From 1b5e6d8855064e5d990bd73f1f3a0aa00cbdfb4c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sat, 01 Mar 2014 22:41:30 +0000
Subject: [PATCH] Flipping features now a flag
---
src/tests.c | 329 +++++++++++++++++++++++++++++++++++++++++++++++++++---
1 files changed, 309 insertions(+), 20 deletions(-)
diff --git a/src/tests.c b/src/tests.c
index 00cd1a1..1c7b01d 100644
--- a/src/tests.c
+++ b/src/tests.c
@@ -19,7 +19,7 @@
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);
@@ -35,7 +35,7 @@
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;
@@ -64,7 +64,7 @@
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");
}
@@ -124,13 +124,13 @@
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);
@@ -141,7 +141,7 @@
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);
@@ -184,26 +184,68 @@
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()
+void train_full()
{
- network net = parse_network_cfg("full.cfg");
- srand(0);
+ network net = parse_network_cfg("cfg/imagenet.cfg");
+ srand(2222222);
int i = 0;
char *labels[] = {"cat","dog"};
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);
+ 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]);
+ //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, 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);
- printf("Round %d\n", i);
+ if(i%10000==0){
+ char buff[256];
+ 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()
{
@@ -218,7 +260,7 @@
int count = 0;
float lr = .0005;
float momentum = .9;
- float decay = 0.01;
+ float decay = 0.001;
clock_t start = clock(), end;
while(++count <= 100){
//visualize_network(net);
@@ -227,7 +269,7 @@
end = clock();
printf("Time: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
start=end;
- cvWaitKey(100);
+ //cvWaitKey(100);
//lr /= 2;
if(count%5 == 0){
float train_acc = network_accuracy(net, train);
@@ -235,7 +277,7 @@
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;
+ //lr *= .5;
}
}
}
@@ -345,12 +387,256 @@
int i;
for(i = 0; i < 1000; ++i){
im2col_cpu(test.data, c, h, w, size, stride, matrix);
- image render = float_to_image(mh, mw, mc, matrix);
+ //image render = float_to_image(mh, mw, mc, matrix);
}
}
-int main()
+void train_VOC()
{
+ network net = parse_network_cfg("cfg/voc_start.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/val_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_clean_ramp_%d.cfg", i);
+ save_network(net, buff);
+ }
+ //lr *= .99;
+ }
+}
+
+int voc_size(int x)
+{
+ 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;
+ x = (x-1)*4+11;
+ return x;
+}
+
+image features_output_size(network net, IplImage *src, int outh, int outw)
+{
+ 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, 6);
+ //printf("%d %d\n%d %d\n", outh, out.h, outw, out.w);
+ free_image(im);
+ cvReleaseImage(&sized);
+ return copy_image(out);
+}
+
+void features_VOC(int part, int total)
+{
+ int i,j, count = 0;
+ network net = parse_network_cfg("cfg/voc_imagenet.cfg");
+ char *path_file = "images/VOC2012/all_paths.txt";
+ char *out_dir = "voc_features/";
+ list *paths = get_paths(path_file);
+ node *n = paths->front;
+ int size = paths->size;
+ for(count = 0; count < part*size/total; ++count) n = n->next;
+ while(n && count++ < (part+1)*size/total){
+ char *path = (char *)n->val;
+ char buff[1024];
+ sprintf(buff, "%s%s.txt",out_dir, path);
