External/genann
1
0
Fork 0
mirror of https://github.com/codeplea/genann.git synced 2025-10-03 16:51:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

Changed name case, code style.

Browse Source
This commit is contained in:
Lewis Van Winkle
2016-02-11 14:38:42 -06:00
parent 2bbc1b146c
commit 99e4d6a0e1
8 changed files with 61 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
README.md
View File

@@ -1,6 +1,6 @@
#GENANN #Genann
GENANN is a very minimal library for training and using feedforward artificial neural Genann is a very minimal library for training and using feedforward artificial neural
networks (ANN) in C. Its primary focus is on being simple, fast, and hackable. It achieves networks (ANN) in C. Its primary focus is on being simple, fast, and hackable. It achieves
this by providing only the necessary functions and little extra. this by providing only the necessary functions and little extra.
@@ -39,7 +39,7 @@ double **training_data_input, **training_data_output, **test_data_input;
/* New network with 5 inputs, /* New network with 5 inputs,
* 2 hidden layer of 10 neurons each, * 2 hidden layer of 10 neurons each,
* and 1 output. */ * and 1 output. */
GENANN *ann = genann_init(5, 2, 10, 1); genann *ann = genann_init(5, 2, 10, 1);
/* Learn on the training set. */ /* Learn on the training set. */
for (i = 0; i < 300; ++i) { for (i = 0; i < 300; ++i) {
@@ -63,23 +63,23 @@ prevent over-fitting.
###Creating and Freeing ANNs ###Creating and Freeing ANNs
```C ```C
GENANN *genann_init(int inputs, int hidden_layers, int hidden, int outputs); genann *genann_init(int inputs, int hidden_layers, int hidden, int outputs);
GENANN *genann_copy(GENANN const *ann); genann *genann_copy(genann const *ann);
void genann_free(GENANN *ann); void genann_free(genann *ann);
``` ```
Creating a new ANN is done with the `genann_init()` function. It's arguments Creating a new ANN is done with the `genann_init()` function. It's arguments
are the number of inputs, the number of hidden layers, the number of neurons in are the number of inputs, the number of hidden layers, the number of neurons in
each hidden layer, and the number of outputs. It returns a `GENANN` struct pointer. each hidden layer, and the number of outputs. It returns a `genann` struct pointer.
Calling `genann_copy()` will create a deep-copy of an existing GENANN struct. Calling `genann_copy()` will create a deep-copy of an existing `genann` struct.
Call `genann_free()` when you're finished with an ANN returned by `genann_init()`. Call `genann_free()` when you're finished with an ANN returned by `genann_init()`.
###Training ANNs ###Training ANNs
```C ```C
void genann_train(GENANN const *ann, double const *inputs, void genann_train(genann const *ann, double const *inputs,
double const *desired_outputs, double learning_rate); double const *desired_outputs, double learning_rate);
``` ```
@@ -88,14 +88,14 @@ should be called by passing in an array of inputs, an array of expected output,
and a learning rate. See *example1.c* for an example of learning with and a learning rate. See *example1.c* for an example of learning with
backpropogation. backpropogation.
A primary design goal of GENANN was to store all the network weights in one A primary design goal of Genann was to store all the network weights in one
contigious block of memory. This makes it easy and efficient to train the contigious block of memory. This makes it easy and efficient to train the
network weights using direct-search numeric optimizion algorthims, network weights using direct-search numeric optimizion algorthims,
such as [Hill Climbing](https://en.wikipedia.org/wiki/Hill_climbing), such as [Hill Climbing](https://en.wikipedia.org/wiki/Hill_climbing),
[the Genetic Algorithm](https://en.wikipedia.org/wiki/Genetic_algorithm), [Simulated [the Genetic Algorithm](https://en.wikipedia.org/wiki/Genetic_algorithm), [Simulated
Annealing](https://en.wikipedia.org/wiki/Simulated_annealing), etc. Annealing](https://en.wikipedia.org/wiki/Simulated_annealing), etc.
These methods can be used by searching on the ANN's weights directly. These methods can be used by searching on the ANN's weights directly.
Every `GENANN` struct contains the members `int total_weights;` and Every `genann` struct contains the members `int total_weights;` and
`double *weight;`. `*weight` points to an array of `total_weights` `double *weight;`. `*weight` points to an array of `total_weights`
size which contains all weights used by the ANN. See *example2.c* for size which contains all weights used by the ANN. See *example2.c* for
an example of training using random hill climbing search. an example of training using random hill climbing search.
@@ -103,16 +103,16 @@ an example of training using random hill climbing search.
###Saving and Loading ANNs ###Saving and Loading ANNs
```C ```C
GENANN *genann_read(FILE *in); genann *genann_read(FILE *in);
void genann_write(GENANN const *ann, FILE *out); void genann_write(genann const *ann, FILE *out);
``` ```
GENANN provides the `genann_read()` and `genann_write()` functions for loading or saving an ANN in a text-based format. Genann provides the `genann_read()` and `genann_write()` functions for loading or saving an ANN in a text-based format.
###Evaluating ###Evaluating
```C ```C
double const *genann_run(GENANN const *ann, double const *inputs); double const *genann_run(genann const *ann, double const *inputs);
``` ```
Call `genann_run()` on a trained ANN to run a feed-forward pass on a given set of inputs. `genann_run()` Call `genann_run()` on a trained ANN to run a feed-forward pass on a given set of inputs. `genann_run()`
@@ -134,4 +134,4 @@ If you're looking for a heavier, more opinionated neural network library in C,
I highly recommend the [FANN library](http://leenissen.dk/fann/wp/). Another I highly recommend the [FANN library](http://leenissen.dk/fann/wp/). Another
good library is Peter van Rossum's [Lightweight Neural good library is Peter van Rossum's [Lightweight Neural
Network](http://lwneuralnet.sourceforge.net/), which despite its name, is Network](http://lwneuralnet.sourceforge.net/), which despite its name, is
heavier and has more features than GENANN. heavier and has more features than Genann.

