From bc902b277e9131cc169751056786de5393da737d Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Mon, 24 Feb 2014 20:21:31 +0000
Subject: [PATCH] Imagenet Features\!
---
src/network.c | 55 ++++++-------
src/image.c | 23 +++++
src/data.c | 1
src/softmax_layer.c | 4
src/tests.c | 105 ++++++++++++++++++++++---
src/image.h | 1
6 files changed, 141 insertions(+), 48 deletions(-)
diff --git a/src/data.c b/src/data.c
index 85c3794..f44f5da 100644
--- a/src/data.c
+++ b/src/data.c
@@ -10,6 +10,7 @@
{
char *path;
FILE *file = fopen(filename, "r");
+ if(!file) file_error(filename);
list *lines = make_list();
while((path=fgetl(file))){
list_insert(lines, path);
diff --git a/src/image.c b/src/image.c
index fad454d..1667977 100644
--- a/src/image.c
+++ b/src/image.c
@@ -4,6 +4,21 @@
int windows = 0;
+image image_distance(image a, image b)
+{
+ int i,j;
+ image dist = make_image(a.h, a.w, 1);
+ for(i = 0; i < a.c; ++i){
+ for(j = 0; j < a.h*a.w; ++j){
+ dist.data[j] += pow(a.data[i*a.h*a.w+j]-b.data[i*a.h*a.w+j],2);
+ }
+ }
+ for(j = 0; j < a.h*a.w; ++j){
+ dist.data[j] = sqrt(dist.data[j]);
+ }
+ return dist;
+}
+
void subtract_image(image a, image b)
{
int i;
@@ -370,9 +385,11 @@
printf("Cannot load file image %s\n", filename);
exit(0);
}
- IplImage *resized = resizeImage(src, h, w, 1);
- cvReleaseImage(&src);
- src = resized;
+ if(h && w ){
+ IplImage *resized = resizeImage(src, h, w, 1);
+ cvReleaseImage(&src);
+ src = resized;
+ }
image out = ipl_to_image(src);
cvReleaseImage(&src);
return out;
diff --git a/src/image.h b/src/image.h
index 0d7d6e2..9f7d74d 100644
--- a/src/image.h
+++ b/src/image.h
@@ -10,6 +10,7 @@
float *data;
} image;
+image image_distance(image a, image b);
void scale_image(image m, float s);
void add_scalar_image(image m, float s);
void normalize_image(image p);
diff --git a/src/network.c b/src/network.c
index f5fea60..b2fc922 100644
--- a/src/network.c
+++ b/src/network.c
@@ -21,18 +21,18 @@
return net;
}
-void print_convolutional_cfg(FILE *fp, convolutional_layer *l)
+void print_convolutional_cfg(FILE *fp, convolutional_layer *l, int first)
{
int i;
- fprintf(fp, "[convolutional]\n"
- "height=%d\n"
- "width=%d\n"
- "channels=%d\n"
- "filters=%d\n"
+ fprintf(fp, "[convolutional]\n");
+ if(first) fprintf(fp, "height=%d\n"
+ "width=%d\n"
+ "channels=%d\n",
+ l->h, l->w, l->c);
+ fprintf(fp, "filters=%d\n"
"size=%d\n"
"stride=%d\n"
"activation=%s\n",
- l->h, l->w, l->c,
l->n, l->size, l->stride,
get_activation_string(l->activation));
fprintf(fp, "data=");
@@ -40,14 +40,14 @@
for(i = 0; i < l->n*l->c*l->size*l->size; ++i) fprintf(fp, "%g,", l->filters[i]);
fprintf(fp, "\n\n");
}
-void print_connected_cfg(FILE *fp, connected_layer *l)
+void print_connected_cfg(FILE *fp, connected_layer *l, int first)
{
int i;
- fprintf(fp, "[connected]\n"
- "input=%d\n"
- "output=%d\n"
+ fprintf(fp, "[connected]\n");
+ if(first) fprintf(fp, "input=%d\n", l->inputs);
+ fprintf(fp, "output=%d\n"
"activation=%s\n",
- l->inputs, l->outputs,
+ l->outputs,
get_activation_string(l->activation));
fprintf(fp, "data=");
