From c62b4f35aa2c59d7db0fd177affeed14b1ba4bcb Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 08 Sep 2016 07:04:39 +0000
Subject: [PATCH] adding coco models
---
src/image.c | 439 +++++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 364 insertions(+), 75 deletions(-)
diff --git a/src/image.c b/src/image.c
index 51871b5..21c2f8b 100644
--- a/src/image.c
+++ b/src/image.c
@@ -1,14 +1,10 @@
#include "image.h"
#include "utils.h"
#include "blas.h"
+#include "cuda.h"
#include <stdio.h>
#include <math.h>
-#ifdef OPENCV
-#include "opencv2/highgui/highgui_c.h"
-#include "opencv2/imgproc/imgproc_c.h"
-#endif
-
#define STB_IMAGE_IMPLEMENTATION
#include "stb_image.h"
#define STB_IMAGE_WRITE_IMPLEMENTATION
@@ -114,13 +110,17 @@
int class = max_index(probs[i], classes);
float prob = probs[i][class];
if(prob > thresh){
- int width = pow(prob, 1./2.)*10+1;
- printf("%s: %.2f\n", names[class], prob);
- int offset = class*17 % classes;
- float red = get_color(0,offset,classes);
+ //int width = pow(prob, 1./2.)*30+1;
+ int width = 8;
+ printf("%s: %.0f%%\n", names[class], prob*100);
+ int offset = class*1 % classes;
+ float red = get_color(2,offset,classes);
float green = get_color(1,offset,classes);
- float blue = get_color(2,offset,classes);
+ float blue = get_color(0,offset,classes);
float rgb[3];
+
+ //width = prob*20+2;
+
rgb[0] = red;
rgb[1] = green;
rgb[2] = blue;
@@ -142,6 +142,42 @@
}
}
+void transpose_image(image im)
+{
+ assert(im.w == im.h);
+ int n, m;
+ int c;
+ for(c = 0; c < im.c; ++c){
+ for(n = 0; n < im.w-1; ++n){
+ for(m = n + 1; m < im.w; ++m){
+ float swap = im.data[m + im.w*(n + im.h*c)];
+ im.data[m + im.w*(n + im.h*c)] = im.data[n + im.w*(m + im.h*c)];
+ im.data[n + im.w*(m + im.h*c)] = swap;
+ }
+ }
+ }
+}
+
+void rotate_image_cw(image im, int times)
+{
+ assert(im.w == im.h);
+ times = (times + 400) % 4;
+ int i, x, y, c;
+ int n = im.w;
+ for(i = 0; i < times; ++i){
+ for(c = 0; c < im.c; ++c){
+ for(x = 0; x < n/2; ++x){
+ for(y = 0; y < (n-1)/2 + 1; ++y){
+ float temp = im.data[y + im.w*(x + im.h*c)];
+ im.data[y + im.w*(x + im.h*c)] = im.data[n-1-x + im.w*(y + im.h*c)];
+ im.data[n-1-x + im.w*(y + im.h*c)] = im.data[n-1-y + im.w*(n-1-x + im.h*c)];
+ im.data[n-1-y + im.w*(n-1-x + im.h*c)] = im.data[x + im.w*(n-1-y + im.h*c)];
+ im.data[x + im.w*(n-1-y + im.h*c)] = temp;
+ }
+ }
+ }
+ }
+}
void flip_image(image a)
{
@@ -213,6 +249,26 @@
void normalize_image(image p)
{
+ int i;
+ float min = 9999999;
+ float max = -999999;
+
+ for(i = 0; i < p.h*p.w*p.c; ++i){
+ float v = p.data[i];
+ if(v < min) min = v;
+ if(v > max) max = v;
+ }
+ if(max - min < .000000001){
+ min = 0;
+ max = 1;
+ }
+ for(i = 0; i < p.c*p.w*p.h; ++i){
+ p.data[i] = (p.data[i] - min)/(max-min);
+ }
+}
+
+void normalize_image2(image p)
+{