2
example1.c
View File

@@ -14,7 +14,7 @@ int main(int argc, char *argv[])
/* New network with 2 inputs, /* New network with 2 inputs,
* 1 hidden layer of 2 neurons, * 1 hidden layer of 2 neurons,
* and 1 output. */ * and 1 output. */
GENANN *ann = genann_init(2, 1, 2, 1); genann *ann = genann_init(2, 1, 2, 1);
/* Train on the four labeled data points many times. */ /* Train on the four labeled data points many times. */
for (i = 0; i < 300; ++i) { for (i = 0; i < 300; ++i) {

4
example2.c
View File

@@ -16,7 +16,7 @@ int main(int argc, char *argv[])
/* New network with 2 inputs, /* New network with 2 inputs,
* 1 hidden layer of 2 neurons, * 1 hidden layer of 2 neurons,
* and 1 output. */ * and 1 output. */
GENANN *ann = genann_init(2, 1, 2, 1); genann *ann = genann_init(2, 1, 2, 1);
double err; double err;
double last_err = 1000; double last_err = 1000;
@@ -29,7 +29,7 @@ int main(int argc, char *argv[])
genann_randomize(ann); genann_randomize(ann);
} }
GENANN *save = genann_copy(ann); genann *save = genann_copy(ann);
/* Take a random guess at the ANN weights. */ /* Take a random guess at the ANN weights. */
for (i = 0; i < ann->total_weights; ++i) { for (i = 0; i < ann->total_weights; ++i) {

2
example3.c
View File

@@ -16,7 +16,7 @@ int main(int argc, char *argv[])
exit(1); exit(1);
} }
GENANN *ann = genann_read(saved); genann *ann = genann_read(saved);
fclose(saved); fclose(saved);
if (!ann) { if (!ann) {

2
example4.c
View File

@@ -78,7 +78,7 @@ int main(int argc, char *argv[])
* 1 hidden layer(s) of 4 neurons. * 1 hidden layer(s) of 4 neurons.
* 3 outputs (1 per class) * 3 outputs (1 per class)
*/ */
GENANN *ann = genann_init(4, 1, 4, 3); genann *ann = genann_init(4, 1, 4, 3);
int i, j; int i, j;
int loops = 5000; int loops = 5000;

