From accf3a59c8b17c70dcc39e8f7daede017190086d Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Tue, 31 Oct 2017 19:10:31 +0000
Subject: [PATCH] Validate and recall always with batch=1
---
src/image.c | 281 ++++++++++++++++++++++++++++++++++++++++++++++++++------
1 files changed, 250 insertions(+), 31 deletions(-)
diff --git a/src/image.c b/src/image.c
index 09718fb..3afe027 100644
--- a/src/image.c
+++ b/src/image.c
@@ -13,6 +13,11 @@
#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
#include "opencv2/imgproc/imgproc_c.h"
+#include "opencv2/core/version.hpp"
+#ifndef CV_VERSION_EPOCH
+#include "opencv2/videoio/videoio_c.h"
+#include "opencv2/imgcodecs/imgcodecs_c.h"
+#endif
#endif
@@ -53,6 +58,7 @@
for(y = 0; y < b.h; ++y){
for(x = 0; x < b.w; ++x){
float val = get_pixel_extend(a, x - border, y - border, k);
+ if(x - border < 0 || x - border >= a.w || y - border < 0 || y - border >= a.h) val = 1;
set_pixel(b, x, y, k, val);
}
}
@@ -70,12 +76,13 @@
return c;
}
-image get_label(image *characters, char *string)
+image get_label(image **characters, char *string, int size)
{
+ if(size > 7) size = 7;
image label = make_empty_image(0,0,0);
while(*string){
- image l = characters[(int)*string];
- image n = tile_images(label, l, -4);
+ image l = characters[size][(int)*string];
+ image n = tile_images(label, l, -size - 1 + (size+1)/2);
free_image(label);
label = n;
++string;
@@ -87,24 +94,19 @@
void draw_label(image a, int r, int c, image label, const float *rgb)
{
- float ratio = (float) label.w / label.h;
- int h = a.h * .04;
- h = label.h;
- h = a.h * .06;
- int w = ratio * h;
- image rl = resize_image(label, w, h);
+ int w = label.w;
+ int h = label.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);
+ float val = get_pixel(label, 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)
@@ -164,19 +166,23 @@
}
}
-image *load_alphabet()
+image **load_alphabet()
{
- int i;
- image *alphabet = calloc(128, sizeof(image));
- for(i = 32; i < 127; ++i){
- char buff[256];
- sprintf(buff, "data/labels/%d.png", i);
- alphabet[i] = load_image_color(buff, 0, 0);
+ int i, j;
+ const int nsize = 8;
+ image **alphabets = calloc(nsize, sizeof(image));
+ for(j = 0; j < nsize; ++j){
+ alphabets[j] = calloc(128, sizeof(image));
+ for(i = 32; i < 127; ++i){
+ char buff[256];
+ sprintf(buff, "data/labels/%d_%d.png", i, j);
+ alphabets[j][i] = load_image_color(buff, 0, 0);
+ }
}
- return alphabet;
+ return alphabets;
}
-void draw_detections(image im, int num, float thresh, box *boxes, float **probs, char **names, image *alphabet, int classes)
+void draw_detections(image im, int num, float thresh, box *boxes, float **probs, char **names, image **alphabet, int classes)
{
int i;
@@ -184,10 +190,24 @@
int class = max_index(probs[i], classes);
float prob = probs[i][class];
if(prob > thresh){
- //int width = pow(prob, 1./2.)*30+1;
+
+ //// for comparison with OpenCV version of DNN Darknet Yolo v2
+ //printf("\n %f, %f, %f, %f, ", boxes[i].x, boxes[i].y, boxes[i].w, boxes[i].h);
+ // int k;
+ //for (k = 0; k < classes; ++k) {
+ // printf("%f, ", probs[i][k]);
+ //}
+ //printf("\n");
+
int width = im.h * .012;
+
+ if(0){
+ width = pow(prob, 1./2.)*10+1;
+ alphabet = 0;
+ }
+
printf("%s: %.0f%%\n", names[class], prob*100);
- int offset = class*1 % classes;
+ int offset = class*123457 % classes;
float red = get_color(2,offset,classes);
float green = get_color(1,offset,classes);
float blue = get_color(0,offset,classes);
@@ -212,13 +232,85 @@
draw_box_width(im, left, top, right, bot, width, red, green, blue);
if (alphabet) {
