From 228d3663f871d0e4bdee468572eb80141cb4fe3f Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sat, 15 Feb 2014 00:09:07 +0000
Subject: [PATCH] Extracting features from VOC with temp filters
---
src/tests.c | 317 +++++++++++++++++++++++++++++-----------------------
1 files changed, 177 insertions(+), 140 deletions(-)
diff --git a/src/tests.c b/src/tests.c
index c459a36..47c9787 100644
--- a/src/tests.c
+++ b/src/tests.c
@@ -1,4 +1,5 @@
#include "connected_layer.h"
+//#include "old_conv.h"
#include "convolutional_layer.h"
#include "maxpool_layer.h"
#include "network.h"
@@ -13,9 +14,12 @@
#include <stdlib.h>
#include <stdio.h>
+#define _GNU_SOURCE
+#include <fenv.h>
+
void test_convolve()
{
- image dog = load_image("dog.jpg");
+ image dog = load_image("dog.jpg",300,400);
printf("dog channels %d\n", dog.c);
image kernel = make_random_image(3,3,dog.c);
image edge = make_image(dog.h, dog.w, 1);
@@ -25,23 +29,23 @@
convolve(dog, kernel, 1, 0, edge, 1);
}
end = clock();
- printf("Convolutions: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
+ printf("Convolutions: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
show_image_layers(edge, "Test Convolve");
}
void test_convolve_matrix()
{
- image dog = load_image("dog.jpg");
+ image dog = load_image("dog.jpg",300,400);
printf("dog channels %d\n", dog.c);
int size = 11;
- int stride = 1;
+ int stride = 4;
int n = 40;
- double *filters = make_random_image(size, size, dog.c*n).data;
+ float *filters = make_random_image(size, size, dog.c*n).data;
int mw = ((dog.h-size)/stride+1)*((dog.w-size)/stride+1);
int mh = (size*size*dog.c);
- double *matrix = calloc(mh*mw, sizeof(double));
+ float *matrix = calloc(mh*mw, sizeof(float));
image edge = make_image((dog.h-size)/stride+1, (dog.w-size)/stride+1, n);
@@ -53,40 +57,17 @@
gemm(0,0,n,mw,mh,1,filters,mh,matrix,mw,1,edge.data,mw);
}
end = clock();
- printf("Convolutions: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
+ printf("Convolutions: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
show_image_layers(edge, "Test Convolve");
cvWaitKey(0);
}
void test_color()
{
- image dog = load_image("test_color.png");
+ image dog = load_image("test_color.png", 300, 400);
show_image_layers(dog, "Test Color");
}
-void test_convolutional_layer()
-{
- srand(0);
- image dog = load_image("dog.jpg");
- int i;
- int n = 3;
- int stride = 1;
- 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);
- }
- forward_convolutional_layer(layer, dog.data);
-
- 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(get_maxpool_image(mlayer), "Test Maxpool Layer");
-}
-
void verify_convolutional_layer()
{
srand(0);
@@ -94,11 +75,11 @@
int n = 1;
int stride = 1;
int size = 3;
- double eps = .00000001;
+ float 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));
+ float **jacobian = calloc(test.h*test.w*test.c, sizeof(float));
forward_convolutional_layer(layer, test.data);
image base = copy_image(out);
@@ -112,19 +93,19 @@
jacobian[i] = partial.data;
test.data[i] -= eps;
}
- double **jacobian2 = calloc(out.h*out.w*out.c, sizeof(double));
+ float **jacobian2 = calloc(out.h*out.w*out.c, sizeof(float));
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_layer(layer, test.data, in_delta.data);
+ backward_convolutional_layer(layer, 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));
+ float *j1 = calloc(test.h*test.w*test.c*out.h*out.w*out.c, sizeof(float));
+ float *j2 = calloc(test.h*test.w*test.c*out.h*out.w*out.c, sizeof(float));
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];
@@ -134,23 +115,22 @@
}
- 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);
+ image mj1 = float_to_image(test.w*test.h*test.c, out.w*out.h*out.c, 1, j1);
