From 913d355ec1cf34aad71fdd75202fc3b0309e63a0 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 28 Jan 2016 20:30:38 +0000
Subject: [PATCH] lots of stuff
---
src/image.c | 255 +++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 207 insertions(+), 48 deletions(-)
diff --git a/src/image.c b/src/image.c
index 046de0c..60ccfb8 100644
--- a/src/image.c
+++ b/src/image.c
@@ -1,8 +1,14 @@
#include "image.h"
#include "utils.h"
+#include "blas.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
@@ -23,6 +29,26 @@
return r;
}
+void draw_label(image a, int r, int c, image label, const float *rgb)
+{
+ float ratio = (float) label.w / label.h;
+ int h = label.h;
+ int w = ratio * h;
+ image rl = resize_image(label, w, h);
+ if (r - h >= 0) r = r - h;
+
+ int i, j, k;
+ for(j = 0; j < h && j + r < a.h; ++j){
+ for(i = 0; i < w && i + c < a.w; ++i){
+ for(k = 0; k < label.c; ++k){
+ float val = get_pixel(rl, i, j, k);
+ set_pixel(a, i+c, j+r, k, rgb[k] * val);
+ }
+ }
+ }
+ free_image(rl);
+}
+
void draw_box(image a, int x1, int y1, int x2, int y2, float r, float g, float b)
{
//normalize_image(a);
@@ -37,25 +63,25 @@
if(y2 < 0) y2 = 0;
if(y2 >= a.h) y2 = a.h-1;
- for(i = x1; i < x2; ++i){
- a.data[i + y1*a.w + 0*a.w*a.h] = b;
- a.data[i + y2*a.w + 0*a.w*a.h] = b;
+ for(i = x1; i <= x2; ++i){
+ a.data[i + y1*a.w + 0*a.w*a.h] = r;
+ a.data[i + y2*a.w + 0*a.w*a.h] = r;
a.data[i + y1*a.w + 1*a.w*a.h] = g;
a.data[i + y2*a.w + 1*a.w*a.h] = g;
- a.data[i + y1*a.w + 2*a.w*a.h] = r;
- a.data[i + y2*a.w + 2*a.w*a.h] = r;
+ a.data[i + y1*a.w + 2*a.w*a.h] = b;
+ a.data[i + y2*a.w + 2*a.w*a.h] = b;
}
- for(i = y1; i < y2; ++i){
- a.data[x1 + i*a.w + 0*a.w*a.h] = b;
- a.data[x2 + i*a.w + 0*a.w*a.h] = b;
+ for(i = y1; i <= y2; ++i){
+ a.data[x1 + i*a.w + 0*a.w*a.h] = r;
+ a.data[x2 + i*a.w + 0*a.w*a.h] = r;
a.data[x1 + i*a.w + 1*a.w*a.h] = g;
a.data[x2 + i*a.w + 1*a.w*a.h] = g;
- a.data[x1 + i*a.w + 2*a.w*a.h] = r;
- a.data[x2 + i*a.w + 2*a.w*a.h] = r;
+ a.data[x1 + i*a.w + 2*a.w*a.h] = b;
+ a.data[x2 + i*a.w + 2*a.w*a.h] = b;
}
}
@@ -67,6 +93,56 @@
}
}
+void draw_bbox(image a, box bbox, int w, float r, float g, float b)
+{
+ int left = (bbox.x-bbox.w/2)*a.w;
+ int right = (bbox.x+bbox.w/2)*a.w;
+ int top = (bbox.y-bbox.h/2)*a.h;
+ int bot = (bbox.y+bbox.h/2)*a.h;
+
+ int i;
+ for(i = 0; i < w; ++i){
+ draw_box(a, left+i, top+i, right-i, bot-i, r, g, b);
+ }
+}
+
+void draw_detections(image im, int num, float thresh, box *boxes, float **probs, char **names, image *labels, int classes)
+{
+ int i;
+
+ for(i = 0; i < num; ++i){
+ 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);
+ float green = get_color(1,offset,classes);
+ float blue = get_color(2,offset,classes);
+ float rgb[3];
+ rgb[0] = red;
+ rgb[1] = green;
+ rgb[2] = blue;
+ box b = boxes[i];
+
+ int left = (b.x-b.w/2.)*im.w;
+ int right = (b.x+b.w/2.)*im.w;
+ int top = (b.y-b.h/2.)*im.h;
+ int bot = (b.y+b.h/2.)*im.h;
+
+ if(left < 0) left = 0;
+ if(right > im.w-1) right = im.w-1;
+ if(top < 0) top = 0;
+ if(bot > im.h-1) bot = im.h-1;
+
+ draw_box_width(im, left, top, right, bot, width, red, green, blue);
+ if (labels) draw_label(im, top + width, left, labels[class], rgb);
+ }
+ }
+}
+
+
void flip_image(image a)
{
int i,j,k;
@@ -183,12 +259,12 @@
}
#ifdef OPENCV
-void show_image_cv(image p, char *name)
+void show_image_cv(image p, const char *name)
{
int x,y,k;
image copy = copy_image(p);
constrain_image(copy);
- rgbgr_image(copy);
+ if(p.c == 3) rgbgr_image(copy);