float *min = calloc(p.c, sizeof(float));
float *max = calloc(p.c, sizeof(float));
int i,j;
@@ -285,7 +341,6 @@
}
free_image(copy);
if(0){
- //if(disp->height < 448 || disp->width < 448 || disp->height > 1000){
int w = 448;
int h = w*p.h/p.w;
if(h > 1000){
@@ -312,28 +367,22 @@
#endif
}
-void save_image(image im, const char *name)
+#ifdef OPENCV
+image get_image_from_stream(CvCapture *cap)
{
- char buff[256];
- //sprintf(buff, "%s (%d)", name, windows);
- sprintf(buff, "%s.png", name);
- unsigned char *data = calloc(im.w*im.h*im.c, sizeof(char));
- int i,k;
- for(k = 0; k < im.c; ++k){
- for(i = 0; i < im.w*im.h; ++i){
- data[i*im.c+k] = (unsigned char) (255*im.data[i + k*im.w*im.h]);
- }
- }
- int success = stbi_write_png(buff, im.w, im.h, im.c, data, im.w*im.c);
- free(data);
- if(!success) fprintf(stderr, "Failed to write image %s\n", buff);
+ IplImage* src = cvQueryFrame(cap);
+ if (!src) return make_empty_image(0,0,0);
+ image im = ipl_to_image(src);
+ rgbgr_image(im);
+ return im;
}
+#endif
#ifdef OPENCV
-void save_image_jpg(image p, char *name)
+void save_image_jpg(image p, const char *name)
{
image copy = copy_image(p);
- rgbgr_image(copy);
+ if(p.c == 3) rgbgr_image(copy);
int x,y,k;
char buff[256];
@@ -354,6 +403,28 @@
}
#endif
+void save_image(image im, const char *name)
+{
+#ifdef OPENCV
+ save_image_jpg(im, name);
+#else
+ char buff[256];
+ //sprintf(buff, "%s (%d)", name, windows);
+ sprintf(buff, "%s.png", name);
+ unsigned char *data = calloc(im.w*im.h*im.c, sizeof(char));
+ int i,k;
+ for(k = 0; k < im.c; ++k){
+ for(i = 0; i < im.w*im.h; ++i){
+ data[i*im.c+k] = (unsigned char) (255*im.data[i + k*im.w*im.h]);
+ }
+ }
+ int success = stbi_write_png(buff, im.w, im.h, im.c, data, im.w*im.c);
+ free(data);
+ if(!success) fprintf(stderr, "Failed to write image %s\n", buff);
+#endif
+}
+
+
void show_image_layers(image p, char *name)
{
int i;
@@ -390,6 +461,17 @@
return out;
}
+image make_random_image(int w, int h, int c)
+{
+ image out = make_empty_image(w,h,c);
+ out.data = calloc(h*w*c, sizeof(float));
+ int i;
+ for(i = 0; i < w*h*c; ++i){
+ out.data[i] = (rand_normal() * .25) + .5;
+ }
+ return out;
+}
+
image float_to_image(int w, int h, int c, float *data)
{
image out = make_empty_image(w,h,c);
@@ -397,6 +479,26 @@
return out;
}
+
+image rotate_crop_image(image im, float rad, float s, int w, int h, float dx, float dy, float aspect)
+{
+ int x, y, c;
+ float cx = im.w/2.;
+ float cy = im.h/2.;
+ image rot = make_image(w, h, im.c);
+ for(c = 0; c < im.c; ++c){
+ for(y = 0; y < h; ++y){
+ for(x = 0; x < w; ++x){
+ float rx = cos(rad)*((x - w/2.)/s*aspect + dx/s*aspect) - sin(rad)*((y - h/2.)/s + dy/s) + cx;
+ float ry = sin(rad)*((x - w/2.)/s*aspect + dx/s*aspect) + cos(rad)*((y - h/2.)/s + dy/s) + cy;
+ float val = bilinear_interpolate(im, rx, ry, c);
