From 989ab8c38a02fa7ea9c25108151736c62e81c972 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 24 Apr 2015 17:27:50 +0000
Subject: [PATCH] IOU loss function
---
src/image.c | 277 ++++++++++++++++++++++++++++++++++++++++++++++++++-----
1 files changed, 251 insertions(+), 26 deletions(-)
diff --git a/src/image.c b/src/image.c
index 32a51cc..948d325 100644
--- a/src/image.c
+++ b/src/image.c
@@ -1,6 +1,7 @@
#include "image.h"
#include "utils.h"
#include <stdio.h>
+#include <math.h>
int windows = 0;
@@ -19,7 +20,7 @@
void draw_box(image a, int x1, int y1, int x2, int y2, float r, float g, float b)
{
- normalize_image(a);
+ //normalize_image(a);
int i;
if(x1 < 0) x1 = 0;
if(x1 >= a.w) x1 = a.w-1;
@@ -112,6 +113,15 @@
return dest;
}
+void constrain_image(image im)
+{
+ int i;
+ for(i = 0; i < im.w*im.h*im.c; ++i){
+ if(im.data[i] < 0) im.data[i] = 0;
+ if(im.data[i] > 1) im.data[i] = 1;
+ }
+}
+
void normalize_image(image p)
{
float *min = calloc(p.c, sizeof(float));
@@ -149,12 +159,11 @@
return copy;
}
-
void show_image(image p, char *name)
{
int x,y,k;
image copy = copy_image(p);
- normalize_image(copy);
+ //normalize_image(copy);
char buff[256];
//sprintf(buff, "%s (%d)", name, windows);
@@ -173,8 +182,8 @@
}
}
free_image(copy);
- if(disp->height < 500 || disp->width < 500 || disp->height > 1000){
- int w = 500;
+ if(disp->height < 448 || disp->width < 448 || disp->height > 1000){
+ int w = 448;
int h = w*p.h/p.w;
if(h > 1000){
h = 1000;
@@ -182,7 +191,7 @@
}
IplImage *buffer = disp;
disp = cvCreateImage(cvSize(w, h), buffer->depth, buffer->nChannels);
- cvResize(buffer, disp, CV_INTER_NN);
+ cvResize(buffer, disp, CV_INTER_LINEAR);
cvReleaseImage(&buffer);
}
cvShowImage(buff, disp);
@@ -193,7 +202,7 @@
{
int x,y,k;
image copy = copy_image(p);
- normalize_image(copy);
+ //normalize_image(copy);
char buff[256];
//sprintf(buff, "%s (%d)", name, windows);
@@ -256,16 +265,23 @@
return out;
}
-void rotate_image(image m)
+image rotate_image(image im, float rad)
{
- int i,j;
- for(j = 0; j < m.c; ++j){
- for(i = 0; i < m.h*m.w/2; ++i){
- float swap = m.data[j*m.h*m.w + i];
- m.data[j*m.h*m.w + i] = m.data[j*m.h*m.w + (m.h*m.w-1 - i)];
- m.data[j*m.h*m.w + (m.h*m.w-1 - i)] = swap;
+ int x, y, c;
+ float cx = im.w/2.;
+ float cy = im.h/2.;
+ image rot = make_image(im.w, im.h, im.c);
+ for(c = 0; c < im.c; ++c){
+ for(y = 0; y < im.h; ++y){
+ for(x = 0; x < im.w; ++x){
+ float rx = cos(rad)*(x-cx) - sin(rad)*(y-cy) + cx;
+ float ry = sin(rad)*(x-cx) + cos(rad)*(y-cy) + cy;
+ float val = billinear_interpolate(im, rx, ry, c);
+ set_pixel(rot, x, y, c, val);
+ }
}
}
+ return rot;
}
void translate_image(image m, float s)
@@ -293,7 +309,7 @@
for(k= 0; k < c; ++k){
for(i = 0; i < h; ++i){
for(j = 0; j < w; ++j){
- out.data[count++] = data[i*step + j*c + k];
+ out.data[count++] = data[i*step + j*c + k]/255.;
}
}
}
@@ -309,7 +325,7 @@
for(i = 0; i < w; ++i){
int r = j + dy;
int c = i + dx;
- float val = 128;
