From c7b10ceadb1a78e7480d281444a31ae2a7dc1b05 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 06 May 2016 23:25:16 +0000
Subject: [PATCH] so much need to commit
---
src/image.c | 270 ++++++++++++++++++++++++++++++++++++++++++++++-------
1 files changed, 233 insertions(+), 37 deletions(-)
diff --git a/src/image.c b/src/image.c
index b6d7577..aff5f64 100644
--- a/src/image.c
+++ b/src/image.c
@@ -1,13 +1,9 @@
#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
@@ -28,6 +24,26 @@
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);
@@ -42,25 +58,25 @@
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;
}
}
@@ -85,6 +101,80 @@
}
}
+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;
+ width = 8;
+ 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 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)
{
int i,j,k;
@@ -201,7 +291,7 @@
}
#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);
@@ -215,7 +305,7 @@
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){
@@ -244,7 +334,7 @@
}
#endif
- void show_image(image p, char *name)
+ void show_image(image p, const char *name)
{
#ifdef OPENCV
show_image_cv(p, name);
@@ -254,7 +344,7 @@
#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);
@@ -272,6 +362,16 @@
}
#ifdef OPENCV
+ image get_image_from_stream(CvCapture *cap)
+ {
+ IplImage* src = cvQueryFrame(cap);
+ image im = ipl_to_image(src);
+ rgbgr_image(im);
+ return im;
+ }
+#endif
+
+#ifdef OPENCV
void save_image_jpg(image p, char *name)
{
image copy = copy_image(p);
@@ -294,7 +394,7 @@
cvReleaseImage(&disp);
free_image(copy);
}
- #endif
+#endif
void show_image_layers(image p, char *name)
{
@@ -332,6 +432,17 @@
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);
@@ -390,6 +501,34 @@
return cropped;
}
+ 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 low, int high, int size)
+ {
+ int r = rand_int(low, high);
+ image resized = resize_min(im, r);
+ int dx = rand_int(0, resized.w - size);
+ int dy = rand_int(0, resized.h - size);
+ image crop = crop_image(resized, dx, dy, size, size);
+
+ if(resized.data != im.data) free_image(resized);
+ return crop;
+ }
+
float three_way_max(float a, float b, float c)
{
return (a > b) ? ( (a > c) ? a : c) : ( (b > c) ? b : c) ;
@@ -482,7 +621,7 @@
{
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){
@@ -491,11 +630,19 @@
}
}
}
- 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);
@@ -525,6 +672,17 @@
}
}
+ 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);
@@ -593,7 +751,7 @@
for(r = 0; r < im.h; ++r){
for(c = 0; c < w; ++c){
float val = 0;
- if(c == w-1){
+ if(c == w-1 || im.w == 1){
val = get_pixel(im, im.w-1, r, k);
} else {
float sx = c*w_scale;
@@ -614,7 +772,7 @@
float val = (1-dy) * get_pixel(part, c, iy, k);
set_pixel(resized, c, r, k, val);
}
- if(r == h-1) continue;
+ 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);
@@ -626,9 +784,13 @@
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);
@@ -643,7 +805,29 @@
image exp5 = copy_image(im);
exposure_image(exp5, .5);
- show_image(im, "Original");
+ image bin = binarize_image(im);
+
+#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(bin, "Binary");
show_image(gray, "Gray");
show_image(sat2, "Saturation-2");
show_image(sat5, "Saturation-.5");
@@ -688,8 +872,12 @@
if( (src = cvLoadImage(filename, flag)) == 0 )
{
- printf("Cannot load file 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);
@@ -705,7 +893,7 @@
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;
@@ -864,18 +1052,26 @@
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);
/*
- 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);
- */
+ 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);
--
Gitblit v1.10.0