Mirrors/MLP
1
0
Fork 0
mirror of https://github.com/davidalbertonogueira/MLP.git synced 2025-12-18 12:54:41 +03:00
Code Issues Actions Packages Projects Releases Wiki Activity

More test changes.

Browse Source
This commit is contained in:
davidjacnogueira
2016-11-03 22:05:09 +00:00
parent c7b67885a4
commit 7965d7b748
1 changed files with 40 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
src/MLPTest.cpp
View File

@@ -43,10 +43,12 @@ UNIT(LearnAND) {
for (const auto & training_sample : training_sample_set_with_bias) { for (const auto & training_sample : training_sample_set_with_bias) {
std::vector<double> output; std::vector<double> output;
my_mlp.GetOutput(training_sample.input_vector(), &output); my_mlp.GetOutput(training_sample.input_vector(), &output);
bool predicted_output = output[0] > 0.5 ? true : false; for (int i = 0; i < num_outputs; i++) {
bool correct_output = training_sample.output_vector()[0] > 0.5 ? true : false; bool predicted_output = output[i] > 0.5 ? true : false;
bool correct_output = training_sample.output_vector()[i] > 0.5 ? true : false;
ASSERT_TRUE(predicted_output == correct_output); ASSERT_TRUE(predicted_output == correct_output);
} }
}
std::cout << "Trained with success." << std::endl; std::cout << "Trained with success." << std::endl;
std::cout << std::endl; std::cout << std::endl;
} }
@@ -82,10 +84,12 @@ UNIT(LearnNAND) {
for (const auto & training_sample : training_sample_set_with_bias) { for (const auto & training_sample : training_sample_set_with_bias) {
std::vector<double> output; std::vector<double> output;
my_mlp.GetOutput(training_sample.input_vector(), &output); my_mlp.GetOutput(training_sample.input_vector(), &output);
bool predicted_output = output[0] > 0.5 ? true : false; for (int i = 0; i < num_outputs; i++) {
bool correct_output = training_sample.output_vector()[0] > 0.5 ? true : false; bool predicted_output = output[i] > 0.5 ? true : false;
bool correct_output = training_sample.output_vector()[i] > 0.5 ? true : false;
ASSERT_TRUE(predicted_output == correct_output); ASSERT_TRUE(predicted_output == correct_output);
} }
}
std::cout << "Trained with success." << std::endl; std::cout << "Trained with success." << std::endl;
std::cout << std::endl; std::cout << std::endl;
} }
@@ -121,10 +125,12 @@ UNIT(LearnOR) {
for (const auto & training_sample : training_sample_set_with_bias) { for (const auto & training_sample : training_sample_set_with_bias) {
std::vector<double> output; std::vector<double> output;
my_mlp.GetOutput(training_sample.input_vector(), &output); my_mlp.GetOutput(training_sample.input_vector(), &output);
bool predicted_output = output[0] > 0.5 ? true : false; for (int i = 0; i < num_outputs; i++) {
bool correct_output = training_sample.output_vector()[0] > 0.5 ? true : false; bool predicted_output = output[i] > 0.5 ? true : false;
bool correct_output = training_sample.output_vector()[i] > 0.5 ? true : false;
ASSERT_TRUE(predicted_output == correct_output); ASSERT_TRUE(predicted_output == correct_output);
} }
}
std::cout << "Trained with success." << std::endl; std::cout << "Trained with success." << std::endl;
std::cout << std::endl; std::cout << std::endl;
} }
@@ -160,10 +166,12 @@ UNIT(LearnNOR) {
for (const auto & training_sample : training_sample_set_with_bias) { for (const auto & training_sample : training_sample_set_with_bias) {
std::vector<double> output; std::vector<double> output;
my_mlp.GetOutput(training_sample.input_vector(), &output); my_mlp.GetOutput(training_sample.input_vector(), &output);
bool predicted_output = output[0] > 0.5 ? true : false; for (int i = 0; i < num_outputs; i++) {
bool correct_output = training_sample.output_vector()[0] > 0.5 ? true : false; bool predicted_output = output[i] > 0.5 ? true : false;
bool correct_output = training_sample.output_vector()[i] > 0.5 ? true : false;
ASSERT_TRUE(predicted_output == correct_output); ASSERT_TRUE(predicted_output == correct_output);
} }
}
