From 0d6bb5d44d8e815ebf6ccce1dae2f83178780e7b Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Tue, 03 Dec 2013 00:41:40 +0000
Subject: [PATCH] Working?
---
src/tests.c | 372 +++++++++++++++++++++++++++++++++++++++-------------
1 files changed, 277 insertions(+), 95 deletions(-)
diff --git a/src/tests.c b/src/tests.c
index 7e2539a..722de1a 100644
--- a/src/tests.c
+++ b/src/tests.c
@@ -3,6 +3,10 @@
#include "maxpool_layer.h"
#include "network.h"
#include "image.h"
+#include "parser.h"
+#include "data.h"
+#include "matrix.h"
+#include "utils.h"
#include <time.h>
#include <stdlib.h>
@@ -18,7 +22,7 @@
int i;
clock_t start = clock(), end;
for(i = 0; i < 1000; ++i){
- convolve(dog, kernel, 1, 0, edge);
+ convolve(dog, kernel, 1, 0, edge, 1);
}
end = clock();
printf("Convolutions: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
@@ -34,23 +38,79 @@
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;
- convolutional_layer layer = make_convolutional_layer(dog.h, dog.w, dog.c, n, size, stride);
+ int size = 3;
+ convolutional_layer layer = *make_convolutional_layer(dog.h, dog.w, dog.c, n, size, stride, RELU);
char buff[256];
for(i = 0; i < n; ++i) {
sprintf(buff, "Kernel %d", i);
show_image(layer.kernels[i], buff);
}
- run_convolutional_layer(dog, layer);
+ forward_convolutional_layer(layer, dog.data);
- maxpool_layer mlayer = make_maxpool_layer(layer.output.h, layer.output.w, layer.output.c, 3);
- run_maxpool_layer(layer.output,mlayer);
+ image output = get_convolutional_image(layer);
+ maxpool_layer mlayer = *make_maxpool_layer(output.h, output.w, output.c, 2);
+ forward_maxpool_layer(mlayer, layer.output);
- show_image_layers(mlayer.output, "Test Maxpool Layer");
+ show_image_layers(get_maxpool_image(mlayer), "Test Maxpool Layer");
+}
+
+void verify_convolutional_layer()
+{
+ srand(0);
+ int i;
+ int n = 1;
+ int stride = 1;
+ int size = 3;
+ double eps = .00000001;
+ image test = make_random_image(5,5, 1);
+ convolutional_layer layer = *make_convolutional_layer(test.h,test.w,test.c, n, size, stride, RELU);
+ image out = get_convolutional_image(layer);
+ double **jacobian = calloc(test.h*test.w*test.c, sizeof(double));
+
+ forward_convolutional_layer(layer, test.data);
+ image base = copy_image(out);
+
+ for(i = 0; i < test.h*test.w*test.c; ++i){
+ test.data[i] += eps;
+ forward_convolutional_layer(layer, test.data);
+ image partial = copy_image(out);
+ subtract_image(partial, base);
+ scale_image(partial, 1/eps);
+ jacobian[i] = partial.data;
+ test.data[i] -= eps;
+ }
+ double **jacobian2 = calloc(out.h*out.w*out.c, sizeof(double));
+ image in_delta = make_image(test.h, test.w, test.c);
+ image out_delta = get_convolutional_delta(layer);
+ for(i = 0; i < out.h*out.w*out.c; ++i){
+ out_delta.data[i] = 1;
+ backward_convolutional_layer2(layer, test.data, in_delta.data);
+ image partial = copy_image(in_delta);
+ jacobian2[i] = partial.data;
+ out_delta.data[i] = 0;
+ }
+ int j;
+ double *j1 = calloc(test.h*test.w*test.c*out.h*out.w*out.c, sizeof(double));
+ double *j2 = calloc(test.h*test.w*test.c*out.h*out.w*out.c, sizeof(double));
+ for(i = 0; i < test.h*test.w*test.c; ++i){
+ for(j =0 ; j < out.h*out.w*out.c; ++j){
