Connected layers work forward and backward!

.gitignore

@@ -3,6 +3,7 @@
 *.csv
 images/
 opencv/
+convnet/
 cnn
 
 # OS Generated #

Makefile

@@ -1,10 +1,10 @@
 CC=gcc
 CFLAGS=-Wall `pkg-config --cflags opencv` -O3 -flto -ffast-math
-#CFLAGS=-Wall `pkg-config --cflags opencv` -O0 -g
+CFLAGS=-Wall `pkg-config --cflags opencv` -O0 -g
 LDFLAGS=`pkg-config --libs opencv` -lm
 VPATH=./src/
 
-OBJ=network.o image.o tests.o convolutional_layer.o connected_layer.o maxpool_layer.o
+OBJ=network.o image.o tests.o convolutional_layer.o connected_layer.o maxpool_layer.o activations.o
 
 all: cnn
 

src/activations.c

@@ -0,0 +1,32 @@
+#include "activations.h"
+
+#include <math.h>
+
+double identity_activation(double x)
+{
+    return x;
+}
+double identity_gradient(double x)
+{
+    return 1;
+}
+
+double relu_activation(double x)
+{
+    return x*(x>0);
+}
+double relu_gradient(double x)
+{
+    return (x>=0);
+}
+
+double sigmoid_activation(double x)
+{
+    return 1./(1.+exp(-x));
+}
+
+double sigmoid_gradient(double x)
+{
+    return x*(1.-x);
+}
+

src/activations.h

@@ -0,0 +1,10 @@
+typedef enum{
+    SIGMOID, RELU, IDENTITY
+}ACTIVATOR_TYPE;
+
+double relu_activation(double x);
+double relu_gradient(double x);
+double sigmoid_activation(double x);
+double sigmoid_gradient(double x);
+double identity_activation(double x);
+double identity_gradient(double x);

src/connected_layer.c

@@ -1,19 +1,10 @@
 #include "connected_layer.h"
 
+#include <math.h>
 #include <stdlib.h>
 #include <string.h>
 
-double activation(double x)
-{
-    return x*(x>0);
-}
-
-double gradient(double x)
-{
-    return (x>=0);
-}
-
-connected_layer make_connected_layer(int inputs, int outputs)
+connected_layer make_connected_layer(int inputs, int outputs, ACTIVATOR_TYPE activator)
 {
     int i;
     connected_layer layer;
@@ -32,6 +23,17 @@ connected_layer make_connected_layer(int inputs, int outputs)
     for(i = 0; i < outputs; ++i)
         layer.biases[i] = (double)rand()/RAND_MAX;
 
+    if(activator == SIGMOID){
+        layer.activation = sigmoid_activation;
+        layer.gradient = sigmoid_gradient;
+    }else if(activator == RELU){
+        layer.activation = relu_activation;
+        layer.gradient = relu_gradient;
+    }else if(activator == IDENTITY){
+        layer.activation = identity_activation;
+        layer.gradient = identity_gradient;
+    }
+
     return layer;
 }
 
@@ -41,39 +43,16 @@ void run_connected_layer(double *input, connected_layer layer)
     for(i = 0; i < layer.outputs; ++i){
         layer.output[i] = layer.biases[i];
         for(j = 0; j < layer.inputs; ++j){
-            layer.output[i] += input[j]*layer.weights[i*layer.outputs + j];
+            layer.output[i] += input[j]*layer.weights[i*layer.inputs + j];
         }
-        layer.output[i] = activation(layer.output[i]);
+        layer.output[i] = layer.activation(layer.output[i]);
     }
 }
 
-void backpropagate_connected_layer(double *input, connected_layer layer)
+void learn_connected_layer(double *input, connected_layer layer)
 {
-    int i, j;
-    double *old_input = calloc(layer.inputs, sizeof(double));
-    memcpy(old_input, input, layer.inputs*sizeof(double));
-    memset(input, 0, layer.inputs*sizeof(double));
-
-    for(i = 0; i < layer.outputs; ++i){
-        for(j = 0; j < layer.inputs; ++j){
-            input[j] += layer.output[i]*layer.weights[i*layer.outputs + j];
-        }
-    }
-    for(j = 0; j < layer.inputs; ++j){
-        input[j] = input[j]*gradient(old_input[j]);
-    }
-    free(old_input);
-}
-
-void calculate_updates_connected_layer(double *input, connected_layer layer)
-{
-    int i, j;
-    for(i = 0; i < layer.outputs; ++i){
-        layer.bias_updates[i] += layer.output[i];
-        for(j = 0; j < layer.inputs; ++j){
-            layer.weight_updates[i*layer.outputs + j] += layer.output[i]*input[j];
-        }
-    }
+    calculate_update_connected_layer(input, layer);
+    backpropagate_connected_layer(input, layer);
 }
 
