sqrt

src/data.c

@@ -17,7 +17,6 @@ struct load_args{
     int nh;
     int nw;
     int num_boxes;
-    int jitter;
     int classes;
     int background;
     data *d;
@@ -115,6 +114,7 @@ void fill_truth_detection(char *path, float *truth, int classes, int num_boxes,
     box *boxes = read_boxes(labelpath, &count);
     randomize_boxes(boxes, count);
     float x,y,w,h;
+    float left, top, right, bot;
     int id;
     int i;
     if(background){
@@ -123,22 +123,29 @@ void fill_truth_detection(char *path, float *truth, int classes, int num_boxes,
         }
     }
     for(i = 0; i < count; ++i){
-        x = boxes[i].x;
+        left  = boxes[i].left  * sx - dx;
-        y = boxes[i].y;
+        right = boxes[i].right * sx - dx;
-        w = boxes[i].w;
+        top   = boxes[i].top   * sy - dy;
-        h = boxes[i].h;
+        bot   = boxes[i].bottom* sy - dy;
         id = boxes[i].id;
 
         if(flip){
-            x = 1-x;
+            float swap = left;
+            left = 1. - right;
+            right = 1. - swap;
         }
 
-        x = x*sx-dx;
+        left =  constrain(0, 1, left);
-        y = y*sy-dy;
+        right = constrain(0, 1, right);
-        w = w*sx;
+        top =   constrain(0, 1, top);
-        h = h*sy;
+        bot =   constrain(0, 1, bot);
 
-        if (x < 0 || x >= 1 || y < 0 || y >= 1) continue;
+        x = (left+right)/2;
+        y = (top+bot)/2;
+        w = (right - left);
+        h = (bot - top);
+
+       if (x <= 0 || x >= 1 || y <= 0 || y >= 1) continue;
 
         int i = (int)(x*num_boxes);
         int j = (int)(y*num_boxes);
@@ -146,8 +153,18 @@ void fill_truth_detection(char *path, float *truth, int classes, int num_boxes,
         x = x*num_boxes - i;
         y = y*num_boxes - j;
 
+        /*
+        float maxwidth = distance_from_edge(i, num_boxes);
+        float maxheight = distance_from_edge(j, num_boxes);
+        w = w/maxwidth;
+        h = h/maxheight;
+        */
+
         w = constrain(0, 1, w);
         h = constrain(0, 1, h);
+        if (w == 0 || h == 0) continue;
+        w = sqrt(w);
+        h = sqrt(h);
 
         int index = (i+j*num_boxes)*(4+classes+background);
         if(truth[index+classes+background+2]) continue;
@@ -156,8 +173,8 @@ void fill_truth_detection(char *path, float *truth, int classes, int num_boxes,
         index += classes;
         truth[index++] = y;
         truth[index++] = x;
-        truth[index++] = w;
         truth[index++] = h;
+        truth[index++] = w;
     }
     free(boxes);
 }
@@ -274,32 +291,49 @@ void free_data(data d)
     }
 }
 
-data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int h, int w, int num_boxes, int jitter, int background)
+data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int h, int w, int num_boxes, int background)
 {
+    //float minscale = 0.85;
+    //float maxscale = 1.15;
     char **random_paths = get_random_paths(paths, n, m);
     int i;
     data d;
     d.shallow = 0;
-    d.X = load_image_paths(random_paths, n, h, w);
+
+    d.X.rows = n;
+    d.X.vals = calloc(d.X.rows, sizeof(float*));
+    d.X.cols = h*w*3;
+
     int k = num_boxes*num_boxes*(4+classes+background);
     d.y = make_matrix(n, k);
     for(i = 0; i < n; ++i){
-        int px = rand()%jitter;
+        image orig = load_image_color(random_paths[i], 0, 0);
-        px = 0;
+        int oh = orig.h;
-        int py = rand()%jitter;
+        int ow = orig.w;
-        py = 0;
+        int pleft  = (rand_uniform() * 64. - 32.);
-        float sy = (float) h / (h-jitter);
+        int pright = (rand_uniform() * 64. - 32.);
-        float sx = (float) w / (w-jitter);
+        int ptop   = (rand_uniform() * 64. - 32.);
-        float dy = (float) py / (h-jitter);
+        int pbot   = (rand_uniform() * 64. - 32.);
-        float dx = (float) px / (w-jitter);
+
+        int swidth =  ow - pleft - pright;
+        int sheight = oh - ptop - pbot;
+
+        float sx = (float)swidth  / ow;
+        float sy = (float)sheight / oh;
 