+ set_pixel(rot, x, y, c, val);
+ }
+ }
+ }
+ return rot;
+}
+
image rotate_image(image im, float rad)
{
int x, y, c;
@@ -438,6 +540,8 @@
int r = j + dy;
int c = i + dx;
float val = 0;
+ r = constrain_int(r, 0, im.h-1);
+ c = constrain_int(c, 0, im.w-1);
if (r >= 0 && r < im.h && c >= 0 && c < im.w) {
val = get_pixel(im, c, r, k);
}
@@ -448,6 +552,118 @@
return cropped;
}
+int best_3d_shift_r(image a, image b, int min, int max)
+{
+ if(min == max) return min;
+ int mid = floor((min + max) / 2.);
+ image c1 = crop_image(b, 0, mid, b.w, b.h);
+ image c2 = crop_image(b, 0, mid+1, b.w, b.h);
+ float d1 = dist_array(c1.data, a.data, a.w*a.h*a.c, 10);
+ float d2 = dist_array(c2.data, a.data, a.w*a.h*a.c, 10);
+ free_image(c1);
+ free_image(c2);
+ if(d1 < d2) return best_3d_shift_r(a, b, min, mid);
+ else return best_3d_shift_r(a, b, mid+1, max);
+}
+
+int best_3d_shift(image a, image b, int min, int max)
+{
+ int i;
+ int best = 0;
+ float best_distance = FLT_MAX;
+ for(i = min; i <= max; i += 2){
+ image c = crop_image(b, 0, i, b.w, b.h);
+ float d = dist_array(c.data, a.data, a.w*a.h*a.c, 100);
+ if(d < best_distance){
+ best_distance = d;
+ best = i;
+ }
+ printf("%d %f\n", i, d);
+ free_image(c);
+ }
+ return best;
+}
+
+void composite_3d(char *f1, char *f2, char *out, int delta)
+{
+ if(!out) out = "out";
+ image a = load_image(f1, 0,0,0);
+ image b = load_image(f2, 0,0,0);
+ int shift = best_3d_shift_r(a, b, -a.h/100, a.h/100);
+
+ image c1 = crop_image(b, 10, shift, b.w, b.h);
+ float d1 = dist_array(c1.data, a.data, a.w*a.h*a.c, 100);
+ image c2 = crop_image(b, -10, shift, b.w, b.h);
+ float d2 = dist_array(c2.data, a.data, a.w*a.h*a.c, 100);
+
+ if(d2 < d1 && 0){
+ image swap = a;
+ a = b;
+ b = swap;
+ shift = -shift;
+ printf("swapped, %d\n", shift);
+ }
+ else{
+ printf("%d\n", shift);
+ }
+
+ image c = crop_image(b, delta, shift, a.w, a.h);
+ int i;
+ for(i = 0; i < c.w*c.h; ++i){
+ c.data[i] = a.data[i];
+ }
+#ifdef OPENCV
+ save_image_jpg(c, out);
+#else
+ save_image(c, out);
+#endif
+}
+
+image resize_min(image im, int min)
+{
+ int w = im.w;
+ int h = im.h;
+ if(w < h){
+ h = (h * min) / w;
+ w = min;
+ } else {
+ w = (w * min) / h;
+ h = min;
+ }
+ if(w == im.w && h == im.h) return im;
+ image resized = resize_image(im, w, h);
+ return resized;
+}
+
+image random_crop_image(image im, int w, int h)
+{
+ int dx = rand_int(0, im.w - w);
+ int dy = rand_int(0, im.h - h);
+ image crop = crop_image(im, dx, dy, w, h);
+ return crop;
+}
+
+image random_augment_image(image im, float angle, float aspect, int low, int high, int size)
+{
+ aspect = rand_scale(aspect);
+ int r = rand_int(low, high);
+ int min = (im.h < im.w*aspect) ? im.h : im.w*aspect;
+ float scale = (float)r / min;
+
