github
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Imagenet Features\!

Browse Source
pull/5299/head
Joseph Redmon 11 years ago
parent 2c6d4ba1d5
commit bc902b277e
6 changed files with 141 additions and 48 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 1
      src/data.c
  2. 23
      src/image.c
  3. 1
      src/image.h
  4. 55
      src/network.c
  5. 4
      src/softmax_layer.c
  6. 105
      src/tests.c

1
src/data.c
Unescape View File

@ -10,6 +10,7 @@ list *get_paths(char *filename)
{ {
char *path; char *path;
FILE *file = fopen(filename, "r"); FILE *file = fopen(filename, "r");
if(!file) file_error(filename);
list *lines = make_list(); list *lines = make_list();
while((path=fgetl(file))){ while((path=fgetl(file))){
list_insert(lines, path); list_insert(lines, path);

23
src/image.c
Unescape View File

@ -4,6 +4,21 @@
int windows = 0; 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) void subtract_image(image a, image b)
{ {
int i; int i;
@ -370,9 +385,11 @@ image load_image(char *filename, int h, int w)
printf("Cannot load file image %s\n", filename); printf("Cannot load file image %s\n", filename);
exit(0); exit(0);
} }
IplImage *resized = resizeImage(src, h, w, 1); if(h && w ){
cvReleaseImage(&src); IplImage *resized = resizeImage(src, h, w, 1);
src = resized; cvReleaseImage(&src);
src = resized;
}
image out = ipl_to_image(src); image out = ipl_to_image(src);
cvReleaseImage(&src); cvReleaseImage(&src);
return out; return out;

1
src/image.h
Unescape View File

@ -10,6 +10,7 @@ typedef struct {
float *data; float *data;
} image; } image;
image image_distance(image a, image b);
void scale_image(image m, float s); void scale_image(image m, float s);
void add_scalar_image(image m, float s); void add_scalar_image(image m, float s);
void normalize_image(image p); void normalize_image(image p);

55
src/network.c
Unescape View File

@ -21,18 +21,18 @@ network make_network(int n)
return net; return net;
} }
void print_convolutional_cfg(FILE *fp, convolutional_layer *l) void print_convolutional_cfg(FILE *fp, convolutional_layer *l, int first)
{ {
int i; int i;
fprintf(fp, "[convolutional]\n" fprintf(fp, "[convolutional]\n");
"height=%d\n" if(first) fprintf(fp, "height=%d\n"
"width=%d\n" "width=%d\n"
"channels=%d\n" "channels=%d\n",
"filters=%d\n" l->h, l->w, l->c);
fprintf(fp, "filters=%d\n"
"size=%d\n" "size=%d\n"
"stride=%d\n" "stride=%d\n"
"activation=%s\n", "activation=%s\n",
l->h, l->w, l->c,
l->n, l->size, l->stride, l->n, l->size, l->stride,
get_activation_string(l->activation)); get_activation_string(l->activation));
fprintf(fp, "data="); fprintf(fp, "data=");
@ -40,14 +40,14 @@ void print_convolutional_cfg(FILE *fp, convolutional_layer *l)
for(i = 0; i < l->n*l->c*l->size*l->size; ++i) fprintf(fp, "%g,", l->filters[i]); for(i = 0; i < l->n*l->c*l->size*l->size; ++i) fprintf(fp, "%g,", l->filters[i]);
fprintf(fp, "\n\n"); 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; int i;
fprintf(fp, "[connected]\n" fprintf(fp, "[connected]\n");
"input=%d\n" if(first) fprintf(fp, "input=%d\n", l->inputs);
"output=%d\n" fprintf(fp, "output=%d\n"
"activation=%s\n", "activation=%s\n",
l->inputs, l->outputs, l->outputs,
get_activation_string(l->activation)); get_activation_string(l->activation));
fprintf(fp, "data="); fprintf(fp, "data=");
for(i = 0; i < l->outputs; ++i) fprintf(fp, "%g,", l->biases[i]); for(i = 0; i < l->outputs; ++i) fprintf(fp, "%g,", l->biases[i]);
@ -55,22 +55,21 @@ void print_connected_cfg(FILE *fp, connected_layer *l)
fprintf(fp, "\n\n"); 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" fprintf(fp, "[maxpool]\n");
"height=%d\n" if(first) fprintf(fp, "height=%d\n"
"width=%d\n" "width=%d\n"
"channels=%d\n" "channels=%d\n",
"stride=%d\n\n", l->h, l->w, l->c);
l->h, l->w, l->c, fprintf(fp, "stride=%d\n\n", l->stride);
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" fprintf(fp, "[softmax]\n");
"input=%d\n\n", if(first) fprintf(fp, "input=%d\n", l->inputs);
l->inputs); fprintf(fp, "\n");
} }
void save_network(network net, char *filename) void save_network(network net, char *filename)
@ -81,13 +80,13 @@ void save_network(network net, char *filename)
for(i = 0; i < net.n; ++i) for(i = 0; i < net.n; ++i)
{ {
if(net.types[i] == CONVOLUTIONAL) 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) 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) 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) 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); fclose(fp);
} }