+ float val = 0;
if (r >= 0 && r < im.h && c >= 0 && c < im.w) {
val = get_pixel(im, c, r, k);
}
@@ -320,18 +336,195 @@
return cropped;
}
+float three_way_max(float a, float b, float c)
+{
+ return (a > b) ? ( (a > c) ? a : c) : ( (b > c) ? b : c) ;
+}
+
+float three_way_min(float a, float b, float c)
+{
+ return (a < b) ? ( (a < c) ? a : c) : ( (b < c) ? b : c) ;
+}
+
+// http://www.cs.rit.edu/~ncs/color/t_convert.html
+void rgb_to_hsv(image im)
+{
+ assert(im.c == 3);
+ int i, j;
+ float r, g, b;
+ float h, s, v;
+ for(j = 0; j < im.h; ++j){
+ for(i = 0; i < im.w; ++i){
+ r = get_pixel(im, i , j, 2);
+ g = get_pixel(im, i , j, 1);
+ b = get_pixel(im, i , j, 0);
+ float max = three_way_max(r,g,b);
+ float min = three_way_min(r,g,b);
+ float delta = max - min;
+ v = max;
+ if(max == 0){
+ s = 0;
+ h = -1;
+ }else{
+ s = delta/max;
+ if(r == max){
+ h = (g - b) / delta;
+ } else if (g == max) {
+ h = 2 + (b - r) / delta;
+ } else {
+ h = 4 + (r - g) / delta;
+ }
+ if (h < 0) h += 6;
+ }
+ set_pixel(im, i, j, 0, h);
+ set_pixel(im, i, j, 1, s);
+ set_pixel(im, i, j, 2, v);
+ }
+ }
+}
+
+void hsv_to_rgb(image im)
+{
+ assert(im.c == 3);
+ int i, j;
+ float r, g, b;
+ float h, s, v;
+ float f, p, q, t;
+ for(j = 0; j < im.h; ++j){
+ for(i = 0; i < im.w; ++i){
+ h = get_pixel(im, i , j, 0);
+ s = get_pixel(im, i , j, 1);
+ v = get_pixel(im, i , j, 2);
+ if (s == 0) {
+ r = g = b = v;
+ } else {
+ int index = floor(h);
+ f = h - index;
+ p = v*(1-s);
+ q = v*(1-s*f);
+ t = v*(1-s*(1-f));
+ if(index == 0){
+ r = v; g = t; b = p;
+ } else if(index == 1){
+ r = q; g = v; b = p;
+ } else if(index == 2){
+ r = p; g = v; b = t;
+ } else if(index == 3){
+ r = p; g = q; b = v;
+ } else if(index == 4){
+ r = t; g = p; b = v;
+ } else {
+ r = v; g = p; b = q;
+ }
+ }
+ set_pixel(im, i, j, 2, r);
+ set_pixel(im, i, j, 1, g);
+ set_pixel(im, i, j, 0, b);
+ }
+ }
+}
+
+image grayscale_image(image im)
+{
+ assert(im.c == 3);
+ int i, j, k;
+ image gray = make_image(im.w, im.h, im.c);
+ float scale[] = {0.114, 0.587, 0.299};
+ for(k = 0; k < im.c; ++k){
+ for(j = 0; j < im.h; ++j){
+ for(i = 0; i < im.w; ++i){
+ gray.data[i+im.w*j] += scale[k]*get_pixel(im, i, j, k);
+ }
+ }
+ }
+ memcpy(gray.data + im.w*im.h*1, gray.data, sizeof(float)*im.w*im.h);
+ memcpy(gray.data + im.w*im.h*2, gray.data, sizeof(float)*im.w*im.h);
+ return gray;
+}
+
+image blend_image(image fore, image back, float alpha)
+{
+ assert(fore.w == back.w && fore.h == back.h && fore.c == back.c);
+ image blend = make_image(fore.w, fore.h, fore.c);
+ int i, j, k;
+ for(k = 0; k < fore.c; ++k){
+ for(j = 0; j < fore.h; ++j){
+ for(i = 0; i < fore.w; ++i){
+ float val = alpha * get_pixel(fore, i, j, k) +
+ (1 - alpha)* get_pixel(back, i, j, k);
+ set_pixel(blend, i, j, k, val);
+ }
+ }
+ }
+ return blend;
+}
+
+void scale_image_channel(image im, int c, float v)
+{
+ int i, j;
+ for(j = 0; j < im.h; ++j){
+ for(i = 0; i < im.w; ++i){
+ float pix = get_pixel(im, i, j, c);