+ float rad = rand_uniform(-angle, angle) * TWO_PI / 360.;
+
+ float dx = (im.w*scale/aspect - size) / 2.;
+ float dy = (im.h*scale - size) / 2.;
+ if(dx < 0) dx = 0;
+ if(dy < 0) dy = 0;
+ dx = rand_uniform(-dx, dx);
+ dy = rand_uniform(-dy, dy);
+
+ image crop = rotate_crop_image(im, rad, scale, size, size, dx, dy, aspect);
+
+ return crop;
+}
+
float three_way_max(float a, float b, float c)
{
return (a > b) ? ( (a > c) ? a : c) : ( (b > c) ? b : c) ;
@@ -476,7 +692,7 @@
v = max;
if(max == 0){
s = 0;
- h = -1;
+ h = 0;
}else{
s = delta/max;
if(r == max){
@@ -487,6 +703,7 @@
h = 4 + (r - g) / delta;
}
if (h < 0) h += 6;
+ h = h/6.;
}
set_pixel(im, i, j, 0, h);
set_pixel(im, i, j, 1, s);
@@ -504,7 +721,7 @@
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);
+ h = 6 * get_pixel(im, i , j, 0);
s = get_pixel(im, i , j, 1);
v = get_pixel(im, i , j, 2);
if (s == 0) {
@@ -591,6 +808,29 @@
}
}
+void translate_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);
+ }
+ }
+}
+
+image binarize_image(image im)
+{
+ image c = copy_image(im);
+ int i;
+ for(i = 0; i < im.w * im.h * im.c; ++i){
+ if(c.data[i] > .5) c.data[i] = 1;
+ else c.data[i] = 0;
+ }
+ return c;
+}
+
void saturate_image(image im, float sat)
{
rgb_to_hsv(im);
@@ -599,6 +839,19 @@
constrain_image(im);
}
+void hue_image(image im, float hue)
+{
+ rgb_to_hsv(im);
+ int i;
+ for(i = 0; i < im.w*im.h; ++i){
+ im.data[i] = im.data[i] + hue;
+ if (im.data[i] > 1) im.data[i] -= 1;
+ if (im.data[i] < 0) im.data[i] += 1;
+ }
+ hsv_to_rgb(im);
+ constrain_image(im);
+}
+
void exposure_image(image im, float sat)
{
rgb_to_hsv(im);
@@ -607,6 +860,29 @@
constrain_image(im);
}
+void distort_image(image im, float hue, float sat, float val)
+{
+ rgb_to_hsv(im);
+ scale_image_channel(im, 1, sat);
+ scale_image_channel(im, 2, val);
+ int i;
+ for(i = 0; i < im.w*im.h; ++i){
+ im.data[i] = im.data[i] + hue;
+ if (im.data[i] > 1) im.data[i] -= 1;
+ if (im.data[i] < 0) im.data[i] += 1;
+ }
+ hsv_to_rgb(im);
+ constrain_image(im);
+}
+
+void random_distort_image(image im, float hue, float saturation, float exposure)
+{
+ float dhue = rand_uniform(-hue, hue);
+ float dsat = rand_scale(saturation);
+ float dexp = rand_scale(exposure);
+ distort_image(im, dhue, dsat, dexp);
+}
+
void saturate_exposure_image(image im, float sat, float exposure)
{
rgb_to_hsv(im);
@@ -616,23 +892,6 @@
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 bilinear_interpolate(image im, float x, float y, int c)
{
int ix = (int) floorf(x);
@@ -692,37 +951,53 @@
return resized;
}
+
void test_resize(char *filename)
{
image im = load_image(filename, 0,0, 3);
+ float mag = mag_array(im.data, im.w*im.h*im.c);
+ printf("L2 Norm: %f\n", mag);
image gray = grayscale_image(im);
- image sat2 = copy_image(im);
- saturate_image(sat2, 2);
+ image c1 = copy_image(im);