+ j1[i*out.h*out.w*out.c + j] = jacobian[i][j];
+ j2[i*out.h*out.w*out.c + j] = jacobian2[j][i];
+ printf("%f %f\n", jacobian[i][j], jacobian2[j][i]);
+ }
+ }
+
+
+ image mj1 = double_to_image(test.w*test.h*test.c, out.w*out.h*out.c, 1, j1);
+ image mj2 = double_to_image(test.w*test.h*test.c, out.w*out.h*out.c, 1, j2);
+ printf("%f %f\n", avg_image_layer(mj1,0), avg_image_layer(mj2,0));
+ show_image(mj1, "forward jacobian");
+ show_image(mj2, "backward jacobian");
+
}
void test_load()
@@ -89,111 +149,233 @@
show_image(random, "Test Rotate Random");
}
-void test_network()
+void test_parser()
{
- network net;
- net.n = 11;
- net.layers = calloc(net.n, sizeof(void *));
- net.types = calloc(net.n, sizeof(LAYER_TYPE));
- net.types[0] = CONVOLUTIONAL;
- net.types[1] = MAXPOOL;
- net.types[2] = CONVOLUTIONAL;
- net.types[3] = MAXPOOL;
- net.types[4] = CONVOLUTIONAL;
- net.types[5] = CONVOLUTIONAL;
- net.types[6] = CONVOLUTIONAL;
- net.types[7] = MAXPOOL;
- net.types[8] = CONNECTED;
- net.types[9] = CONNECTED;
- net.types[10] = CONNECTED;
-
- image dog = load_image("test_hinton.jpg");
-
- int n = 48;
- int stride = 4;
- int size = 11;
- convolutional_layer cl = make_convolutional_layer(dog.h, dog.w, dog.c, n, size, stride);
- maxpool_layer ml = make_maxpool_layer(cl.output.h, cl.output.w, cl.output.c, 2);
-
- n = 128;
- size = 5;
- stride = 1;
- convolutional_layer cl2 = make_convolutional_layer(ml.output.h, ml.output.w, ml.output.c, n, size, stride);
- maxpool_layer ml2 = make_maxpool_layer(cl2.output.h, cl2.output.w, cl2.output.c, 2);
-
- n = 192;
- size = 3;
- convolutional_layer cl3 = make_convolutional_layer(ml2.output.h, ml2.output.w, ml2.output.c, n, size, stride);
- convolutional_layer cl4 = make_convolutional_layer(cl3.output.h, cl3.output.w, cl3.output.c, n, size, stride);
- 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);
-
- net.layers[0] = &cl;
- net.layers[1] = &ml;
- net.layers[2] = &cl2;
- net.layers[3] = &ml2;
- net.layers[4] = &cl3;
- net.layers[5] = &cl4;
- net.layers[6] = &cl5;
- net.layers[7] = &ml3;
- net.layers[8] = &nl;
- net.layers[9] = &nl2;
- net.layers[10] = &nl3;
-
- int i;
- clock_t start = clock(), end;
- for(i = 0; i < 10; ++i){
- run_network(dog, net);
- rotate_image(dog);
+ network net = parse_network_cfg("test_parser.cfg");
+ double input[1];
+ int count = 0;
+
+ double avgerr = 0;
+ while(1){
+ double v = ((double)rand()/RAND_MAX);
+ double truth = v*v;
+ input[0] = v;
+ forward_network(net, input);
+ double *out = get_network_output(net);
+ double *delta = get_network_delta(net);
+ double err = pow((out[0]-truth),2.);
+ avgerr = .99 * avgerr + .01 * err;
+ //if(++count % 100000 == 0) printf("%f\n", avgerr);
+ if(++count % 1000000 == 0) printf("%f %f :%f AVG %f \n", truth, out[0], err, avgerr);
+ delta[0] = truth - out[0];
+ learn_network(net, input);
+ update_network(net, .001);
}
- end = clock();
- printf("Ran %lf second per iteration\n", (double)(end-start)/CLOCKS_PER_SEC/10);
-
- show_image_layers(get_network_image(net), "Test Network Layer");
}
-void test_backpropagate()
+
+void test_data()
{
- int n = 3;
- int size = 4;
- int stride = 10;
- image dog = load_image("dog.jpg");
