(MLPPOldHiddenLayer(n_hidden, activation, alg.gaussianNoise(n, k), weightInit, reg, lambda, alpha));
@ -109,7 +109,7 @@ void MLPPGAN::addLayer(int n_hidden, std::string activation, std::string weightI
} }
} }
void MLPPGAN::addOutputLayer(std::string weightInit, std::string reg, real_t lambda, real_t alpha) { void MLPPGANOld::addOutputLayer(std::string weightInit, std::string reg, real_t lambda, real_t alpha) {
MLPPLinAlg alg; MLPPLinAlg alg;
if (!network.empty()) { if (!network.empty()) {
outputLayer = new MLPPOldOutputLayer(network[network.size() - 1].n_hidden, "Sigmoid", "LogLoss", network[network.size() - 1].a, weightInit, reg, lambda, alpha); outputLayer = new MLPPOldOutputLayer(network[network.size() - 1].n_hidden, "Sigmoid", "LogLoss", network[network.size() - 1].a, weightInit, reg, lambda, alpha);
@ -118,7 +118,7 @@ void MLPPGAN::addOutputLayer(std::string weightInit, std::string reg, real_t lam
} }
} }
std::vector<std::vector<real_t>> MLPPGAN::modelSetTestGenerator(std::vector<std::vector<real_t>> X) { std::vector<std::vector<real_t>> MLPPGANOld::modelSetTestGenerator(std::vector<std::vector<real_t>> X) {
if (!network.empty()) { if (!network.empty()) {
network[0].input = X; network[0].input = X;
network[0].forwardPass(); network[0].forwardPass();
@ -131,7 +131,7 @@ std::vector<std::vector<real_t>> MLPPGAN::modelSetTestGenerator(std::vector<std:
return network[network.size() / 2].a; return network[network.size() / 2].a;
} }
std::vector<real_t> MLPPGAN::modelSetTestDiscriminator(std::vector<std::vector<real_t>> X) { std::vector<real_t> MLPPGANOld::modelSetTestDiscriminator(std::vector<std::vector<real_t>> X) {
if (!network.empty()) { if (!network.empty()) {
for (uint32_t i = network.size() / 2 + 1; i < network.size(); i++) { for (uint32_t i = network.size() / 2 + 1; i < network.size(); i++) {
if (i == network.size() / 2 + 1) { if (i == network.size() / 2 + 1) {
@ -147,7 +147,7 @@ std::vector<real_t> MLPPGAN::modelSetTestDiscriminator(std::vector<std::vector<r
return outputLayer->a; return outputLayer->a;
} }
real_t MLPPGAN::Cost(std::vector<real_t> y_hat, std::vector<real_t> y) { real_t MLPPGANOld::Cost(std::vector<real_t> y_hat, std::vector<real_t> y) {
MLPPReg regularization; MLPPReg regularization;
class MLPPCost cost; class MLPPCost cost;
real_t totalRegTerm = 0; real_t totalRegTerm = 0;
@ -161,7 +161,7 @@ real_t MLPPGAN::Cost(std::vector<real_t> y_hat, std::vector<real_t> y) {
return (cost.*cost_function)(y_hat, y) + totalRegTerm + regularization.regTerm(outputLayer->weights, outputLayer->lambda, outputLayer->alpha, outputLayer->reg); return (cost.*cost_function)(y_hat, y) + totalRegTerm + regularization.regTerm(outputLayer->weights, outputLayer->lambda, outputLayer->alpha, outputLayer->reg);
} }
void MLPPGAN::forwardPass() { void MLPPGANOld::forwardPass() {
MLPPLinAlg alg; MLPPLinAlg alg;
if (!network.empty()) { if (!network.empty()) {
network[0].input = alg.gaussianNoise(n, k); network[0].input = alg.gaussianNoise(n, k);
@ -179,7 +179,7 @@ void MLPPGAN::forwardPass() {
y_hat = outputLayer->a; y_hat = outputLayer->a;
} }
void MLPPGAN::updateDiscriminatorParameters(std::vector<std::vector<std::vector<real_t>>> hiddenLayerUpdations, std::vector<real_t> outputLayerUpdation, real_t learning_rate) { void MLPPGANOld::updateDiscriminatorParameters(std::vector<std::vector<std::vector<real_t>>> hiddenLayerUpdations, std::vector<real_t> outputLayerUpdation, real_t learning_rate) {
