mirror of
https://github.com/Relintai/pmlpp.git
synced 2024-12-31 16:17:10 +01:00
Added TanhRegOld.
This commit is contained in:
parent
e191ab9a16
commit
628e5124e9
1
SCsub
1
SCsub
@ -62,6 +62,7 @@ sources = [
|
||||
"mlpp/svc/svc_old.cpp",
|
||||
"mlpp/softmax_reg/softmax_reg_old.cpp",
|
||||
"mlpp/auto_encoder/auto_encoder_old.cpp",
|
||||
"mlpp/tanh_reg/tanh_reg_old.cpp",
|
||||
|
||||
"test/mlpp_tests.cpp",
|
||||
]
|
||||
|
||||
196
mlpp/tanh_reg/tanh_reg_old.cpp
Normal file
196
mlpp/tanh_reg/tanh_reg_old.cpp
Normal file
@ -0,0 +1,196 @@
|
||||
//
|
||||
// TanhReg.cpp
|
||||
//
|
||||
// Created by Marc Melikyan on 10/2/20.
|
||||
//
|
||||
|
||||
#include "tanh_reg_old.h"
|
||||
|
||||
#include "../activation/activation.h"
|
||||
#include "../cost/cost.h"
|
||||
#include "../lin_alg/lin_alg.h"
|
||||
#include "../regularization/reg.h"
|
||||
#include "../utilities/utilities.h"
|
||||
|
||||
#include <iostream>
|
||||
#include <random>
|
||||
|
||||
MLPPTanhRegOld::MLPPTanhRegOld(std::vector<std::vector<real_t>> inputSet, std::vector<real_t> outputSet, std::string reg, real_t lambda, real_t alpha) :
|
||||
inputSet(inputSet), outputSet(outputSet), n(inputSet.size()), k(inputSet[0].size()), reg(reg), lambda(lambda), alpha(alpha) {
|
||||
y_hat.resize(n);
|
||||
weights = MLPPUtilities::weightInitialization(k);
|
||||
bias = MLPPUtilities::biasInitialization();
|
||||
}
|
||||
|
||||
std::vector<real_t> MLPPTanhRegOld::modelSetTest(std::vector<std::vector<real_t>> X) {
|
||||
return Evaluate(X);
|
||||
}
|
||||
|
||||
real_t MLPPTanhRegOld::modelTest(std::vector<real_t> x) {
|
||||
return Evaluate(x);
|
||||
}
|
||||
|
||||
void MLPPTanhRegOld::gradientDescent(real_t learning_rate, int max_epoch, bool UI) {
|
||||
MLPPActivation avn;
|
||||
MLPPLinAlg alg;
|
||||
MLPPReg regularization;
|
||||
real_t cost_prev = 0;
|
||||
int epoch = 1;
|
||||
forwardPass();
|
||||
|
||||
while (true) {
|
||||
cost_prev = Cost(y_hat, outputSet);
|
||||
|
||||
std::vector<real_t> error = alg.subtraction(y_hat, outputSet);
|
||||
|
||||
weights = alg.subtraction(weights, alg.scalarMultiply(learning_rate / n, alg.mat_vec_mult(alg.transpose(inputSet), alg.hadamard_product(error, avn.tanh(z, 1)))));
|
||||
weights = regularization.regWeights(weights, lambda, alpha, reg);
|
||||
|
||||
// Calculating the bias gradients
|
||||
bias -= learning_rate * alg.sum_elements(alg.hadamard_product(error, avn.tanh(z, 1))) / n;
|
||||
|
||||
forwardPass();
|
||||
|
||||
// UI PORTION
|
||||
if (UI) {
|
||||
MLPPUtilities::CostInfo(epoch, cost_prev, Cost(y_hat, outputSet));
|
||||
MLPPUtilities::UI(weights, bias);
|
||||
}
|
||||
epoch++;
|
||||
|
||||
if (epoch > max_epoch) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
void MLPPTanhRegOld::SGD(real_t learning_rate, int max_epoch, bool UI) {
|
||||
MLPPLinAlg alg;
|
||||
MLPPReg regularization;
|
||||
real_t cost_prev = 0;
|
||||
int epoch = 1;
|
||||
|
||||
while (true) {
|
||||
std::random_device rd;
|
||||
std::default_random_engine generator(rd());
|
||||
std::uniform_int_distribution<int> distribution(0, int(n - 1));
|
||||
int outputIndex = distribution(generator);
|
||||
|
||||
real_t y_hat = Evaluate(inputSet[outputIndex]);
|
||||
cost_prev = Cost({ y_hat }, { outputSet[outputIndex] });
|
||||
|
||||
real_t error = y_hat - outputSet[outputIndex];
|
||||
|
||||
// Weight Updation
|
||||
weights = alg.subtraction(weights, alg.scalarMultiply(learning_rate * error * (1 - y_hat * y_hat), inputSet[outputIndex]));
|
||||
weights = regularization.regWeights(weights, lambda, alpha, reg);
|
||||
|
||||
// Bias updation
|
||||
bias -= learning_rate * error * (1 - y_hat * y_hat);
|
||||
|
||||
y_hat = Evaluate({ inputSet[outputIndex] });
|
||||
|
||||