 void update_connected_layer(connected_layer layer, double step)
@@ -82,11 +61,36 @@ void update_connected_layer(connected_layer layer, double step)
     for(i = 0; i < layer.outputs; ++i){
         layer.biases[i] += step*layer.bias_updates[i];
         for(j = 0; j < layer.inputs; ++j){
-            int index = i*layer.outputs+j;
-            layer.weights[index] = layer.weight_updates[index];
+            int index = i*layer.inputs+j;
+            layer.weights[index] += step*layer.weight_updates[index];
         }
     }
     memset(layer.bias_updates, 0, layer.outputs*sizeof(double));
     memset(layer.weight_updates, 0, layer.outputs*layer.inputs*sizeof(double));
 }
 
+void calculate_update_connected_layer(double *input, connected_layer layer)
+{
+    int i, j;
+    for(i = 0; i < layer.outputs; ++i){
+        layer.bias_updates[i] += layer.output[i];
+        for(j = 0; j < layer.inputs; ++j){
+            layer.weight_updates[i*layer.inputs + j] += layer.output[i]*input[j];
+        }
+    }
+}
+
+void backpropagate_connected_layer(double *input, connected_layer layer)
+{
+    int i, j;
+
+    for(j = 0; j < layer.inputs; ++j){
+        double grad = layer.gradient(input[j]);
+        input[j] = 0;
+        for(i = 0; i < layer.outputs; ++i){
+            input[j] += layer.output[i]*layer.weights[i*layer.inputs + j];
+        }
+        input[j] *= grad;
+    }
+}
+

src/connected_layer.h

@@ -1,6 +1,8 @@
 #ifndef CONNECTED_LAYER_H
 #define CONNECTED_LAYER_H
 
+#include "activations.h"
+
 typedef struct{
     int inputs;
     int outputs;
@@ -9,13 +11,19 @@ typedef struct{
     double *weight_updates;
     double *bias_updates;
     double *output;
+
+    double (* activation)();
+    double (* gradient)();
 } connected_layer;
 
-connected_layer make_connected_layer(int inputs, int outputs);
+connected_layer make_connected_layer(int inputs, int outputs, ACTIVATOR_TYPE activator);
+
 void run_connected_layer(double *input, connected_layer layer);
-void backpropagate_connected_layer(double *input, connected_layer layer);
-void calculate_updates_connected_layer(double *input, connected_layer layer);
+void learn_connected_layer(double *input, connected_layer layer);
 void update_connected_layer(connected_layer layer, double step);
 
+void backpropagate_connected_layer(double *input, connected_layer layer);
+void calculate_update_connected_layer(double *input, connected_layer layer);
+
 #endif
 

src/convolutional_layer.c

@@ -33,12 +33,12 @@ void run_convolutional_layer(const image input, const convolutional_layer layer)
     for(i = 0; i < layer.n; ++i){
         convolve(input, layer.kernels[i], layer.stride, i, layer.output);
     }
-    for(i = 0; i < input.h*input.w*input.c; ++i){
-        input.data[i] = convolution_activation(input.data[i]);
+    for(i = 0; i < layer.output.h*layer.output.w*layer.output.c; ++i){
+        layer.output.data[i] = convolution_activation(layer.output.data[i]);
     }
 }
 
-void backpropagate_layer(image input, convolutional_layer layer)
+void backpropagate_convolutional_layer(image input, convolutional_layer layer)
 {
     int i;
     zero_image(input);
@@ -47,7 +47,7 @@ void backpropagate_layer(image input, convolutional_layer layer)
     }
 }
 
-void backpropagate_layer_convolve(image input, convolutional_layer layer)
+void backpropagate_convolutional_layer_convolve(image input, convolutional_layer layer)
 {
     int i,j;
     for(i = 0; i < layer.n; ++i){
@@ -67,20 +67,29 @@ void backpropagate_layer_convolve(image input, convolutional_layer layer)
     }
 }
 
-void error_convolutional_layer(image input, convolutional_layer layer)
+void learn_convolutional_layer(image input, convolutional_layer layer)
 {
     int i;
     for(i = 0; i < layer.n; ++i){
         kernel_update(input, layer.kernel_updates[i], layer.stride, i, layer.output);
     }
     image old_input = copy_image(input);
-    zero_image(input);
-    for(i = 0; i < layer.n; ++i){
-        back_convolve(input, layer.kernels[i], layer.stride, i, layer.output);
-    }
+    backpropagate_convolutional_layer(input, layer);
     for(i = 0; i < input.h*input.w*input.c; ++i){
-        input.data[i] = input.data[i]*convolution_gradient(input.data[i]);
+        input.data[i] *= convolution_gradient(old_input.data[i]);
     }
     free_image(old_input);
 }
 