MLPPLinAlg alg; MLPPLinAlg alg;
outputLayer->weights = alg.subtraction(outputLayer->weights, outputLayerUpdation); outputLayer->weights = alg.subtraction(outputLayer->weights, outputLayerUpdation);
@ -196,7 +196,7 @@ void MLPPGAN::updateDiscriminatorParameters(std::vector<std::vector<std::vector<
} }
} }
void MLPPGAN::updateGeneratorParameters(std::vector<std::vector<std::vector<real_t>>> hiddenLayerUpdations, real_t learning_rate) { void MLPPGANOld::updateGeneratorParameters(std::vector<std::vector<std::vector<real_t>>> hiddenLayerUpdations, real_t learning_rate) {
MLPPLinAlg alg; MLPPLinAlg alg;
if (!network.empty()) { if (!network.empty()) {
@ -209,7 +209,7 @@ void MLPPGAN::updateGeneratorParameters(std::vector<std::vector<std::vector<real
} }
} }
std::tuple<std::vector<std::vector<std::vector<real_t>>>, std::vector<real_t>> MLPPGAN::computeDiscriminatorGradients(std::vector<real_t> y_hat, std::vector<real_t> outputSet) { std::tuple<std::vector<std::vector<std::vector<real_t>>>, std::vector<real_t>> MLPPGANOld::computeDiscriminatorGradients(std::vector<real_t> y_hat, std::vector<real_t> outputSet) {
class MLPPCost cost; class MLPPCost cost;
MLPPActivation avn; MLPPActivation avn;
MLPPLinAlg alg; MLPPLinAlg alg;
@ -245,7 +245,7 @@ std::tuple<std::vector<std::vector<std::vector<real_t>>>, std::vector<real_t>> M
return { cumulativeHiddenLayerWGrad, outputWGrad }; return { cumulativeHiddenLayerWGrad, outputWGrad };
} }
std::vector<std::vector<std::vector<real_t>>> MLPPGAN::computeGeneratorGradients(std::vector<real_t> y_hat, std::vector<real_t> outputSet) { std::vector<std::vector<std::vector<real_t>>> MLPPGANOld::computeGeneratorGradients(std::vector<real_t> y_hat, std::vector<real_t> outputSet) {
class MLPPCost cost; class MLPPCost cost;
MLPPActivation avn; MLPPActivation avn;
MLPPLinAlg alg; MLPPLinAlg alg;
@ -274,7 +274,7 @@ std::vector<std::vector<std::vector<real_t>>> MLPPGAN::computeGeneratorGradients
return cumulativeHiddenLayerWGrad; return cumulativeHiddenLayerWGrad;
} }
void MLPPGAN::UI(int epoch, real_t cost_prev, std::vector<real_t> y_hat, std::vector<real_t> outputSet) { void MLPPGANOld::UI(int epoch, real_t cost_prev, std::vector<real_t> y_hat, std::vector<real_t> outputSet) {
MLPPUtilities::CostInfo(epoch, cost_prev, Cost(y_hat, outputSet)); MLPPUtilities::CostInfo(epoch, cost_prev, Cost(y_hat, outputSet));
std::cout << "Layer " << network.size() + 1 << ": " << std::endl; std::cout << "Layer " << network.size() + 1 << ": " << std::endl;
MLPPUtilities::UI(outputLayer->weights, outputLayer->bias); MLPPUtilities::UI(outputLayer->weights, outputLayer->bias);

6
mlpp/gan/gan_old.h
View File

@ -20,10 +20,10 @@
#include <tuple> #include <tuple>
#include <vector> #include <vector>
class MLPPGAN { class MLPPGANOld {
public: public:
MLPPGAN(real_t k, std::vector<std::vector<real_t>> outputSet); MLPPGANOld(real_t k, std::vector<std::vector<real_t>> outputSet);
~MLPPGAN(); ~MLPPGANOld();
std::vector<std::vector<real_t>> generateExample(int n); std::vector<std::vector<real_t>> generateExample(int n);
void gradientDescent(real_t learning_rate, int max_epoch, bool UI = false); void gradientDescent(real_t learning_rate, int max_epoch, bool UI = false);
real_t score(); real_t score();