if (UI) {
|
||||
MLPPUtilities::CostInfo(epoch, cost_prev, Cost({ y_hat }, { outputSet[outputIndex] }));
|
||||
MLPPUtilities::UI(weights, bias);
|
||||
}
|
||||
epoch++;
|
||||
|
||||
if (epoch > max_epoch) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
forwardPass();
|
||||
}
|
||||
|
||||
void MLPPTanhRegOld::MBGD(real_t learning_rate, int max_epoch, int mini_batch_size, bool UI) {
|
||||
MLPPActivation avn;
|
||||
MLPPLinAlg alg;
|
||||
MLPPReg regularization;
|
||||
|
||||
real_t cost_prev = 0;
|
||||
int epoch = 1;
|
||||
|
||||
// Creating the mini-batches
|
||||
int n_mini_batch = n / mini_batch_size;
|
||||
auto batches = MLPPUtilities::createMiniBatches(inputSet, outputSet, n_mini_batch);
|
||||
auto inputMiniBatches = std::get<0>(batches);
|
||||
auto outputMiniBatches = std::get<1>(batches);
|
||||
|
||||
while (true) {
|
||||
for (int i = 0; i < n_mini_batch; i++) {
|
||||
std::vector<real_t> y_hat = Evaluate(inputMiniBatches[i]);
|
||||
std::vector<real_t> z = propagate(inputMiniBatches[i]);
|
||||
cost_prev = Cost(y_hat, outputMiniBatches[i]);
|
||||
|
||||
std::vector<real_t> error = alg.subtraction(y_hat, outputMiniBatches[i]);
|
||||
|
||||
// Calculating the weight gradients
|
||||
weights = alg.subtraction(weights, alg.scalarMultiply(learning_rate / n, alg.mat_vec_mult(alg.transpose(inputMiniBatches[i]), alg.hadamard_product(error, avn.tanh(z, 1)))));
|
||||
weights = regularization.regWeights(weights, lambda, alpha, reg);
|
||||
|
||||
// Calculating the bias gradients
|
||||
bias -= learning_rate * alg.sum_elements(alg.hadamard_product(error, avn.tanh(z, 1))) / n;
|
||||
|
||||
forwardPass();
|
||||
|
||||
y_hat = Evaluate(inputMiniBatches[i]);
|
||||
|
||||
if (UI) {
|
||||
MLPPUtilities::CostInfo(epoch, cost_prev, Cost(y_hat, outputMiniBatches[i]));
|
||||
MLPPUtilities::UI(weights, bias);
|
||||
}
|
||||
}
|
||||
epoch++;
|
||||
if (epoch > max_epoch) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
forwardPass();
|
||||
}
|
||||
|
||||
real_t MLPPTanhRegOld::score() {
|
||||
MLPPUtilities util;
|
||||
return util.performance(y_hat, outputSet);
|
||||
}
|
||||
|
||||
void MLPPTanhRegOld::save(std::string fileName) {
|
||||
MLPPUtilities util;
|
||||
util.saveParameters(fileName, weights, bias);
|
||||
}
|
||||
|
||||
real_t MLPPTanhRegOld::Cost(std::vector<real_t> y_hat, std::vector<real_t> y) {
|
||||
MLPPReg regularization;
|
||||
class MLPPCost cost;
|
||||
return cost.MSE(y_hat, y) + regularization.regTerm(weights, lambda, alpha, reg);
|
||||
}
|
||||
|
||||
std::vector<real_t> MLPPTanhRegOld::Evaluate(std::vector<std::vector<real_t>> X) {
|
||||
MLPPLinAlg alg;
|
||||
MLPPActivation avn;
|
||||
return avn.tanh(alg.scalarAdd(bias, alg.mat_vec_mult(X, weights)));
|
||||
}
|
||||
|
||||
std::vector<real_t> MLPPTanhRegOld::propagate(std::vector<std::vector<real_t>> X) {
|
||||
MLPPLinAlg alg;
|
||||
return alg.scalarAdd(bias, alg.mat_vec_mult(X, weights));
|
||||
}
|
||||
|
||||
real_t MLPPTanhRegOld::Evaluate(std::vector<real_t> x) {
|
||||
MLPPLinAlg alg;
|
||||
MLPPActivation avn;
|
||||
return avn.tanh(alg.dot(weights, x) + bias);
|
||||
}
|
||||
|
||||
real_t MLPPTanhRegOld::propagate(std::vector<real_t> x) {
|
||||
MLPPLinAlg alg;
|
||||
return alg.dot(weights, x) + bias;
|
||||
}
|
||||
|
||||
// Tanh ( wTx + b )
|
||||
void MLPPTanhRegOld::forwardPass() {
|
||||
MLPPActivation avn;
|
||||
|
||||
z = propagate(inputSet);
|
||||
y_hat = avn.tanh(z);
|
||||
}
|
||||
55
mlpp/tanh_reg/tanh_reg_old.h
Normal file
55
mlpp/tanh_reg/tanh_reg_old.h
Normal file
@ -0,0 +1,55 @@
|
||||
|
||||
#ifndef MLPP_TANH_REG_OLD_H
|
||||
#define MLPP_TANH_REG_OLD_H
|
||||
|
||||
//
|
||||
// TanhReg.hpp
|
||||
//
|
||||
// Created by Marc Melikyan on 10/2/20.