+void update_convolutional_layer(convolutional_layer layer, double step)
+{
+    int i,j;
+    for(i = 0; i < layer.n; ++i){
+        int pixels = layer.kernels[i].h*layer.kernels[i].w*layer.kernels[i].c;
+        for(j = 0; j < pixels; ++j){
+            layer.kernels[i].data[j] += step*layer.kernel_updates[i].data[j];
+        }
+        zero_image(layer.kernel_updates[i]);
+    }
+}
+

src/convolutional_layer.h

@@ -14,8 +14,7 @@ typedef struct {
 
 convolutional_layer make_convolutional_layer(int w, int h, int c, int n, int size, int stride);
 void run_convolutional_layer(const image input, const convolutional_layer layer);
-void backpropagate_layer(image input, convolutional_layer layer);
-void backpropagate_layer_convolve(image input, convolutional_layer layer);
+void learn_convolutional_layer(image input, convolutional_layer layer);
 
 #endif
 

src/image.c

@@ -132,7 +132,7 @@ image make_random_image(int h, int w, int c)
     image out = make_image(h,w,c);
     int i;
     for(i = 0; i < h*w*c; ++i){
-        out.data[i] = (double)rand()/RAND_MAX;
+        out.data[i] = .5-(double)rand()/RAND_MAX;
     }
     return out;
 }

src/network.c

@@ -8,7 +8,7 @@
 void run_network(image input, network net)
 {
     int i;
-    double *input_d = 0;
+    double *input_d = input.data;
     for(i = 0; i < net.n; ++i){
         if(net.types[i] == CONVOLUTIONAL){
             convolutional_layer layer = *(convolutional_layer *)net.layers[i];
@@ -30,6 +30,77 @@ void run_network(image input, network net)
     }
 }
 
+void update_network(network net, double step)
+{
+    int i;
+    for(i = 0; i < net.n; ++i){
+        if(net.types[i] == CONVOLUTIONAL){
+            convolutional_layer layer = *(convolutional_layer *)net.layers[i];
+            update_convolutional_layer(layer, step);
+        }
+        else if(net.types[i] == MAXPOOL){
+            //maxpool_layer layer = *(maxpool_layer *)net.layers[i];
+        }
+        else if(net.types[i] == CONNECTED){
+            connected_layer layer = *(connected_layer *)net.layers[i];
+            update_connected_layer(layer, step);
+        }
+    }
+}
+
+void learn_network(image input, network net)
+{
+    int i;
+    image prev;
+    double *prev_p;
+    for(i = net.n-1; i >= 0; --i){
+        if(i == 0){
+            prev = input;
+            prev_p = prev.data;
+        } else if(net.types[i-1] == CONVOLUTIONAL){
+            convolutional_layer layer = *(convolutional_layer *)net.layers[i-1];
+            prev = layer.output;
+            prev_p = prev.data;
+        } else if(net.types[i-1] == MAXPOOL){
+            maxpool_layer layer = *(maxpool_layer *)net.layers[i-1];
+            prev = layer.output;
+            prev_p = prev.data;
+        } else if(net.types[i-1] == CONNECTED){
+            connected_layer layer = *(connected_layer *)net.layers[i-1];
+            prev_p = layer.output;
+        }
+
+        if(net.types[i] == CONVOLUTIONAL){
+            convolutional_layer layer = *(convolutional_layer *)net.layers[i];
+            learn_convolutional_layer(prev, layer);
+        }
+        else if(net.types[i] == MAXPOOL){
+            //maxpool_layer layer = *(maxpool_layer *)net.layers[i];
+        }
+        else if(net.types[i] == CONNECTED){
+            connected_layer layer = *(connected_layer *)net.layers[i];
+            learn_connected_layer(prev_p, layer);
+        }
+    }
+}
+
+double *get_network_output(network net)
+{
+    int i = net.n-1;
+    if(net.types[i] == CONVOLUTIONAL){
+        convolutional_layer layer = *(convolutional_layer *)net.layers[i];
+        return layer.output.data;
+    }
+    else if(net.types[i] == MAXPOOL){
+        maxpool_layer layer = *(maxpool_layer *)net.layers[i];
+        return layer.output.data;
+    }
+    else if(net.types[i] == CONNECTED){
+        connected_layer layer = *(connected_layer *)net.layers[i];
+        return layer.output;
+    }
+    return 0;
+}
 image get_network_image(network net)
 {
     int i;

src/network.h

@@ -17,6 +17,9 @@ typedef struct {
 } network;
 
 void run_network(image input, network net);
+double *get_network_output(network net);
+void learn_network(image input, network net);
+void update_network(network net, double step);
 image get_network_image(network net);
 
