rawalcher/c-net
Archived
1
0
Fork 0
Code Issues 5 Pull requests Projects Releases 2 Packages Wiki Activity Actions

HolyFuckItsAlive #13

Merged
jastornig merged 105 commits from Delta-Error-Test into main 2023-09-23 22:27:54 +02:00
Conversation 3 Commits 105 Files changed 19 +45 -44
2 changed files with 45 additions and 44 deletions
Download patch file Download diff file Expand all files Collapse all files
Showing only changes of commit 30317791e4 - Show all commits

2
CMakeLists.txt
View file

@ -3,5 +3,5 @@ project(c_net C)
set(CMAKE_C_STANDARD 11)
add_executable(c_net main.c matrix.c image.c)
add_executable(c_net main.c matrix.c image.c neuronal_network.c)
target_link_libraries(c_net m)

87
neuronal_network.c
View file

@ -4,20 +4,20 @@
#include <time.h>
Neural_Network* new_network(int input_size, int hidden_size, int output_size, double learning_rate){
Neural_Network network = malloc(sizeof(Neural_Network));
Neural_Network *network = malloc(sizeof(Neural_Network));
// initialize networks variables
network.input_size = input_size;
network.hidden_size = hidden_size;
network.output_size = output_size;
network.learning_rate = learning_rate;
network->hidden_size = hidden_size;
network->input_size = input_size;
network->output_size = output_size;
network->learning_rate = learning_rate;
network.weights_1 = matrix_randomize(matrix_create(hidden_size, input_size));
network.weights_2 = matrix_randomize(matrix_create(hidden_size, hidden_size));
network.weights_3 = matrix_randomize(matrix_create(hidden_size, hidden_size));
network.weights_output = matrix_randomize(matrix_create(output_size, hidden_size));
network.bias_1 = matrix_randomize(matrix_create(hidden_size, 1));
network.bias_2 = matrix_randomize(matrix_create(hidden_size, 1));
network.bias_3 = matrix_randomize(matrix_create(hidden_size, 1));
network->weights_1 = matrix_create(hidden_size, input_size);
network->weights_2 = matrix_create(hidden_size, hidden_size);
network->weights_3 = matrix_create(hidden_size, hidden_size);
network->weights_output = matrix_create(output_size, hidden_size);
network->bias_1 = matrix_create(hidden_size, 1);
network->bias_2 = matrix_create(hidden_size, 1);
network->bias_3 = matrix_create(hidden_size, 1);
//network.bias_output = matrix_create(output_size, 1); // do we need it?
return network;
@ -60,7 +60,7 @@ void save_network(Neural_Network* network) {
fprintf(save_file, "%d\n", network->output_size);
// close the file
fclose(file_name);
fclose(save_file);
// save first layer
matrix_save(network->bias_1, file_name);
@ -81,40 +81,41 @@ void save_network(Neural_Network* network) {
}
Neural_Network* load_network(char* file) {
return NULL;
}
double predict_images(Neural_Network* network, Image** images, int amount) {
int num_correct = 0;
for (int i = 0; i < amount; i++) {
Matrix* prediction = predict_image(network, images[i]);
if (matrix_argmax(prediction) == images[i]->image_label) {
num_correct++;
}
matrix_free(prediction);
}
return 1.0 * num_correct / amount;
}
Matrix* predict_image(Neural_Network* network, Image*);
//double predict_images(Neural_Network* network, Image** images, int amount) {
// int num_correct = 0;
// for (int i = 0; i < amount; i++) {
// Matrix* prediction = predict_image(network, images[i]);
// if (matrix_argmax(prediction) == images[i]->label) {
// num_correct++;
// }
// matrix_free(prediction);
// }
// return 1.0 * num_correct / amount;
//}
Matrix* predict(Neural_Network* network, Matrix* image_data) {
Matrix* hidden1_outputs = apply(relu, add(dot(network->weights_1, image_data), network->bias_1));
//Matrix* predict_image(Neural_Network* network, Image*);
Matrix* hidden2_outputs = apply(relu, add(dot(network->weights_2, hidden1_outputs), network->bias_2));
Matrix* hidden3_outputs = apply(relu, add(dot(network->weights_3, hidden2_outputs), network->bias_3));
Matrix* final_outputs = apply(relu, dot(network->weights_output, hidden3_outputs));
Matrix* result = softmax(final_outputs);
matrix_free(hidden1_outputs);
matrix_free(hidden2_outputs);
matrix_free(hidden3_outputs);
matrix_free(final_outputs);
return result;
}
//Matrix* predict(Neural_Network* network, Matrix* image_data) {
// Matrix* hidden1_outputs = apply(relu, add(dot(network->weights_1, image_data), network->bias_1));
//
// Matrix* hidden2_outputs = apply(relu, add(dot(network->weights_2, hidden1_outputs), network->bias_2));
//
// Matrix* hidden3_outputs = apply(relu, add(dot(network->weights_3, hidden2_outputs), network->bias_3));
//
// Matrix* final_outputs = apply(relu, dot(network->weights_output, hidden3_outputs));
//
// Matrix* result = softmax(final_outputs);
//
// matrix_free(hidden1_outputs);
// matrix_free(hidden2_outputs);
// matrix_free(hidden3_outputs);
// matrix_free(final_outputs);
//
// return result;
//}
void train_network(Neural_Network* network, Matrix* input, Matrix* output);
void batch_train_network(Neural_Network* network, Image** images, int size);