34
genann.c
View File

@@ -75,7 +75,7 @@ double genann_act_threshold(double a) {
} }
GENANN *genann_init(int inputs, int hidden_layers, int hidden, int outputs) { genann *genann_init(int inputs, int hidden_layers, int hidden, int outputs) {
if (hidden_layers < 0) return 0; if (hidden_layers < 0) return 0;
if (inputs < 1) return 0; if (inputs < 1) return 0;
if (outputs < 1) return 0; if (outputs < 1) return 0;
@@ -89,8 +89,8 @@ GENANN *genann_init(int inputs, int hidden_layers, int hidden, int outputs) {
const int total_neurons = (inputs + hidden * hidden_layers + outputs); const int total_neurons = (inputs + hidden * hidden_layers + outputs);
/* Allocate extra size for weights, outputs, and deltas. */ /* Allocate extra size for weights, outputs, and deltas. */
const int size = sizeof(GENANN) + sizeof(double) * (total_weights + total_neurons + (total_neurons - inputs)); const int size = sizeof(genann) + sizeof(double) * (total_weights + total_neurons + (total_neurons - inputs));
GENANN *ret = malloc(size); genann *ret = malloc(size);
if (!ret) return 0; if (!ret) return 0;
ret->inputs = inputs; ret->inputs = inputs;
@@ -102,7 +102,7 @@ GENANN *genann_init(int inputs, int hidden_layers, int hidden, int outputs) {
ret->total_neurons = total_neurons; ret->total_neurons = total_neurons;
/* Set pointers. */ /* Set pointers. */
ret->weight = (double*)((char*)ret + sizeof(GENANN)); ret->weight = (double*)((char*)ret + sizeof(genann));
ret->output = ret->weight + ret->total_weights; ret->output = ret->weight + ret->total_weights;
ret->delta = ret->output + ret->total_neurons; ret->delta = ret->output + ret->total_neurons;
@@ -115,11 +115,11 @@ GENANN *genann_init(int inputs, int hidden_layers, int hidden, int outputs) {
} }
GENANN *genann_read(FILE *in) { genann *genann_read(FILE *in) {
int inputs, hidden_layers, hidden, outputs; int inputs, hidden_layers, hidden, outputs;
fscanf(in, "%d %d %d %d", &inputs, &hidden_layers, &hidden, &outputs); fscanf(in, "%d %d %d %d", &inputs, &hidden_layers, &hidden, &outputs);
GENANN *ann = genann_init(inputs, hidden_layers, hidden, outputs); genann *ann = genann_init(inputs, hidden_layers, hidden, outputs);
int i; int i;
for (i = 0; i < ann->total_weights; ++i) { for (i = 0; i < ann->total_weights; ++i) {
@@ -130,15 +130,15 @@ GENANN *genann_read(FILE *in) {
} }
GENANN *genann_copy(GENANN const *ann) { genann *genann_copy(genann const *ann) {
const int size = sizeof(GENANN) + sizeof(double) * (ann->total_weights + ann->total_neurons + (ann->total_neurons - ann->inputs)); const int size = sizeof(genann) + sizeof(double) * (ann->total_weights + ann->total_neurons + (ann->total_neurons - ann->inputs));
GENANN *ret = malloc(size); genann *ret = malloc(size);
if (!ret) return 0; if (!ret) return 0;
memcpy(ret, ann, size); memcpy(ret, ann, size);
/* Set pointers. */ /* Set pointers. */
ret->weight = (double*)((char*)ret + sizeof(GENANN)); ret->weight = (double*)((char*)ret + sizeof(genann));
ret->output = ret->weight + ret->total_weights; ret->output = ret->weight + ret->total_weights;
ret->delta = ret->output + ret->total_neurons; ret->delta = ret->output + ret->total_neurons;
@@ -146,7 +146,7 @@ GENANN *genann_copy(GENANN const *ann) {
} }
void genann_randomize(GENANN *ann) { void genann_randomize(genann *ann) {
int i; int i;
for (i = 0; i < ann->total_weights; ++i) { for (i = 0; i < ann->total_weights; ++i) {
double r = GENANN_RANDOM(); double r = GENANN_RANDOM();
@@ -156,13 +156,13 @@ void genann_randomize(GENANN *ann) {
} }
void genann_free(GENANN *ann) { void genann_free(genann *ann) {
/* The weight, output, and delta pointers go to the same buffer. */ /* The weight, output, and delta pointers go to the same buffer. */
free(ann); free(ann);
} }
double const *genann_run(GENANN const *ann, double const *inputs) { double const *genann_run(genann const *ann, double const *inputs) {
double const *w = ann->weight; double const *w = ann->weight;
double *o = ann->output + ann->inputs; double *o = ann->output + ann->inputs;
double const *i = ann->output; double const *i = ann->output;
@@ -173,8 +173,8 @@ double const *genann_run(GENANN const *ann, double const *inputs) {
int h, j, k; int h, j, k;
const GENANN_ACTFUN act = ann->activation_hidden; const genann_actfun act = ann->activation_hidden;
const GENANN_ACTFUN acto = ann->activation_output; const genann_actfun acto = ann->activation_output;
/* Figure hidden layers, if any. */ /* Figure hidden layers, if any. */
for (h = 0; h < ann->hidden_layers; ++h) { for (h = 0; h < ann->hidden_layers; ++h) {
@@ -217,7 +217,7 @@ double const *genann_run(GENANN const *ann, double const *inputs) {
} }
void genann_train(GENANN const *ann, double const *inputs, double const *desired_outputs, double learning_rate) { void genann_train(genann const *ann, double const *inputs, double const *desired_outputs, double learning_rate) {
/* To begin with, we must run the network forward. */ /* To begin with, we must run the network forward. */
genann_run(ann, inputs); genann_run(ann, inputs);
@@ -334,7 +334,7 @@ void genann_train(GENANN const *ann, double const *inputs, double const *desired
} }
void genann_write(GENANN const *ann, FILE *out) { void genann_write(genann const *ann, FILE *out) {
fprintf(out, "%d %d %d %d", ann->inputs, ann->hidden_layers, ann->hidden, ann->outputs); fprintf(out, "%d %d %d %d", ann->inputs, ann->hidden_layers, ann->hidden, ann->outputs);
int i; int i;