 #endif

src/tests.c

@@ -34,11 +34,11 @@ void test_color()
 void test_convolutional_layer()
 {
     srand(0);
-    image dog = load_image("test_dog.jpg");
+    image dog = load_image("dog.jpg");
     int i;
-    int n = 5;
+    int n = 3;
     int stride = 1;
-    int size = 8;
+    int size = 3;
     convolutional_layer layer = make_convolutional_layer(dog.h, dog.w, dog.c, n, size, stride);
     char buff[256];
     for(i = 0; i < n; ++i) {
@@ -47,7 +47,7 @@ void test_convolutional_layer()
     }
     run_convolutional_layer(dog, layer);
     
-    maxpool_layer mlayer = make_maxpool_layer(layer.output.h, layer.output.w, layer.output.c, 3);
+    maxpool_layer mlayer = make_maxpool_layer(layer.output.h, layer.output.w, layer.output.c, 2);
     run_maxpool_layer(layer.output,mlayer);
 
     show_image_layers(mlayer.output, "Test Maxpool Layer");
@@ -128,9 +128,9 @@ void test_network()
     n = 128;
     convolutional_layer cl5 = make_convolutional_layer(cl4.output.h, cl4.output.w, cl4.output.c, n, size, stride);
     maxpool_layer ml3 = make_maxpool_layer(cl5.output.h, cl5.output.w, cl5.output.c, 4);
-    connected_layer nl = make_connected_layer(ml3.output.h*ml3.output.w*ml3.output.c, 4096);
-    connected_layer nl2 = make_connected_layer(4096, 4096);
-    connected_layer nl3 = make_connected_layer(4096, 1000);
+    connected_layer nl = make_connected_layer(ml3.output.h*ml3.output.w*ml3.output.c, 4096, RELU);
+    connected_layer nl2 = make_connected_layer(4096, 4096, RELU);
+    connected_layer nl3 = make_connected_layer(4096, 1000, RELU);
 
     net.layers[0] = &cl;
     net.layers[1] = &ml;
@@ -155,6 +155,7 @@ void test_network()
 
     show_image_layers(get_network_image(net), "Test Network Layer");
 }
+
 void test_backpropagate()
 {
     int n = 3;
@@ -169,13 +170,13 @@ void test_backpropagate()
     int i;
     clock_t start = clock(), end;
     for(i = 0; i < 100; ++i){
-        backpropagate_layer(dog_copy, cl);
+        backpropagate_convolutional_layer(dog_copy, cl);
     }
     end = clock();
     printf("Backpropagate: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
     start = clock();
     for(i = 0; i < 100; ++i){
-        backpropagate_layer_convolve(dog, cl);
+        backpropagate_convolutional_layer_convolve(dog, cl);
     }
     end = clock();
     printf("Backpropagate Using Convolutions: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
@@ -185,14 +186,54 @@ void test_backpropagate()
     show_image(dog, "Test Backpropagate Difference");
 }
 
+void test_ann()
+{
+    network net;
+    net.n = 3;
+    net.layers = calloc(net.n, sizeof(void *));
+    net.types = calloc(net.n, sizeof(LAYER_TYPE));
+    net.types[0] = CONNECTED;
+    net.types[1] = CONNECTED;
+    net.types[2] = CONNECTED;
+
+    connected_layer nl = make_connected_layer(1, 20, RELU);
+    connected_layer nl2 = make_connected_layer(20, 20, RELU);
+    connected_layer nl3 = make_connected_layer(20, 1, RELU);
+
+    net.layers[0] = &nl;
+    net.layers[1] = &nl2;
+    net.layers[2] = &nl3;
+
+    image t = make_image(1,1,1);
+    int count = 0;
+        
+    double avgerr = 0;
+    while(1){
+        double v = ((double)rand()/RAND_MAX);
+        double truth = v*v;
+        set_pixel(t,0,0,0,v);
+        run_network(t, net);
+        double *out = get_network_output(net);
+        double err = pow((out[0]-truth),2.);
+        avgerr = .99 * avgerr + .01 * err;
+        //if(++count % 100000 == 0) printf("%f\n", avgerr);
+        if(++count % 100000 == 0) printf("%f %f :%f AVG %f \n", truth, out[0], err, avgerr);
+        out[0] = truth - out[0];
+        learn_network(t, net);
+        update_network(net, .001);
+    }
+
+}
+
 int main()
 {
     //test_backpropagate();
+    test_ann();
     //test_convolve();
     //test_upsample();
     //test_rotate();
     //test_load();
-    test_network();
+    //test_network();
     //test_convolutional_layer();
     //test_color();
     cvWaitKey(0);