Relintai/pmlpp
1
0
Fork 0
mirror of https://github.com/Relintai/pmlpp.git synced 2025-01-21 15:27:17 +01:00
Code Issues Packages Projects Releases Wiki Activity

Fixed a few crashes and issues.

Browse Source
This commit is contained in:
Relintai 2023-02-05 10:59:45 +01:00
parent 4281746cfc
commit e6afa5b715
2 changed files with 12 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
mlpp/activation/activation.cpp
View File

@ -851,11 +851,11 @@ real_t MLPPActivation::sigmoid_normr(real_t z) {
} }
Ref<MLPPVector> MLPPActivation::sigmoid_normv(const Ref<MLPPVector> &z) { Ref<MLPPVector> MLPPActivation::sigmoid_normv(const Ref<MLPPVector> &z) {
MLPPLinAlg alg; MLPPLinAlg alg;
return alg.element_wise_division(alg.onevecv(z->size()), alg.additionm(alg.onevecv(z->size()), alg.expv(alg.scalar_multiplynv(-1, z)))); return alg.element_wise_division(alg.onevecv(z->size()), alg.additionnv(alg.onevecv(z->size()), alg.expv(alg.scalar_multiplynv(-1, z))));
} }
Ref<MLPPMatrix> MLPPActivation::sigmoid_normm(const Ref<MLPPMatrix> &z) { Ref<MLPPMatrix> MLPPActivation::sigmoid_normm(const Ref<MLPPMatrix> &z) {
MLPPLinAlg alg; MLPPLinAlg alg;
return alg.element_wise_division(alg.onematm(z->size().x, z->size().y), alg.additionm(alg.onematm(z->size().x, z->size().y), alg.expv(alg.scalar_multiplynv(-1, z)))); return alg.element_wise_divisionm(alg.onematm(z->size().x, z->size().y), alg.additionm(alg.onematm(z->size().x, z->size().y), alg.expm(alg.scalar_multiplym(-1, z))));
} }
real_t MLPPActivation::sigmoid_derivr(real_t z) { real_t MLPPActivation::sigmoid_derivr(real_t z) {
@ -874,9 +874,9 @@ Ref<MLPPVector> MLPPActivation::sigmoid_derivv(const Ref<MLPPVector> &z) {
Ref<MLPPMatrix> MLPPActivation::sigmoid_derivm(const Ref<MLPPMatrix> &z) { Ref<MLPPMatrix> MLPPActivation::sigmoid_derivm(const Ref<MLPPMatrix> &z) {
MLPPLinAlg alg; MLPPLinAlg alg;
Ref<MLPPVector> sig_norm = sigmoid_normm(z); Ref<MLPPMatrix> sig_norm = sigmoid_normm(z);
return alg.subtractionnv(sig_norm, alg.hadamard_productnv(sig_norm, sig_norm)); return alg.subtractionm(sig_norm, alg.hadamard_productm(sig_norm, sig_norm));
} }
//SOFTMAX //SOFTMAX

20
mlpp/mlp/mlp.cpp
View File

@ -106,12 +106,8 @@ void MLPPMLP::gradient_descent(real_t learning_rate, int max_epoch, bool UI) {
// Calculating the weight/bias for layer 1 // Calculating the weight/bias for layer 1
Ref<MLPPMatrix> D1_1; Ref<MLPPMatrix> D1_1 = alg.outer_product(error, weights2);
Ref<MLPPMatrix> D1_2 = alg.hadamard_productm(alg.transposem(D1_1), avn.sigmoid_derivm(z2));
D1_1 = alg.outer_product(error, weights2);
Ref<MLPPMatrix> D1_2 = alg.hadamard_productm(D1_1, avn.sigmoid_derivm(z2));
Ref<MLPPMatrix> D1_3 = alg.matmultm(alg.transposem(input_set), D1_2); Ref<MLPPMatrix> D1_3 = alg.matmultm(alg.transposem(input_set), D1_2);
// weight an bias updation for layer 1 // weight an bias updation for layer 1
@ -354,15 +350,15 @@ real_t MLPPMLP::cost(const Ref<MLPPVector> &y_hat, const Ref<MLPPVector> &y) {
MLPPReg regularization; MLPPReg regularization;
class MLPPCost cost; class MLPPCost cost;
return cost.log_lossv(y_hat, y) + regularization.reg_termv(weights2, lambda, alpha, reg) + regularization.reg_termv(weights1, lambda, alpha, reg); return cost.log_lossv(y_hat, y) + regularization.reg_termv(weights2, lambda, alpha, reg) + regularization.reg_termm(weights1, lambda, alpha, reg);
} }
Ref<MLPPVector> MLPPMLP::evaluatem(const Ref<MLPPMatrix> &X) { Ref<MLPPVector> MLPPMLP::evaluatem(const Ref<MLPPMatrix> &X) {
MLPPLinAlg alg; MLPPLinAlg alg;
MLPPActivation avn; MLPPActivation avn;
Ref<MLPPVector> pz2 = alg.mat_vec_addv(alg.matmultm(X, weights1), bias1); Ref<MLPPMatrix> pz2 = alg.mat_vec_addv(alg.matmultm(X, weights1), bias1);
Ref<MLPPVector> pa2 = avn.sigmoid_normm(pz2); Ref<MLPPMatrix> pa2 = avn.sigmoid_normm(pz2);
return avn.sigmoid_normv(alg.scalar_addnv(bias2, alg.mat_vec_multv(pa2, weights2))); return avn.sigmoid_normv(alg.scalar_addnv(bias2, alg.mat_vec_multv(pa2, weights2)));
} }
@ -397,10 +393,10 @@ void MLPPMLP::forward_pass() {
MLPPLinAlg alg; MLPPLinAlg alg;
MLPPActivation avn; MLPPActivation avn;
z2 = alg.mat_vec_addv(alg.matmultm(input_set, weights1), bias1); z2->set_from_mlpp_matrix(alg.mat_vec_addv(alg.matmultm(input_set, weights1), bias1));
a2 = avn.sigmoid_normv(z2); a2->set_from_mlpp_matrix(avn.sigmoid_normm(z2));
y_hat = avn.sigmoid_normv(alg.scalar_addm(bias2, alg.mat_vec_multv(a2, weights2))); y_hat = avn.sigmoid_normv(alg.scalar_addnv(bias2, alg.mat_vec_multv(a2, weights2)));
} }
MLPPMLP::MLPPMLP(const Ref<MLPPMatrix> &p_input_set, const Ref<MLPPVector> &p_output_set, int p_n_hidden, MLPPReg::RegularizationType p_reg, real_t p_lambda, real_t p_alpha) { MLPPMLP::MLPPMLP(const Ref<MLPPMatrix> &p_input_set, const Ref<MLPPVector> &p_output_set, int p_n_hidden, MLPPReg::RegularizationType p_reg, real_t p_lambda, real_t p_alpha) {