std::cout << "Trained with success." << std::endl; std::cout << "Trained with success." << std::endl;
std::cout << std::endl; std::cout << std::endl;
} }
@@ -197,10 +205,12 @@ UNIT(LearnXOR) {
for (const auto & training_sample : training_sample_set_with_bias) { for (const auto & training_sample : training_sample_set_with_bias) {
std::vector<double> output; std::vector<double> output;
my_mlp.GetOutput(training_sample.input_vector(), &output); my_mlp.GetOutput(training_sample.input_vector(), &output);
bool predicted_output = output[0] > 0.5 ? true : false; for (int i = 0; i < num_outputs; i++) {
bool correct_output = training_sample.output_vector()[0] > 0.5 ? true : false; bool predicted_output = output[i] > 0.5 ? true : false;
bool correct_output = training_sample.output_vector()[i] > 0.5 ? true : false;
ASSERT_TRUE(predicted_output == correct_output); ASSERT_TRUE(predicted_output == correct_output);
} }
}
std::cout << "Trained with success." << std::endl; std::cout << "Trained with success." << std::endl;
std::cout << std::endl; std::cout << std::endl;
} }
@@ -232,10 +242,12 @@ UNIT(LearnNOT) {
for (const auto & training_sample : training_sample_set_with_bias) { for (const auto & training_sample : training_sample_set_with_bias) {
std::vector<double> output; std::vector<double> output;
my_mlp.GetOutput(training_sample.input_vector(), &output); my_mlp.GetOutput(training_sample.input_vector(), &output);
bool predicted_output = output[0] > 0.5 ? true : false; for (int i = 0; i < num_outputs; i++) {
bool correct_output = training_sample.output_vector()[0] > 0.5 ? true : false; bool predicted_output = output[i] > 0.5 ? true : false;
bool correct_output = training_sample.output_vector()[i] > 0.5 ? true : false;
ASSERT_TRUE(predicted_output == correct_output); ASSERT_TRUE(predicted_output == correct_output);
} }
}
std::cout << "Trained with success." << std::endl; std::cout << "Trained with success." << std::endl;
std::cout << std::endl; std::cout << std::endl;
} }
@@ -269,15 +281,16 @@ UNIT(LearnX1) {
for (const auto & training_sample : training_sample_set_with_bias) { for (const auto & training_sample : training_sample_set_with_bias) {
std::vector<double> output; std::vector<double> output;
my_mlp.GetOutput(training_sample.input_vector(), &output); my_mlp.GetOutput(training_sample.input_vector(), &output);
bool predicted_output = output[0] > 0.5 ? true : false; for (int i = 0; i < num_outputs; i++) {
bool correct_output = training_sample.output_vector()[0] > 0.5 ? true : false; bool predicted_output = output[i] > 0.5 ? true : false;
bool correct_output = training_sample.output_vector()[i] > 0.5 ? true : false;
ASSERT_TRUE(predicted_output == correct_output); ASSERT_TRUE(predicted_output == correct_output);
} }
}
std::cout << "Trained with success." << std::endl; std::cout << "Trained with success." << std::endl;
std::cout << std::endl; std::cout << std::endl;
} }
UNIT(LearnX2) { UNIT(LearnX2) {
std::cout << "Train X2 function with mlp." << std::endl; std::cout << "Train X2 function with mlp." << std::endl;
@@ -307,10 +320,12 @@ UNIT(LearnX2) {
for (const auto & training_sample : training_sample_set_with_bias) { for (const auto & training_sample : training_sample_set_with_bias) {
std::vector<double> output; std::vector<double> output;
my_mlp.GetOutput(training_sample.input_vector(), &output); my_mlp.GetOutput(training_sample.input_vector(), &output);
bool predicted_output = output[0] > 0.5 ? true : false; for (int i = 0; i < num_outputs; i++) {
bool correct_output = training_sample.output_vector()[0] > 0.5 ? true : false; bool predicted_output = output[i] > 0.5 ? true : false;
bool correct_output = training_sample.output_vector()[i] > 0.5 ? true : false;
ASSERT_TRUE(predicted_output == correct_output); ASSERT_TRUE(predicted_output == correct_output);
} }
}
std::cout << "Trained with success." << std::endl; std::cout << "Trained with success." << std::endl;
std::cout << std::endl; std::cout << std::endl;
} }