26
genann.h
View File

@@ -40,18 +40,18 @@ extern "C" {
#endif #endif
typedef double (*GENANN_ACTFUN)(double a); typedef double (*genann_actfun)(double a);
typedef struct GENANN { typedef struct genann {
/* How many inputs, outputs, and hidden neurons. */ /* How many inputs, outputs, and hidden neurons. */
int inputs, hidden_layers, hidden, outputs; int inputs, hidden_layers, hidden, outputs;
/* Which activation function to use for hidden neurons. Default: gennann_act_sigmoid_cached*/ /* Which activation function to use for hidden neurons. Default: gennann_act_sigmoid_cached*/
GENANN_ACTFUN activation_hidden; genann_actfun activation_hidden;
/* Which activation function to use for output. Default: gennann_act_sigmoid_cached*/ /* Which activation function to use for output. Default: gennann_act_sigmoid_cached*/
GENANN_ACTFUN activation_output; genann_actfun activation_output;
/* Total number of weights, and size of weights buffer. */ /* Total number of weights, and size of weights buffer. */
int total_weights; int total_weights;
@@ -68,33 +68,33 @@ typedef struct GENANN {
/* Stores delta of each hidden and output neuron (total_neurons - inputs long). */ /* Stores delta of each hidden and output neuron (total_neurons - inputs long). */
double *delta; double *delta;
} GENANN; } genann;
/* Creates and returns a new ann. */ /* Creates and returns a new ann. */
GENANN *genann_init(int inputs, int hidden_layers, int hidden, int outputs); genann *genann_init(int inputs, int hidden_layers, int hidden, int outputs);
/* Creates ANN from file saved with genann_write. */ /* Creates ANN from file saved with genann_write. */
GENANN *genann_read(FILE *in); genann *genann_read(FILE *in);
/* Sets weights randomly. Called by init. */ /* Sets weights randomly. Called by init. */
void genann_randomize(GENANN *ann); void genann_randomize(genann *ann);
/* Returns a new copy of ann. */ /* Returns a new copy of ann. */
GENANN *genann_copy(GENANN const *ann); genann *genann_copy(genann const *ann);
/* Frees the memory used by an ann. */ /* Frees the memory used by an ann. */
void genann_free(GENANN *ann); void genann_free(genann *ann);
/* Runs the feedforward algorithm to calculate the ann's output. */ /* Runs the feedforward algorithm to calculate the ann's output. */
double const *genann_run(GENANN const *ann, double const *inputs); double const *genann_run(genann const *ann, double const *inputs);
/* Does a single backprop update. */ /* Does a single backprop update. */
void genann_train(GENANN const *ann, double const *inputs, double const *desired_outputs, double learning_rate); void genann_train(genann const *ann, double const *inputs, double const *desired_outputs, double learning_rate);
/* Saves the ann. */ /* Saves the ann. */
void genann_write(GENANN const *ann, FILE *out); void genann_write(genann const *ann, FILE *out);
double genann_act_sigmoid(double a); double genann_act_sigmoid(double a);