//normalize_image(copy);
char buff[256];
@@ -197,7 +273,7 @@
IplImage *disp = cvCreateImage(cvSize(p.w,p.h), IPL_DEPTH_8U, p.c);
int step = disp->widthStep;
- cvNamedWindow(buff, CV_WINDOW_AUTOSIZE);
+ cvNamedWindow(buff, CV_WINDOW_NORMAL);
//cvMoveWindow(buff, 100*(windows%10) + 200*(windows/10), 100*(windows%10));
++windows;
for(y = 0; y < p.h; ++y){
@@ -209,7 +285,7 @@
}
free_image(copy);
if(0){
- //if(disp->height < 448 || disp->width < 448 || disp->height > 1000){
+ //if(disp->height < 448 || disp->width < 448 || disp->height > 1000){
int w = 448;
int h = w*p.h/p.w;
if(h > 1000){
@@ -226,17 +302,17 @@
}
#endif
-void show_image(image p, char *name)
+void show_image(image p, const char *name)
{
- #ifdef OPENCV
+#ifdef OPENCV
show_image_cv(p, name);
- #else
+#else
fprintf(stderr, "Not compiled with OpenCV, saving to %s.png instead\n", name);
save_image(p, name);
- #endif
+#endif
}
-void save_image(image im, char *name)
+void save_image(image im, const char *name)
{
char buff[256];
//sprintf(buff, "%s (%d)", name, windows);
@@ -249,19 +325,19 @@
}
}
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);
}
-/*
-void save_image_cv(image p, char *name)
+#ifdef OPENCV
+void save_image_jpg(image p, char *name)
{
- int x,y,k;
image copy = copy_image(p);
- //normalize_image(copy);
+ rgbgr_image(copy);
+ int x,y,k;
char buff[256];
- //sprintf(buff, "%s (%d)", name, windows);
- sprintf(buff, "%s.png", name);
+ sprintf(buff, "%s.jpg", name);
IplImage *disp = cvCreateImage(cvSize(p.w,p.h), IPL_DEPTH_8U, p.c);
int step = disp->widthStep;
@@ -272,11 +348,11 @@
}
}
}
- free_image(copy);
cvSaveImage(buff, disp,0);
cvReleaseImage(&disp);
+ free_image(copy);
}
-*/
+#endif
void show_image_layers(image p, char *name)
{
@@ -314,6 +390,17 @@
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);
@@ -332,7 +419,7 @@
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);
+ float val = bilinear_interpolate(im, rx, ry, c);
set_pixel(rot, x, y, c, val);
}
}
@@ -464,7 +551,7 @@
{
assert(im.c == 3);
int i, j, k;
- image gray = make_image(im.w, im.h, im.c);
+ image gray = make_image(im.w, im.h, 1);
float scale[] = {0.587, 0.299, 0.114};
for(k = 0; k < im.c; ++k){
for(j = 0; j < im.h; ++j){
@@ -473,11 +560,19 @@
}
}
}
- 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 threshold_image(image im, float thresh)
+{
+ int i;
+ image t = make_image(im.w, im.h, im.c);
+ for(i = 0; i < im.w*im.h*im.c; ++i){
+ t.data[i] = im.data[i]>thresh ? 1 : 0;
+ }
+ return t;
+}
+
image blend_image(image fore, image back, float alpha)
{
assert(fore.w == back.w && fore.h == back.h && fore.c == back.c);
@@ -549,7 +644,7 @@
}
*/
-float billinear_interpolate(image im, float x, float y, int c)
+float bilinear_interpolate(image im, float x, float y, int c)
{
int ix = (int) floorf(x);
int iy = (int) floorf(y);
@@ -564,29 +659,57 @@
return val;
}
-// #wikipedia
image resize_image(image im, int w, int h)
{
image resized = make_image(w, h, im.c);
+ image part = make_image(w, im.h, im.c);
int r, c, k;
float w_scale = (float)(im.w - 1) / (w - 1);
float h_scale = (float)(im.h - 1) / (h - 1);
for(k = 0; k < im.c; ++k){
- for(r = 0; r < h; ++r){
+ for(r = 0; r < im.h; ++r){
for(c = 0; c < w; ++c){
- float sx = c*w_scale;
- float sy = r*h_scale;
- float val = billinear_interpolate(im, sx, sy, k);
- set_pixel(resized, c, r, k, val);
+ float val = 0;
+ if(c == w-1 || im.w == 1){
+ val = get_pixel(im, im.w-1, r, k);
+ } else {
+ float sx = c*w_scale;