- show_image(dog, "Test Backpropagate Input");
- image dog_copy = copy_image(dog);
- convolutional_layer cl = make_convolutional_layer(dog.h, dog.w, dog.c, n, size, stride);
- run_convolutional_layer(dog, cl);
- show_image(cl.output, "Test Backpropagate Output");
+ char *labels[] = {"cat","dog"};
+ batch train = random_batch("train_paths.txt", 101,labels, 2);
+ show_image(train.images[0], "Test Data Loading");
+ show_image(train.images[100], "Test Data Loading");
+ show_image(train.images[10], "Test Data Loading");
+ free_batch(train);
+}
+
+void test_full()
+{
+ network net = parse_network_cfg("full.cfg");
+ srand(0);
+ int i = 0;
+ char *labels[] = {"cat","dog"};
+ while(i++ < 1000 || 1){
+ batch train = random_batch("train_paths.txt", 1000, labels, 2);
+ train_network_batch(net, train);
+ free_batch(train);
+ printf("Round %d\n", i);
+ }
+}
+
+double error_network(network net, matrix m, double *truth)
+{
+ int i;
+ int correct = 0;
+ for(i = 0; i < m.rows; ++i){
+ forward_network(net, m.vals[i]);
+ double *out = get_network_output(net);
+ double err = truth[i] - out[0];
+ if(fabs(err) < .5) ++correct;
+ }
+ return (double)correct/m.rows;
+}
+
+double **one_hot(double *a, int n, int k)
+{
+ int i;
+ double **t = calloc(n, sizeof(double*));
+ for(i = 0; i < n; ++i){
+ t[i] = calloc(k, sizeof(double));
+ int index = (int)a[i];
+ t[i][index] = 1;
+ }
+ return t;
+}
+
+void test_nist()
+{
+ network net = parse_network_cfg("nist.cfg");
+ matrix m = csv_to_matrix("images/nist_train.csv");
+ matrix ho = hold_out_matrix(&m, 3000);
+ double *truth_1d = pop_column(&m, 0);
+ double **truth = one_hot(truth_1d, m.rows, 10);
+ double *ho_truth_1d = pop_column(&ho, 0);
+ double **ho_truth = one_hot(ho_truth_1d, ho.rows, 10);
+ int i,j;
+ clock_t start = clock(), end;
+ int count = 0;
+ double lr = .0001;
+ while(++count <= 3000000){
+ //lr *= .99;
+ int index = 0;
+ int correct = 0;
+ for(i = 0; i < 1000; ++i){
+ index = rand()%m.rows;
+ normalize_array(m.vals[index], 28*28);
+ forward_network(net, m.vals[index]);
+ double *out = get_network_output(net);
+ double *delta = get_network_delta(net);
+ int max_i = 0;
+ double max = out[0];
+ for(j = 0; j < 10; ++j){
+ delta[j] = truth[index][j]-out[j];
+ if(out[j] > max){
+ max = out[j];
+ max_i = j;
+ }
+ }
+ if(truth[index][max_i]) ++correct;
+ learn_network(net, m.vals[index]);
+ update_network(net, lr);
+ }
+ print_network(net);
+ image input = double_to_image(28,28,1, m.vals[index]);
+ show_image(input, "Input");
+ image o = get_network_image(net);
+ show_image_collapsed(o, "Output");
+ visualize_network(net);
+ cvWaitKey(100);
+ //double test_acc = error_network(net, m, truth);
+ //double valid_acc = error_network(net, ho, ho_truth);
+ //printf("%f, %f\n", test_acc, valid_acc);
+ fprintf(stderr, "%5d: %f %f\n",count, (double)correct/1000, lr);
+ //if(valid_acc > .70) break;
+ }
+ end = clock();
+ printf("Neural Net Learning: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
+}
+
+void test_kernel_update()
+{
+ srand(0);
+ double delta[] = {.1};
+ double input[] = {.3, .5, .3, .5, .5, .5, .5, .0, .5};
+ double kernel[] = {1,2,3,4,5,6,7,8,9};