+ pix = pix*v;
+ set_pixel(im, i, j, c, pix);
+ }
+ }
+}
+
+void saturate_image(image im, float sat)
+{
+ rgb_to_hsv(im);
+ scale_image_channel(im, 1, sat);
+ hsv_to_rgb(im);
+ constrain_image(im);
+}
+
+void exposure_image(image im, float sat)
+{
+ rgb_to_hsv(im);
+ scale_image_channel(im, 2, sat);
+ hsv_to_rgb(im);
+ constrain_image(im);
+}
+
+void saturate_exposure_image(image im, float sat, float exposure)
+{
+ rgb_to_hsv(im);
+ scale_image_channel(im, 1, sat);
+ scale_image_channel(im, 2, exposure);
+ hsv_to_rgb(im);
+ constrain_image(im);
+}
+
+/*
+image saturate_image(image im, float sat)
+{
+ image gray = grayscale_image(im);
+ image blend = blend_image(im, gray, sat);
+ free_image(gray);
+ constrain_image(blend);
+ return blend;
+}
+
+image brightness_image(image im, float b)
+{
+ image bright = make_image(im.w, im.h, im.c);
+ return bright;
+}
+*/
+
float billinear_interpolate(image im, float x, float y, int c)
{
- int ix = (int) x;
- int iy = (int) y;
+ int ix = (int) floorf(x);
+ int iy = (int) floorf(y);
float dx = x - ix;
float dy = y - iy;
float val = (1-dy) * (1-dx) * get_pixel_extend(im, ix, iy, c) +
- dy * (1-dx) * get_pixel_extend(im, ix, iy+1, c) +
- (1-dy) * dx * get_pixel_extend(im, ix+1, iy, c) +
- dy * dx * get_pixel_extend(im, ix+1, iy+1, c);
+ dy * (1-dx) * get_pixel_extend(im, ix, iy+1, c) +
+ (1-dy) * dx * get_pixel_extend(im, ix+1, iy, c) +
+ dy * dx * get_pixel_extend(im, ix+1, iy+1, c);
return val;
}
@@ -362,11 +555,42 @@
image big = resize_image(im, 513, 512);
image crop = crop_image(im, 50, 10, 100, 100);
image crop2 = crop_image(im, -30, -50, 291, 400);
+ image rot = rotate_image(big, .02);
+ image rot2 = rotate_image(big, 3.14159265/2.);
+ image test = rotate_image(im, .6);
+ image gray = grayscale_image(im);
+
+ image sat2 = copy_image(im);
+ saturate_image(sat2, 2);
+ exposure_image(sat2, 2);
+
+ image sat5 = copy_image(im);
+ saturate_image(sat5, 2);
+ exposure_image(sat5, .5);
+
+ image exp2 = copy_image(im);
+ saturate_image(exp2, .5);
+ exposure_image(exp2, 2);
+
+ image exp5 = copy_image(im);
+ saturate_image(exp5, .5);
+ exposure_image(exp5, .5);
+
show_image(im, "original");
- show_image(small, "smaller");
- show_image(big, "bigger");
- show_image(crop, "crop");
- show_image(crop2, "crop2");
+ show_image(gray, "gray");
+ show_image(sat2, "sat2");
+ show_image(sat5, "sat5");
+ show_image(exp2, "exp2");
+ show_image(exp5, "exp5");
+ /*
+ show_image(small, "smaller");
+ show_image(big, "bigger");
+ show_image(crop, "crop");
+ show_image(crop2, "crop2");
+ show_image(rot, "rot");
+ show_image(rot2, "rot2");
+ show_image(test, "test");
+ */
cvWaitKey(0);
}
@@ -379,12 +603,13 @@
exit(0);
}
image out = ipl_to_image(src);
+ cvReleaseImage(&src);
if((h && w) && (h != out.h || w != out.w)){
+ //printf("resize\n");
image resized = resize_image(out, w, h);
free_image(out);
out = resized;
}
- cvReleaseImage(&src);
return out;
}
--
Gitblit v1.10.0