|
||||
//
|
||||
|
||||
#include "core/math/math_defs.h"
|
||||
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
class MLPPTanhRegOld {
|
||||
public:
|
||||
MLPPTanhRegOld(std::vector<std::vector<real_t>> inputSet, std::vector<real_t> outputSet, std::string reg = "None", real_t lambda = 0.5, real_t alpha = 0.5);
|
||||
std::vector<real_t> modelSetTest(std::vector<std::vector<real_t>> X);
|
||||
real_t modelTest(std::vector<real_t> x);
|
||||
void gradientDescent(real_t learning_rate, int max_epoch, bool UI = false);
|
||||
void SGD(real_t learning_rate, int max_epoch, bool UI = false);
|
||||
void MBGD(real_t learning_rate, int max_epoch, int mini_batch_size, bool UI = false);
|
||||
real_t score();
|
||||
void save(std::string fileName);
|
||||
|
||||
private:
|
||||
real_t Cost(std::vector<real_t> y_hat, std::vector<real_t> y);
|
||||
|
||||
std::vector<real_t> Evaluate(std::vector<std::vector<real_t>> X);
|
||||
std::vector<real_t> propagate(std::vector<std::vector<real_t>> X);
|
||||
real_t Evaluate(std::vector<real_t> x);
|
||||
real_t propagate(std::vector<real_t> x);
|
||||
void forwardPass();
|
||||
|
||||
std::vector<std::vector<real_t>> inputSet;
|
||||
std::vector<real_t> outputSet;
|
||||
std::vector<real_t> z;
|
||||
std::vector<real_t> y_hat;
|
||||
std::vector<real_t> weights;
|
||||
real_t bias;
|
||||
|
||||
int n;
|
||||
int k;
|
||||
|
||||
// UI Portion
|
||||
void UI(int epoch, real_t cost_prev);
|
||||
|
||||
// Regularization Params
|
||||
std::string reg;
|
||||
real_t lambda;
|
||||
real_t alpha; /* This is the controlling param for Elastic Net*/
|
||||
};
|
||||
|
||||
#endif /* TanhReg_hpp */
|
||||
@ -54,6 +54,7 @@
|
||||
#include "../mlpp/probit_reg/probit_reg_old.h"
|
||||
#include "../mlpp/softmax_reg/softmax_reg_old.h"
|
||||
#include "../mlpp/svc/svc_old.h"
|
||||
#include "../mlpp/tanh_reg/tanh_reg_old.h"
|
||||
#include "../mlpp/uni_lin_reg/uni_lin_reg_old.h"
|
||||
#include "../mlpp/wgan/wgan_old.h"
|
||||
|
||||
@ -390,10 +391,11 @@ void MLPPTests::test_tanh_regression(bool ui) {
|
||||
// TANH REGRESSION
|
||||
std::vector<std::vector<real_t>> inputSet = { { 4, 3, 0, -3, -4 }, { 0, 0, 0, 1, 1 } };
|
||||
std::vector<real_t> outputSet = { 1, 1, 0, -1, -1 };
|
||||
MLPPTanhReg model(alg.transpose(inputSet), outputSet);
|
||||
model.SGD(0.1, 10000, ui);
|
||||
alg.printVector(model.modelSetTest(alg.transpose(inputSet)));
|
||||
std::cout << "ACCURACY: " << 100 * model.score() << "%" << std::endl;
|
||||
|
||||
MLPPTanhRegOld model_old(alg.transpose(inputSet), outputSet);
|
||||
model_old.SGD(0.1, 10000, ui);
|
||||
alg.printVector(model_old.modelSetTest(alg.transpose(inputSet)));
|
||||
std::cout << "ACCURACY (Old): " << 100 * model_old.score() << "%" << std::endl;
|
||||
}
|
||||
void MLPPTests::test_softmax_regression(bool ui) {
|
||||
MLPPLinAlg alg;
|
||||
|
||||
Loading…
Reference in New Issue
Block a user