+ image c2 = copy_image(im);
+ image c3 = copy_image(im);
+ image c4 = copy_image(im);
+ distort_image(c1, .1, 1.5, 1.5);
+ distort_image(c2, -.1, .66666, .66666);
+ distort_image(c3, .1, 1.5, .66666);
+ distort_image(c4, .1, .66666, 1.5);
- image sat5 = copy_image(im);
- saturate_image(sat5, .5);
- image exp2 = copy_image(im);
- exposure_image(exp2, 2);
-
- image exp5 = copy_image(im);
- exposure_image(exp5, .5);
-
- image r = resize_image(im, im.w/2, im.h/2);
-
- image black = make_image(im.w, im.h, im.c);
- shortcut_cpu(black.data, im.w, im.h, im.c, 1, 2, r.data, 1, r.c);
-
- show_image(im, "Original");
+ show_image(im, "Original");
show_image(gray, "Gray");
- show_image(black, "Black");
- show_image(sat2, "Saturation-2");
- show_image(sat5, "Saturation-.5");
- show_image(exp2, "Exposure-2");
- show_image(exp5, "Exposure-.5");
+ show_image(c1, "C1");
+ show_image(c2, "C2");
+ show_image(c3, "C3");
+ show_image(c4, "C4");
#ifdef OPENCV
- cvWaitKey(0);
+ while(1){
+ image aug = random_augment_image(im, 0, 320, 448, 320, .75);
+ show_image(aug, "aug");
+ free_image(aug);
+
+
+ float exposure = 1.15;
+ float saturation = 1.15;
+ float hue = .05;
+
+ image c = copy_image(im);
+
+ float dexp = rand_scale(exposure);
+ float dsat = rand_scale(saturation);
+ float dhue = rand_uniform(-hue, hue);
+
+ distort_image(c, dhue, dsat, dexp);
+ show_image(c, "rand");
+ printf("%f %f %f\n", dhue, dsat, dexp);
+ free_image(c);
+ cvWaitKey(0);
+ }
#endif
}
@@ -760,8 +1035,12 @@
if( (src = cvLoadImage(filename, flag)) == 0 )
{
- printf("Cannot load image \"%s\"\n", filename);
- exit(0);
+ fprintf(stderr, "Cannot load image \"%s\"\n", filename);
+ char buff[256];
+ sprintf(buff, "echo %s >> bad.list", filename);
+ system(buff);
+ return make_image(10,10,3);
+ //exit(0);
}
image out = ipl_to_image(src);
cvReleaseImage(&src);
@@ -834,7 +1113,11 @@
}
float get_pixel_extend(image m, int x, int y, int c)
{
- if(x < 0 || x >= m.w || y < 0 || y >= m.h || c < 0 || c >= m.c) return 0;
+ if(x < 0) x = 0;
+ if(x >= m.w) x = m.w-1;
+ if(y < 0) y = 0;
+ if(y >= m.h) y = m.h-1;
+ if(c < 0 || c >= m.c) return 0;
return get_pixel(m, x, y, c);
}
void set_pixel(image m, int x, int y, int c, float val)
@@ -936,6 +1219,14 @@
return filters;
}
+void show_image_normalized(image im, const char *name)
+{
+ image c = copy_image(im);
+ normalize_image(c);
+ show_image(c, name);
+ free_image(c);
+}
+
void show_images(image *ims, int n, char *window)
{
image m = collapse_images_vert(ims, n);
@@ -949,10 +1240,8 @@
image sized = resize_image(m, w, h);
*/
normalize_image(m);
- image sized = resize_image(m, m.w, m.h);
- save_image(sized, window);
- show_image(sized, window);
- free_image(sized);
+ save_image(m, window);
+ show_image(m, window);
free_image(m);
}
--
Gitblit v1.10.0