+ int ix = (int) sx;
+ float dx = sx - ix;
+ val = (1 - dx) * get_pixel(im, ix, r, k) + dx * get_pixel(im, ix+1, r, k);
+ }
+ set_pixel(part, c, r, k, val);
}
}
}
+ for(k = 0; k < im.c; ++k){
+ for(r = 0; r < h; ++r){
+ float sy = r*h_scale;
+ int iy = (int) sy;
+ float dy = sy - iy;
+ for(c = 0; c < w; ++c){
+ float val = (1-dy) * get_pixel(part, c, iy, k);
+ set_pixel(resized, c, r, k, val);
+ }
+ if(r == h-1 || im.h == 1) continue;
+ for(c = 0; c < w; ++c){
+ float val = dy * get_pixel(part, c, iy+1, k);
+ add_pixel(resized, c, r, k, val);
+ }
+ }
+ }
+
+ free_image(part);
return resized;
}
+#include "cuda.h"
+
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);
@@ -601,15 +724,34 @@
image exp5 = copy_image(im);
exposure_image(exp5, .5);
+ #ifdef GPU
+ image r = resize_image(im, im.w, im.h);
+ image black = make_image(im.w*2 + 3, im.h*2 + 3, 9);
+ image black2 = make_image(im.w, im.h, 3);
+
+ float *r_gpu = cuda_make_array(r.data, r.w*r.h*r.c);
+ float *black_gpu = cuda_make_array(black.data, black.w*black.h*black.c);
+ float *black2_gpu = cuda_make_array(black2.data, black2.w*black2.h*black2.c);
+ shortcut_gpu(3, r.w, r.h, 1, r_gpu, black.w, black.h, 3, black_gpu);
+ //flip_image(r);
+ //shortcut_gpu(3, r.w, r.h, 1, r.data, black.w, black.h, 3, black.data);
+
+ shortcut_gpu(3, black.w, black.h, 3, black_gpu, black2.w, black2.h, 1, black2_gpu);
+ cuda_pull_array(black_gpu, black.data, black.w*black.h*black.c);
+ cuda_pull_array(black2_gpu, black2.data, black2.w*black2.h*black2.c);
+ show_image_layers(black, "Black");
+ show_image(black2, "Recreate");
+ #endif
+
show_image(im, "Original");
show_image(gray, "Gray");
show_image(sat2, "Saturation-2");
show_image(sat5, "Saturation-.5");
show_image(exp2, "Exposure-2");
show_image(exp5, "Exposure-.5");
- #ifdef OPENCV
+#ifdef OPENCV
cvWaitKey(0);
- #endif
+#endif
}
#ifdef OPENCV
@@ -643,10 +785,10 @@
else {
fprintf(stderr, "OpenCV can't force load with %d channels\n", channels);
}
-
+
if( (src = cvLoadImage(filename, flag)) == 0 )
{
- printf("Cannot load file image %s\n", filename);
+ printf("Cannot load image \"%s\"\n", filename);
exit(0);
}
image out = ipl_to_image(src);
@@ -663,7 +805,7 @@
int w, h, c;
unsigned char *data = stbi_load(filename, &w, &h, &c, channels);
if (!data) {
- fprintf(stderr, "Cannot load file image %s\nSTB Reason: %s\n", filename, stbi_failure_reason());
+ fprintf(stderr, "Cannot load image \"%s\"\nSTB Reason: %s\n", filename, stbi_failure_reason());
exit(0);
}
if(channels) c = channels;
@@ -684,11 +826,11 @@
image load_image(char *filename, int w, int h, int c)
{
- #ifdef OPENCV
+#ifdef OPENCV
image out = load_image_cv(filename, c);
- #else
+#else
image out = load_image_stb(filename, c);
- #endif
+#endif
if((h && w) && (h != out.h || w != out.w)){
image resized = resize_image(out, w, h);
@@ -728,6 +870,11 @@
assert(x < m.w && y < m.h && c < m.c);
m.data[c*m.h*m.w + y*m.w + x] = val;
}
+void add_pixel(image m, int x, int y, int c, float val)
+{
+ assert(x < m.w && y < m.h && c < m.c);
+ m.data[c*m.h*m.w + y*m.w + x] += val;
+}
void print_image(image m)
{
@@ -820,8 +967,20 @@
void show_images(image *ims, int n, char *window)
{
image m = collapse_images_vert(ims, n);
- save_image(m, window);
- show_image(m, window);
+ /*
+ int w = 448;
+ int h = ((float)m.h/m.w) * 448;
+ if(h > 896){
+ h = 896;
+ w = ((float)m.w/m.h) * 896;
+ }
+ 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);
free_image(m);
}
--
Gitblit v1.10.0