for(i = 0; i < l->outputs; ++i) fprintf(fp, "%g,", l->biases[i]);
@@ -55,22 +55,21 @@
fprintf(fp, "\n\n");
}
-void print_maxpool_cfg(FILE *fp, maxpool_layer *l)
+void print_maxpool_cfg(FILE *fp, maxpool_layer *l, int first)
{
- fprintf(fp, "[maxpool]\n"
- "height=%d\n"
- "width=%d\n"
- "channels=%d\n"
- "stride=%d\n\n",
- l->h, l->w, l->c,
- l->stride);
+ fprintf(fp, "[maxpool]\n");
+ if(first) fprintf(fp, "height=%d\n"
+ "width=%d\n"
+ "channels=%d\n",
+ l->h, l->w, l->c);
+ fprintf(fp, "stride=%d\n\n", l->stride);
}
-void print_softmax_cfg(FILE *fp, softmax_layer *l)
+void print_softmax_cfg(FILE *fp, softmax_layer *l, int first)
{
- fprintf(fp, "[softmax]\n"
- "input=%d\n\n",
- l->inputs);
+ fprintf(fp, "[softmax]\n");
+ if(first) fprintf(fp, "input=%d\n", l->inputs);
+ fprintf(fp, "\n");
}
void save_network(network net, char *filename)
@@ -81,13 +80,13 @@
for(i = 0; i < net.n; ++i)
{
if(net.types[i] == CONVOLUTIONAL)
- print_convolutional_cfg(fp, (convolutional_layer *)net.layers[i]);
+ print_convolutional_cfg(fp, (convolutional_layer *)net.layers[i], i==0);
else if(net.types[i] == CONNECTED)
- print_connected_cfg(fp, (connected_layer *)net.layers[i]);
+ print_connected_cfg(fp, (connected_layer *)net.layers[i], i==0);
else if(net.types[i] == MAXPOOL)
- print_maxpool_cfg(fp, (maxpool_layer *)net.layers[i]);
+ print_maxpool_cfg(fp, (maxpool_layer *)net.layers[i], i==0);
else if(net.types[i] == SOFTMAX)
- print_softmax_cfg(fp, (softmax_layer *)net.layers[i]);
+ print_softmax_cfg(fp, (softmax_layer *)net.layers[i], i==0);
}
fclose(fp);
}
diff --git a/src/softmax_layer.c b/src/softmax_layer.c
index 79375de..b6b7ff3 100644
--- a/src/softmax_layer.c
+++ b/src/softmax_layer.c
@@ -36,9 +36,9 @@
}
for(i = 0; i < layer.inputs; ++i){
sum += exp(input[i]-largest);
- printf("%f, ", input[i]);
+ //printf("%f, ", input[i]);
}
- printf("\n");
+ //printf("\n");
if(sum) sum = largest+log(sum);
else sum = largest-100;
for(i = 0; i < layer.inputs; ++i){
diff --git a/src/tests.c b/src/tests.c
index c72e900..91ee4bf 100644
--- a/src/tests.c
+++ b/src/tests.c
@@ -188,37 +188,64 @@
free_data(train);
}
-void test_full()
+void train_full()
{
- network net = parse_network_cfg("full.cfg");
+ network net = parse_network_cfg("cfg/imagenet.cfg");
srand(2222222);
- int i = 800;
+ int i = 0;
char *labels[] = {"cat","dog"};
float lr = .00001;
float momentum = .9;
float decay = 0.01;
- while(i++ < 1000 || 1){
- visualize_network(net);
- cvWaitKey(100);
- data train = load_data_image_pathfile_random("train_paths.txt", 1000, labels, 2, 256, 256);
+ while(1){
+ i += 1000;
+ data train = load_data_image_pathfile_random("images/assira/train.list", 1000, labels, 2, 256, 256);
image im = float_to_image(256, 256, 3,train.X.vals[0]);
- show_image(im, "input");
- cvWaitKey(100);
+ //visualize_network(net);
+ //cvWaitKey(100);
+ //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);
+ 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%100==0){
+ if(i%10000==0){
char buff[256];
- sprintf(buff, "backup_%d.cfg", i);
- //save_network(net, buff);