         int flip = rand()%2;
-        fill_truth_detection(random_paths[i], d.y.vals[i], classes, num_boxes, flip, background, dx, dy, sx, sy);
+        image cropped = crop_image(orig, ptop, pleft, sheight, swidth);
-        image a = float_to_image(h, w, 3, d.X.vals[i]);
+        float dx = ((float)pleft/ow)/sx;
-        if(flip) flip_image(a);
+        float dy = ((float)ptop /oh)/sy;
-        jitter_image(a, h-jitter, w-jitter, py, px);
+
+        free_image(orig);
+        image sized = resize_image(cropped, h, w);
+        free_image(cropped);
+        if(flip) flip_image(sized);
+        d.X.vals[i] = sized.data;
+
+        fill_truth_detection(random_paths[i], d.y.vals[i], classes, num_boxes, flip, background, dx, dy, 1./sx, 1./sy);
     }
-    d.X.cols = (h-jitter)*(w-jitter)*3;
     free(random_paths);
     return d;
 }
@@ -308,14 +342,14 @@ void *load_detection_thread(void *ptr)
 {
     printf("Loading data: %d\n", rand());
     struct load_args a = *(struct load_args*)ptr;
-    *a.d = load_data_detection_jitter_random(a.n, a.paths, a.m, a.classes, a.h, a.w, a.num_boxes, a.jitter, a.background);
+    *a.d = load_data_detection_jitter_random(a.n, a.paths, a.m, a.classes, a.h, a.w, a.num_boxes, a.background);
     translate_data_rows(*a.d, -128);
     scale_data_rows(*a.d, 1./128);
     free(ptr);
     return 0;
 }
 
-pthread_t load_data_detection_thread(int n, char **paths, int m, int classes, int h, int w, int nh, int nw, int jitter, int background, data *d)
+pthread_t load_data_detection_thread(int n, char **paths, int m, int classes, int h, int w, int nh, int nw, int background, data *d)
 {
     pthread_t thread;
     struct load_args *args = calloc(1, sizeof(struct load_args));
@@ -328,7 +362,6 @@ pthread_t load_data_detection_thread(int n, char **paths, int m, int classes, in
     args->nw = nw;
     args->num_boxes = nw;
     args->classes = classes;
-    args->jitter = jitter;
     args->background = background;
     args->d = d;
     if(pthread_create(&thread, 0, load_detection_thread, args)) {

src/data.h

@@ -5,6 +5,18 @@
 #include "matrix.h"
 #include "list.h"
 
+static inline float distance_from_edge(int x, int max)
+{
+    int dx = (max/2) - x;
+    if (dx < 0) dx = -dx;
+    dx = (max/2) + 1 - dx;
+    dx *= 2;
+    float dist = (float)dx/max;
+    if (dist > 1) dist = 1;
+    return dist;
+}
+
+
 typedef struct{
     matrix X;
     matrix y;
@@ -20,8 +32,8 @@ data load_data_captcha_encode(char **paths, int n, int m, int h, int w);
 data load_data(char **paths, int n, int m, char **labels, int k, int h, int w);
 pthread_t load_data_thread(char **paths, int n, int m, char **labels, int k, int h, int w, data *d);
 