+ image mj2 = float_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()
{
- image dog = load_image("dog.jpg");
+ image dog = load_image("dog.jpg", 300, 400);
show_image(dog, "Test Load");
show_image_layers(dog, "Test Load");
}
void test_upsample()
{
- image dog = load_image("dog.jpg");
+ image dog = load_image("dog.jpg", 300, 400);
int n = 3;
image up = make_image(n*dog.h, n*dog.w, dog.c);
upsample_image(dog, n, up);
@@ -161,13 +141,13 @@
void test_rotate()
{
int i;
- image dog = load_image("dog.jpg");
+ image dog = load_image("dog.jpg",300,400);
clock_t start = clock(), end;
for(i = 0; i < 1001; ++i){
rotate_image(dog);
}
end = clock();
- printf("Rotations: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
+ printf("Rotations: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
show_image(dog, "Test Rotate");
image random = make_random_image(3,3,3);
@@ -181,18 +161,18 @@
void test_parser()
{
network net = parse_network_cfg("test_parser.cfg");
- double input[1];
+ float input[1];
int count = 0;
- double avgerr = 0;
+ float avgerr = 0;
while(++count < 100000000){
- double v = ((double)rand()/RAND_MAX);
- double truth = v*v;
+ float v = ((float)rand()/RAND_MAX);
+ float 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.);
+ float *out = get_network_output(net);
+ float *delta = get_network_delta(net);
+ float err = pow((out[0]-truth),2.);
avgerr = .99 * avgerr + .01 * err;
if(count % 1000000 == 0) printf("%f %f :%f AVG %f \n", truth, out[0], err, avgerr);
delta[0] = truth - out[0];
@@ -204,24 +184,39 @@
void test_data()
{
char *labels[] = {"cat","dog"};
- data train = load_data_image_pathfile_random("train_paths.txt", 101,labels, 2);
+ data train = load_data_image_pathfile_random("train_paths.txt", 101,labels, 2, 300, 400);
free_data(train);
}
void test_full()
{
network net = parse_network_cfg("full.cfg");
- srand(0);
- int i = 0;
+ srand(2222222);
+ int i = 800;
char *labels[] = {"cat","dog"};
- double lr = .00001;
- double momentum = .9;
- double decay = 0.01;
+ float lr = .00001;
+ float momentum = .9;
+ float decay = 0.01;
while(i++ < 1000 || 1){
- data train = load_data_image_pathfile_random("train_paths.txt", 1000, labels, 2);
- train_network(net, train, lr, momentum, decay);
+ visualize_network(net);
+ cvWaitKey(100);
+ data train = load_data_image_pathfile_random("train_paths.txt", 1000, labels, 2, 256, 256);
+ image im = float_to_image(256, 256, 3,train.X.vals[0]);
+ show_image(im, "input");
+ cvWaitKey(100);
+ //scale_data_rows(train, 1./255.);
+ normalize_data_rows(train);
+ clock_t start = clock(), end;
+ float loss = train_network_sgd(net, train, 100, lr, momentum, decay);
+ end = clock();
+ printf("%d: %f, Time: %lf seconds, LR: %f, Momentum: %f, Decay: %f\n", i, loss, (float)(end-start)/CLOCKS_PER_SEC, lr, momentum, decay);
free_data(train);
- printf("Round %d\n", i);
+ if(i%100==0){
+ char buff[256];
+ sprintf(buff, "backup_%d.cfg", i);
+ //save_network(net, buff);
+ }
+ //lr *= .99;
}
}
@@ -229,32 +224,33 @@
{
srand(444444);
srand(888888);
- network net = parse_network_cfg("nist_basic.cfg");
+ network net = parse_network_cfg("nist.cfg");
data train = load_categorical_data_csv("mnist/mnist_train.csv", 0, 10);
data test = load_categorical_data_csv("mnist/mnist_test.csv",0,10);
normalize_data_rows(train);
normalize_data_rows(test);
//randomize_data(train);
int count = 0;
- double lr = .0005;
- double momentum = .9;
- double decay = 0.01;
+ float lr = .0005;
+ float momentum = .9;
+ float decay = 0.001;
clock_t start = clock(), end;
- while(++count <= 1000){
- double acc = train_network_sgd(net, train, 6400, lr, momentum, decay);
- printf("%5d Training Loss: %lf, Params: %f %f %f, ",count*100, 1.-acc, lr, momentum, decay);
- end = clock();