20
test.c
View File

@@ -32,7 +32,7 @@
void basic() { void basic() {
GENANN *ann = genann_init(1, 0, 0, 1); genann *ann = genann_init(1, 0, 0, 1);
lequal(ann->total_weights, 2); lequal(ann->total_weights, 2);
double a; double a;
@@ -67,7 +67,7 @@ void basic() {
void xor() { void xor() {
GENANN *ann = genann_init(2, 1, 2, 1); genann *ann = genann_init(2, 1, 2, 1);
ann->activation_hidden = genann_act_threshold; ann->activation_hidden = genann_act_threshold;
ann->activation_output = genann_act_threshold; ann->activation_output = genann_act_threshold;
@@ -102,7 +102,7 @@ void xor() {
void backprop() { void backprop() {
GENANN *ann = genann_init(1, 0, 0, 1); genann *ann = genann_init(1, 0, 0, 1);
double input, output; double input, output;
input = .5; input = .5;
@@ -121,7 +121,7 @@ void train_and() {
double input[4][2] = {{0, 0}, {0, 1}, {1, 0}, {1, 1}}; double input[4][2] = {{0, 0}, {0, 1}, {1, 0}, {1, 1}};
double output[4] = {0, 0, 0, 1}; double output[4] = {0, 0, 0, 1};
GENANN *ann = genann_init(2, 0, 0, 1); genann *ann = genann_init(2, 0, 0, 1);
int i, j; int i, j;
@@ -145,7 +145,7 @@ void train_or() {
double input[4][2] = {{0, 0}, {0, 1}, {1, 0}, {1, 1}}; double input[4][2] = {{0, 0}, {0, 1}, {1, 0}, {1, 1}};
double output[4] = {0, 1, 1, 1}; double output[4] = {0, 1, 1, 1};
GENANN *ann = genann_init(2, 0, 0, 1); genann *ann = genann_init(2, 0, 0, 1);
genann_randomize(ann); genann_randomize(ann);
int i, j; int i, j;
@@ -171,7 +171,7 @@ void train_xor() {
double input[4][2] = {{0, 0}, {0, 1}, {1, 0}, {1, 1}}; double input[4][2] = {{0, 0}, {0, 1}, {1, 0}, {1, 1}};
double output[4] = {0, 1, 1, 0}; double output[4] = {0, 1, 1, 0};
GENANN *ann = genann_init(2, 1, 2, 1); genann *ann = genann_init(2, 1, 2, 1);
int i, j; int i, j;
@@ -194,7 +194,7 @@ void train_xor() {
void persist() { void persist() {
GENANN *first = genann_init(1000, 5, 50, 10); genann *first = genann_init(1000, 5, 50, 10);
FILE *out = fopen("persist.txt", "w"); FILE *out = fopen("persist.txt", "w");
genann_write(first, out); genann_write(first, out);
@@ -202,7 +202,7 @@ void persist() {
FILE *in = fopen("persist.txt", "r"); FILE *in = fopen("persist.txt", "r");
GENANN *second = genann_read(in); genann *second = genann_read(in);
fclose(out); fclose(out);
lequal(first->inputs, second->inputs); lequal(first->inputs, second->inputs);
@@ -222,9 +222,9 @@ void persist() {
void copy() { void copy() {
GENANN *first = genann_init(1000, 5, 50, 10); genann *first = genann_init(1000, 5, 50, 10);
GENANN *second = genann_copy(first); genann *second = genann_copy(first);
lequal(first->inputs, second->inputs); lequal(first->inputs, second->inputs);
lequal(first->hidden_layers, second->hidden_layers); lequal(first->hidden_layers, second->hidden_layers);