-pthread_t load_data_detection_thread(int n, char **paths, int m, int classes, int h, int w, int nh, int nw, int jitter, int background, data *d);
+pthread_t load_data_detection_thread(int n, char **paths, int m, int classes, int h, int w, int nh, int nw, int background, data *d);
-data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int h, int w, int num_boxes, int jitter, int background);
+data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int h, int w, int num_boxes, int background);
 
 data load_data_image_pathfile(char *filename, char **labels, int k, int h, int w);
 data load_cifar10_data(char *filename);

src/detection.c

@@ -26,11 +26,21 @@ void draw_detection(image im, float *box, int side)
                 float green = get_color(1,class,classes);
                 float blue = get_color(2,class,classes);
 
+                //float maxheight = distance_from_edge(r, side);
+                //float maxwidth  = distance_from_edge(c, side);
                 j += classes;
-                int left = box[j]  *im.w;
+                float y = box[j+0];
-                int right = box[j+1]*im.w;
+                float x = box[j+1];
-                int top = box[j+2]*im.h;
+                x = (x+c)/side;
-                int bot = box[j+3]*im.h;
+                y = (y+r)/side;
+                float h = box[j+2]; //*maxheight;
+                float w = box[j+3]; //*maxwidth;
+                //printf("coords %f %f %f %f\n", x, y, w, h);
+
+                int left  = (x-w/2)*im.w;
+                int right = (x+w/2)*im.w;
+                int top   = (y-h/2)*im.h;
+                int bot   = (y+h/2)*im.h;
                 draw_box(im, left, top, right, bot, red, green, blue);
             }
         }
@@ -59,25 +69,20 @@ void train_detection(char *cfgfile, char *weightfile)
     char **paths = (char **)list_to_array(plist);
     printf("%d\n", plist->size);
     data train, buffer;
-    int im_dim = 512;
+    int im_dim = 448;
-    int jitter = 64;
     int classes = 20;
     int background = 1;
-    pthread_t load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, im_dim, im_dim, 7, 7, jitter, background, &buffer);
+    pthread_t load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, im_dim, im_dim, 7, 7, background, &buffer);
     clock_t time;
     while(1){
         i += 1;
         time=clock();
         pthread_join(load_thread, 0);
         train = buffer;
-        load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, im_dim, im_dim, 7, 7, jitter, background, &buffer);
+        load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, im_dim, im_dim, 7, 7, background, &buffer);
 
-/*
+           //image im = float_to_image(im_dim, im_dim, 3, train.X.vals[114]);
-           image im = float_to_image(im_dim - jitter, im_dim-jitter, 3, train.X.vals[114]);
+           //draw_detection(im, train.y.vals[114], 7);
-           draw_detection(im, train.y.vals[114], 7);
-           show_image(im, "truth");
-           cvWaitKey(0);
-*/
 
         printf("Loaded: %lf seconds\n", sec(clock()-time));
         time=clock();
@@ -147,8 +152,10 @@ void validate_detection(char *cfgfile, char *weightfile)
                     int ci = k+classes+background+nuisance;
                     float y = (pred.vals[j][ci + 0] + row)/num_boxes;
                     float x = (pred.vals[j][ci + 1] + col)/num_boxes;
-                    float h = pred.vals[j][ci + 2];
+                    float h = pred.vals[j][ci + 2]; //* distance_from_edge(row, num_boxes);
-                    float w = pred.vals[j][ci + 3];
+                    h = h*h;
+                    float w = pred.vals[j][ci + 3]; //* distance_from_edge(col, num_boxes);
+                    w = w*w;
                     printf("%d %d %f %f %f %f %f\n", (i-1)*m/splits + j, class, scale*pred.vals[j][k+class+background+nuisance], y, x, h, w);
                 }
             }

src/image.h

@@ -17,6 +17,8 @@ void flip_image(image a);
 void draw_box(image a, int x1, int y1, int x2, int y2, float r, float g, float b);
 image image_distance(image a, image b);
 void scale_image(image m, float s);
+image crop_image(image im, int dr, int dc, int h, int w);
+image resize_image(image im, int h, int w);
 void translate_image(image m, float s);
 void normalize_image(image p);
 void z_normalize_image(image p);