- printf("Time: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
- start=end;
+ while(++count <= 100){
//visualize_network(net);
+ float loss = train_network_sgd(net, train, 1000, lr, momentum, decay);
+ printf("%5d Training Loss: %lf, Params: %f %f %f, ",count*100, loss, lr, momentum, decay);
+ end = clock();
+ printf("Time: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
+ start=end;
//cvWaitKey(100);
//lr /= 2;
- if(count%5 == 0 && 0){
- double train_acc = network_accuracy(net, train);
+ if(count%5 == 0){
+ float train_acc = network_accuracy(net, train);
fprintf(stderr, "\nTRAIN: %f\n", train_acc);
- double test_acc = network_accuracy(net, test);
+ float test_acc = network_accuracy(net, test);
fprintf(stderr, "TEST: %f\n\n", test_acc);
printf("%d, %f, %f\n", count, train_acc, test_acc);
+ //lr *= .5;
}
}
}
@@ -268,70 +264,52 @@
data test = load_categorical_data_csv("mnist/mnist_test.csv", 0,10);
normalize_data_rows(test);
data train = d;
- /*
- data *split = split_data(d, 1, 10);
- data train = split[0];
- data test = split[1];
- */
+ // data *split = split_data(d, 1, 10);
+ // data train = split[0];
+ // data test = split[1];
matrix prediction = make_matrix(test.y.rows, test.y.cols);
int n = 30;
for(i = 0; i < n; ++i){
int count = 0;
- double lr = .0005;
- double momentum = .9;
- double decay = .01;
+ float lr = .0005;
+ float momentum = .9;
+ float decay = .01;
network net = parse_network_cfg("nist.cfg");
while(++count <= 15){
- double acc = train_network_sgd(net, train, train.X.rows, lr, momentum, decay);
+ float acc = train_network_sgd(net, train, train.X.rows, lr, momentum, decay);
printf("Training Accuracy: %lf Learning Rate: %f Momentum: %f Decay: %f\n", acc, lr, momentum, decay );
lr /= 2;
}
matrix partial = network_predict_data(net, test);
- double acc = matrix_accuracy(test.y, partial);
+ float acc = matrix_accuracy(test.y, partial);
printf("Model Accuracy: %lf\n", acc);
matrix_add_matrix(partial, prediction);
acc = matrix_accuracy(test.y, prediction);
printf("Current Ensemble Accuracy: %lf\n", acc);
free_matrix(partial);
}
- double acc = matrix_accuracy(test.y, prediction);
+ float acc = matrix_accuracy(test.y, prediction);
printf("Full Ensemble Accuracy: %lf\n", acc);
}
-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, LINEAR);
- 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);
+ float *truth = pop_column(&m, 0);
+ //float *ho_truth = pop_column(&ho, 0);
int i;
clock_t start = clock(), end;
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]);
+ //image p = float_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);
+ float *out = get_network_output(net);
+ float *delta = get_network_delta(net);
//printf("%f\n", out[0]);
delta[0] = truth[index] - out[0];
// printf("%f\n", delta[0]);
@@ -339,8 +317,8 @@
//backward_network(net, m.vals[index], );
update_network(net, .00001, 0,0);
}
- //double test_acc = error_network(net, m, truth);
- //double valid_acc = error_network(net, ho, ho_truth);
+ //float test_acc = error_network(net, m, truth);
+ //float 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;
@@ -351,12 +329,12 @@
truth = pop_column(&test, 0);
for(i = 0; i < test.rows; ++i){
forward_network(net, test.vals[i]);
- double *out = get_network_output(net);
+ float *out = get_network_output(net);
if(fabs(out[0]) < .5) fprintf(fp, "0\n");
else fprintf(fp, "1\n");
}
fclose(fp);
- printf("Neural Net Learning: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
+ printf("Neural Net Learning: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
}
void test_split()
@@ -366,30 +344,6 @@
printf("%d, %d, %d\n", train.X.rows, split[0].X.rows, split[1].X.rows);
}
-double *random_matrix(int rows, int cols)
-{
- int i, j;