+ printf("%s\n", 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);
+ }
+ int w = src->width;
+ int h = src->height;
+ int sbin = 8;
+ int interval = 10;
+ double scale = pow(2., 1./interval);
+ int m = (w<h)?w:h;
+ int max_scale = 1+floor((double)log((double)m/(5.*sbin))/log(scale));
+ image *ims = calloc(max_scale+interval, sizeof(image));
+
+ for(i = 0; i < interval; ++i){
+ double factor = 1./pow(scale, i);
+ double ih = round(h*factor);
+ double iw = round(w*factor);
+ int ex_h = round(ih/4.) - 2;
+ int ex_w = round(iw/4.) - 2;
+ ims[i] = features_output_size(net, src, ex_h, ex_w);
+
+ ih = round(h*factor);
+ iw = round(w*factor);
+ ex_h = round(ih/8.) - 2;
+ ex_w = round(iw/8.) - 2;
+ ims[i+interval] = features_output_size(net, src, ex_h, ex_w);
+ for(j = i+interval; j < max_scale; j += interval){
+ factor /= 2.;
+ ih = round(h*factor);
+ iw = round(w*factor);
+ ex_h = round(ih/8.) - 2;
+ ex_w = round(iw/8.) - 2;
+ ims[j+interval] = features_output_size(net, src, ex_h, ex_w);
+ }
+ }
+ for(i = 0; i < max_scale+interval; ++i){
+ image out = ims[i];
+ //printf("%d, %d\n", out.h, out.w);
+ 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");
+ free_image(out);
+ }
+ free(ims);
+ fclose(fp);
+ cvReleaseImage(&src);
+ n = n->next;
+ }
+}
+
+void features_VOC_image(char *image_file, char *image_dir, char *out_dir)
+{
+ int flip = 1;
+ int interval = 4;
+ int i,j;
+ network net = parse_network_cfg("cfg/voc_imagenet.cfg");
+ char image_path[1024];
+ sprintf(image_path, "%s%s",image_dir, image_file);
+ char out_path[1024];
+ if (flip)sprintf(out_path, "%s%d/%s_r.txt",out_dir, interval, image_file);
+ else sprintf(out_path, "%s%d/%s.txt",out_dir, interval, image_file);
+ printf("%s\n", image_file);
+ FILE *fp = fopen(out_path, "w");
+ if(fp == 0) file_error(out_path);
+
+ IplImage* src = 0;
+ if( (src = cvLoadImage(image_path,-1)) == 0 ) file_error(image_path);
+if(flip)cvFlip(src, 0, 1);
+ int w = src->width;
+ int h = src->height;
+ int sbin = 8;
+ double scale = pow(2., 1./interval);
+ int m = (w<h)?w:h;
+ int max_scale = 1+floor((double)log((double)m/(5.*sbin))/log(scale));
+ image *ims = calloc(max_scale+interval, sizeof(image));
+
+ for(i = 0; i < interval; ++i){
+ double factor = 1./pow(scale, i);
+ double ih = round(h*factor);
+ double iw = round(w*factor);
+ int ex_h = round(ih/4.) - 2;
+ int ex_w = round(iw/4.) - 2;
+ ims[i] = features_output_size(net, src, ex_h, ex_w);
+
+ ih = round(h*factor);
+ iw = round(w*factor);
+ ex_h = round(ih/8.) - 2;
+ ex_w = round(iw/8.) - 2;
+ ims[i+interval] = features_output_size(net, src, ex_h, ex_w);
+ for(j = i+interval; j < max_scale; j += interval){
+ factor /= 2.;
+ ih = round(h*factor);
+ iw = round(w*factor);
+ ex_h = round(ih/8.) - 2;
+ ex_w = round(iw/8.) - 2;
+ ims[j+interval] = features_output_size(net, src, ex_h, ex_w);
+ }
+ }
+ for(i = 0; i < max_scale+interval; ++i){
+ image out = ims[i];
+ 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");
+ free_image(out);
+ }
+ free(ims);
+ fclose(fp);
+ 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();
@@ -358,8 +644,11 @@
// test_im2row();
//test_split();
//test_ensemble();
- test_nist();
+ //test_nist();
//test_full();
+ //train_VOC();
+ features_VOC_image(argv[1], argv[2], argv[3]);
+ printf("Success!\n");
//test_random_preprocess();
//test_random_classify();
//test_parser();
--
Gitblit v1.10.0