4
src/softmax_layer.c
Unescape View File

@ -36,9 +36,9 @@ void forward_softmax_layer(const softmax_layer layer, float *input)
} }
for(i = 0; i < layer.inputs; ++i){ for(i = 0; i < layer.inputs; ++i){
sum += exp(input[i]-largest); sum += exp(input[i]-largest);
printf("%f, ", input[i]); //printf("%f, ", input[i]);
} }
printf("\n"); //printf("\n");
if(sum) sum = largest+log(sum); if(sum) sum = largest+log(sum);
else sum = largest-100; else sum = largest-100;
for(i = 0; i < layer.inputs; ++i){ for(i = 0; i < layer.inputs; ++i){

105
src/tests.c
Unescape View File

@ -188,37 +188,64 @@ void test_data()
free_data(train); 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); srand(2222222);
int i = 800; int i = 0;
char *labels[] = {"cat","dog"}; char *labels[] = {"cat","dog"};
float lr = .00001; float lr = .00001;
float momentum = .9; float momentum = .9;
float decay = 0.01; float decay = 0.01;
while(i++ < 1000 || 1){ while(1){
visualize_network(net); i += 1000;
cvWaitKey(100); data train = load_data_image_pathfile_random("images/assira/train.list", 1000, labels, 2, 256, 256);
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]); image im = float_to_image(256, 256, 3,train.X.vals[0]);
show_image(im, "input"); //visualize_network(net);
cvWaitKey(100); //cvWaitKey(100);
//show_image(im, "input");
//cvWaitKey(100);
//scale_data_rows(train, 1./255.); //scale_data_rows(train, 1./255.);
normalize_data_rows(train); normalize_data_rows(train);
clock_t start = clock(), end; 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(); 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); 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); free_data(train);
if(i%100==0){ if(i%10000==0){
char buff[256]; char buff[256];
sprintf(buff, "backup_%d.cfg", i); sprintf(buff, "cfg/assira_backup_%d.cfg", i);
//save_network(net, buff); save_network(net, buff);
} }
//lr *= .99; //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() void test_nist()
{ {
@ -398,6 +425,7 @@ void train_VOC()
int voc_size(int x) int voc_size(int x)
{ {
x = x-1+3;
x = x-1+3; x = x-1+3;
x = x-1+3; x = x-1+3;
x = (x-1)*2+1; x = (x-1)*2+1;
@ -411,13 +439,14 @@ image features_output_size(network net, IplImage *src, int outh, int outw)
{ {
int h = voc_size(outh); int h = voc_size(outh);
int w = voc_size(outw); int w = voc_size(outw);
printf("%d %d\n", h, w);
IplImage *sized = cvCreateImage(cvSize(w,h), src->depth, src->nChannels); IplImage *sized = cvCreateImage(cvSize(w,h), src->depth, src->nChannels);
cvResize(src, sized, CV_INTER_LINEAR); cvResize(src, sized, CV_INTER_LINEAR);
image im = ipl_to_image(sized); image im = ipl_to_image(sized);
reset_network_size(net, im.h, im.w, im.c); reset_network_size(net, im.h, im.w, im.c);
forward_network(net, im.data); 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); //printf("%d %d\n%d %d\n", outh, out.h, outw, out.w);
free_image(im); free_image(im);
cvReleaseImage(&sized); cvReleaseImage(&sized);
@ -500,7 +529,7 @@ void features_VOC(int part, int total)
void features_VOC_image(char *image_file, char *image_dir, char *out_dir) void features_VOC_image(char *image_file, char *image_dir, char *out_dir)
{ {
int i,j; int i,j;
network net = parse_network_cfg("cfg/voc_features.cfg"); network net = parse_network_cfg("cfg/imagenet.cfg");
char image_path[1024]; char image_path[1024];
sprintf(image_path, "%s%s",image_dir, image_file); sprintf(image_path, "%s%s",image_dir, image_file);
char out_path[1024]; char out_path[1024];
@ -557,8 +586,54 @@ void features_VOC_image(char *image_file, char *image_dir, char *out_dir)
cvReleaseImage(&src); 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(&copy);
//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[]) int main(int argc, char *argv[])
{ {
//train_full();
//test_distribution();
//feenableexcept(FE_DIVBYZERO | FE_INVALID | FE_OVERFLOW); //feenableexcept(FE_DIVBYZERO | FE_INVALID | FE_OVERFLOW);
//test_blas(); //test_blas();

Write Preview
Loading…
Cancel
Save