- double *m = calloc(rows*cols, sizeof(double));
- for(i = 0; i < rows; ++i){
- for(j = 0; j < cols; ++j){
- m[i*cols+j] = (double)rand()/RAND_MAX;
- }
- }
- return m;
-}
-
-void test_blas()
-{
- int m = 6025, n = 20, k = 11*11*3;
- double *a = random_matrix(m,k);
- double *b = random_matrix(k,n);
- double *c = random_matrix(m,n);
- int i;
- for(i = 0; i<1000; ++i){
- gemm(0,0,m,n,k,1,a,k,b,n,1,c,n);
- }
-}
-
void test_im2row()
{
int h = 20;
@@ -402,24 +356,107 @@
int mw = ((h-size)/stride+1)*((w-size)/stride+1);
int mh = (size*size*c);
int msize = mc*mw*mh;
- double *matrix = calloc(msize, sizeof(double));
+ float *matrix = calloc(msize, sizeof(float));
int i;
for(i = 0; i < 1000; ++i){
- im2col_cpu(test.data, c, h, w, size, stride, matrix);
- image render = double_to_image(mh, mw, mc, matrix);
+ im2col_cpu(test.data, c, h, w, size, stride, matrix);
+ //image render = float_to_image(mh, mw, mc, matrix);
+ }
+}
+
+void train_VOC()
+{
+ network net = parse_network_cfg("cfg/voc_backup_sig_20.cfg");
+ srand(2222222);
+ int i = 20;
+ char *labels[] = {"aeroplane","bicycle","bird","boat","bottle","bus","car","cat","chair","cow","diningtable","dog","horse","motorbike","person","pottedplant","sheep","sofa","train","tvmonitor"};
+ float lr = .00001;
+ float momentum = .9;
+ float decay = 0.01;
+ while(i++ < 1000 || 1){
+ data train = load_data_image_pathfile_random("images/VOC2012/train_paths.txt", 1000, labels, 20, 300, 400);
+
+ image im = float_to_image(300, 400, 3,train.X.vals[0]);
+ show_image(im, "input");
+ visualize_network(net);
+ cvWaitKey(100);
+
+ normalize_data_rows(train);
+ clock_t start = clock(), end;
+ float loss = train_network_sgd(net, train, 1000, lr, momentum, decay);
+ end = clock();
+ printf("%d: %f, Time: %lf seconds, LR: %f, Momentum: %f, Decay: %f\n", i, loss, (float)(end-start)/CLOCKS_PER_SEC, lr, momentum, decay);
+ free_data(train);
+ if(i%10==0){
+ char buff[256];
+ sprintf(buff, "cfg/voc_backup_sig_%d.cfg", i);
+ save_network(net, buff);
+ }
+ //lr *= .99;
+ }
+}
+
+void features_VOC()
+{
+ int i,j;
+ network net = parse_network_cfg("cfg/voc_features.cfg");
+ char *path_file = "images/VOC2012/all_paths.txt";
+ char *out_dir = "voc_features/";
+ list *paths = get_paths(path_file);
+ node *n = paths->front;
+ while(n){
+ char *path = (char *)n->val;
+ char buff[1024];
+ sprintf(buff, "%s%s.txt",out_dir, path);
+ FILE *fp = fopen(buff, "w");
+ if(fp == 0) file_error(buff);
+
+ IplImage* src = 0;
+ if( (src = cvLoadImage(path,-1)) == 0 )
+ {
+ printf("Cannot load file image %s\n", path);
+ exit(0);
+ }
+
+ for(i = 0; i < 10; ++i){
+ int w = 1024 - 90*i; //PICKED WITH CAREFUL CROSS-VALIDATION!!!!
+ int h = (int)((double)w/src->width * src->height);
+ IplImage *sized = cvCreateImage(cvSize(w,h), src->depth, src->nChannels);
+ cvResize(src, sized, CV_INTER_LINEAR);
+ image im = ipl_to_image(sized);
+ reset_network_size(net, im.h, im.w, im.c);
+ forward_network(net, im.data);
+ free_image(im);
+ image out = get_network_image_layer(net, 5);
+ fprintf(fp, "%d, %d, %d\n",out.c, out.h, out.w);
+ for(j = 0; j < out.c*out.h*out.w; ++j){
+ if(j != 0)fprintf(fp, ",");
+ fprintf(fp, "%g", out.data[j]);
+ }
+ fprintf(fp, "\n");
+ out.c = 1;
+ show_image(out, "output");
+ cvWaitKey(10);
+ cvReleaseImage(&sized);
+ }
+ fclose(fp);
+ n = n->next;
}
}
int main()
{
+ //feenableexcept(FE_DIVBYZERO | FE_INVALID | FE_OVERFLOW);
+
//test_blas();
- //test_convolve_matrix();
-// test_im2row();
- //test_kernel_update();
+ //test_convolve_matrix();
+ // test_im2row();
//test_split();
//test_ensemble();
- test_nist();
+ //test_nist();
//test_full();
+ //train_VOC();
+ features_VOC();
//test_random_preprocess();
//test_random_classify();
//test_parser();
--
Gitblit v1.10.0