+ sprintf(buff, "cfg/assira_backup_%d.cfg", i);
+ save_network(net, buff);
}
//lr *= .99;
}
}
+void test_full()
+{
+ network net = parse_network_cfg("cfg/backup_1300.cfg");
+ srand(2222222);
+ int i,j;
+ int total = 100;
+ char *labels[] = {"cat","dog"};
+ FILE *fp = fopen("preds.txt","w");
+ for(i = 0; i < total; ++i){
+ visualize_network(net);
+ cvWaitKey(100);
+ data test = load_data_image_pathfile_part("images/assira/test.list", i, total, labels, 2, 256, 256);
+ image im = float_to_image(256, 256, 3,test.X.vals[0]);
+ show_image(im, "input");
+ cvWaitKey(100);
+ normalize_data_rows(test);
+ for(j = 0; j < test.X.rows; ++j){
+ float *x = test.X.vals[j];
+ forward_network(net, x);
+ int class = get_predicted_class_network(net);
+ fprintf(fp, "%d\n", class);
+ }
+ free_data(test);
+ }
+ fclose(fp);
+}
void test_nist()
{
@@ -400,6 +427,7 @@
{
x = x-1+3;
x = x-1+3;
+ x = x-1+3;
x = (x-1)*2+1;
x = x-1+5;
x = (x-1)*2+1;
@@ -411,13 +439,14 @@
{
int h = voc_size(outh);
int w = voc_size(outw);
+ printf("%d %d\n", h, w);
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);
- image out = get_network_image_layer(net, 5);
+ image out = get_network_image_layer(net, 6);
//printf("%d %d\n%d %d\n", outh, out.h, outw, out.w);
free_image(im);
cvReleaseImage(&sized);
@@ -500,7 +529,7 @@
void features_VOC_image(char *image_file, char *image_dir, char *out_dir)
{
int i,j;
- network net = parse_network_cfg("cfg/voc_features.cfg");
+ network net = parse_network_cfg("cfg/imagenet.cfg");
char image_path[1024];
sprintf(image_path, "%s%s",image_dir, image_file);
char out_path[1024];
@@ -557,8 +586,54 @@
cvReleaseImage(&src);
}
+void test_distribution()
+{
+ IplImage* img = 0;
+ if( (img = cvLoadImage("im_small.jpg",-1)) == 0 ) file_error("im_small.jpg");
+ network net = parse_network_cfg("cfg/voc_features.cfg");
+ int h = img->height/8-2;
+ int w = img->width/8-2;
+ image out = features_output_size(net, img, h, w);
+ int c = out.c;
+ out.c = 1;
+ show_image(out, "output");
+ out.c = c;
+ image input = ipl_to_image(img);
+ show_image(input, "input");
+ CvScalar s;
+ int i,j;
+ image affects = make_image(input.h, input.w, 1);
+ int count = 0;
+ for(i = 0; i<img->height; i += 1){
+ for(j = 0; j < img->width; j += 1){
+ IplImage *copy = cvCloneImage(img);
+ s=cvGet2D(copy,i,j); // get the (i,j) pixel value
+ printf("%d/%d\n", count++, img->height*img->width);
+ s.val[0]=0;
+ s.val[1]=0;
+ s.val[2]=0;
+ cvSet2D(copy,i,j,s); // set the (i,j) pixel value
+ image mod = features_output_size(net, copy, h, w);
+ image dist = image_distance(out, mod);
+ show_image(affects, "affects");
+ cvWaitKey(1);
+ cvReleaseImage(©);
+ //affects.data[i*affects.w + j] += dist.data[3*dist.w+5];
+ affects.data[i*affects.w + j] += dist.data[1*dist.w+1];
+ free_image(mod);
+ free_image(dist);
+ }
+ }
+ show_image(affects, "Origins");
+ cvWaitKey(0);
+ cvWaitKey(0);
+}
+
+
int main(int argc, char *argv[])
{
+ //train_full();
+ //test_distribution();
//feenableexcept(FE_DIVBYZERO | FE_INVALID | FE_OVERFLOW);
//test_blas();
--
Gitblit v1.10.0