+ convolutional_layer layer = *make_convolutional_layer(3, 3, 1, 1, 3, 1, IDENTITY);
+ layer.kernels[0].data = kernel;
+ layer.delta = delta;
+ learn_convolutional_layer(layer, input);
+ print_image(layer.kernels[0]);
+ print_image(get_convolutional_delta(layer));
+ print_image(layer.kernel_updates[0]);
+
+}
+
+void test_random_classify()
+{
+ network net = parse_network_cfg("connected.cfg");
+ matrix m = csv_to_matrix("train.csv");
+ matrix ho = hold_out_matrix(&m, 2500);
+ double *truth = pop_column(&m, 0);
+ double *ho_truth = pop_column(&ho, 0);
int i;
clock_t start = clock(), end;
- for(i = 0; i < 100; ++i){
- backpropagate_layer(dog_copy, cl);
+ int count = 0;
+ while(++count <= 300){
+ for(i = 0; i < m.rows; ++i){
+ int index = rand()%m.rows;
+ //image p = double_to_image(1690,1,1,m.vals[index]);
+ //normalize_image(p);
+ forward_network(net, m.vals[index]);
+ double *out = get_network_output(net);
+ double *delta = get_network_delta(net);
+ //printf("%f\n", out[0]);
+ delta[0] = truth[index] - out[0];
+ // printf("%f\n", delta[0]);
+ //printf("%f %f\n", truth[index], out[0]);
+ learn_network(net, m.vals[index]);
+ update_network(net, .00001);
+ }
+ double test_acc = error_network(net, m, truth);
+ double valid_acc = error_network(net, ho, ho_truth);
+ printf("%f, %f\n", test_acc, valid_acc);
+ fprintf(stderr, "%5d: %f Valid: %f\n",count, test_acc, valid_acc);
+ //if(valid_acc > .70) break;
}
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);
+ FILE *fp = fopen("submission/out.txt", "w");
+ matrix test = csv_to_matrix("test.csv");
+ truth = pop_column(&test, 0);
+ for(i = 0; i < test.rows; ++i){
+ forward_network(net, test.vals[i]);
+ double *out = get_network_output(net);
+ if(fabs(out[0]) < .5) fprintf(fp, "0\n");
+ else fprintf(fp, "1\n");
}
- end = clock();
- printf("Backpropagate Using Convolutions: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
- show_image(dog_copy, "Test Backpropagate 1");
- show_image(dog, "Test Backpropagate 2");
- subtract_image(dog, dog_copy);
- show_image(dog, "Test Backpropagate Difference");
+ fclose(fp);
+ printf("Neural Net Learning: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
+}
+
+void test_random_preprocess()
+{
+ FILE *file = fopen("train.csv", "w");
+ char *labels[] = {"cat","dog"};
+ int i,j,k;
+ srand(0);
+ network net = parse_network_cfg("convolutional.cfg");
+ for(i = 0; i < 100; ++i){
+ printf("%d\n", i);
+ batch part = get_batch("train_paths.txt", i, 100, labels, 2);
+ for(j = 0; j < part.n; ++j){
+ forward_network(net, part.images[j].data);
+ double *out = get_network_output(net);
+ fprintf(file, "%f", part.truth[j][0]);
+ for(k = 0; k < get_network_output_size(net); ++k){
+ fprintf(file, ",%f", out[k]);
+ }
+ fprintf(file, "\n");
+ }
+ free_batch(part);
+ }
}
int main()
{
+ //test_kernel_update();
+ //test_nist();
+ test_full();
+ //test_random_preprocess();
+ //test_random_classify();
+ //test_parser();
//test_backpropagate();
+ //test_ann();
//test_convolve();
//test_upsample();
//test_rotate();
//test_load();
- test_network();
+ //test_network();
//test_convolutional_layer();
+ //verify_convolutional_layer();
//test_color();
cvWaitKey(0);
return 0;
--
Gitblit v1.10.0