- image label = get_label(alphabet, names[class]);
+ image label = get_label(alphabet, names[class], (im.h*.03)/10);
draw_label(im, top + width, left, label, rgb);
}
}
}
}
+#ifdef OPENCV
+void draw_detections_cv(IplImage* show_img, int num, float thresh, box *boxes, float **probs, char **names, image **alphabet, 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 = show_img->height * .012;
+
+ if (0) {
+ width = pow(prob, 1. / 2.) * 10 + 1;
+ alphabet = 0;
+ }
+
+ printf("%s: %.0f%%\n", names[class], prob * 100);
+ int offset = class * 123457 % classes;
+ float red = get_color(2, offset, classes);
+ float green = get_color(1, 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;
+ box b = boxes[i];
+
+ int left = (b.x - b.w / 2.)*show_img->width;
+ int right = (b.x + b.w / 2.)*show_img->width;
+ int top = (b.y - b.h / 2.)*show_img->height;
+ int bot = (b.y + b.h / 2.)*show_img->height;
+
+ if (left < 0) left = 0;
+ if (right > show_img->width - 1) right = show_img->width - 1;
+ if (top < 0) top = 0;
+ if (bot > show_img->height - 1) bot = show_img->height - 1;
+
+ float const font_size = show_img->height / 1000.F;
+ CvPoint pt1, pt2, pt_text, pt_text_bg1, pt_text_bg2;
+ pt1.x = left;
+ pt1.y = top;
+ pt2.x = right;
+ pt2.y = bot;
+ pt_text.x = left;
+ pt_text.y = top - 12;
+ pt_text_bg1.x = left;
+ pt_text_bg1.y = top - (10+25*font_size);
+ pt_text_bg2.x = right;
+ pt_text_bg2.y = top;
+ CvScalar color;
+ color.val[0] = red * 256;
+ color.val[1] = green * 256;
+ color.val[2] = blue * 256;
+
+ cvRectangle(show_img, pt1, pt2, color, width, 8, 0);
+ //printf("left=%d, right=%d, top=%d, bottom=%d, obj_id=%d, obj=%s \n", left, right, top, bot, class, names[class]);
+ cvRectangle(show_img, pt_text_bg1, pt_text_bg2, color, width, 8, 0);
+ cvRectangle(show_img, pt_text_bg1, pt_text_bg2, color, CV_FILLED, 8, 0); // filled
+ CvScalar black_color;
+ black_color.val[0] = 0;
+ CvFont font;
+ cvInitFont(&font, CV_FONT_HERSHEY_SIMPLEX, font_size, font_size, 0, font_size * 3, 8);
+ cvPutText(show_img, names[class], pt_text, &font, black_color);
+ }
+ }
+}
+#endif
+
void transpose_image(image im)
{
assert(im.w == im.h);
@@ -430,8 +522,48 @@
cvReleaseImage(&buffer);
}
cvShowImage(buff, disp);
+
cvReleaseImage(&disp);
}
+
+
+void show_image_cv_ipl(IplImage *disp, const char *name, const char *out_filename)
+{
+ if (disp == NULL) return;
+ char buff[256];
+ //sprintf(buff, "%s (%d)", name, windows);
+ sprintf(buff, "%s", name);
+ cvNamedWindow(buff, CV_WINDOW_NORMAL);
+ //cvMoveWindow(buff, 100*(windows%10) + 200*(windows/10), 100*(windows%10));
+ ++windows;
+ cvShowImage(buff, disp);
+
+ if(out_filename)
+ {
+ CvSize size;
+ {
+ size.width = disp->width, size.height = disp->height;
+ }
+
+ static CvVideoWriter* output_video = NULL; // cv::VideoWriter output_video;
+ if (output_video == NULL)
+ {
+ //const char* output_name = "test_dnn_out.avi";
+ //output_video = cvCreateVideoWriter(out_filename, CV_FOURCC('H', '2', '6', '4'), 25, size, 1);
+ output_video = cvCreateVideoWriter(out_filename, CV_FOURCC('D', 'I', 'V', 'X'), 25, size, 1);
+ //output_video = cvCreateVideoWriter(out_filename, CV_FOURCC('M', 'J', 'P', 'G'), 25, size, 1);
+ //output_video = cvCreateVideoWriter(out_filename, CV_FOURCC('M', 'P', '4', 'V'), 25, size, 1);
+ //output_video = cvCreateVideoWriter(out_filename, CV_FOURCC('M', 'P', '4', '2'), 25, size, 1);
+ //output_video = cvCreateVideoWriter(out_filename, CV_FOURCC('X', 'V', 'I', 'D'), 25, size, 1);
+ //output_video = cvCreateVideoWriter(out_filename, CV_FOURCC('W', 'M', 'V', '2'), 25, size, 1);
+ }
+
+ cvWriteFrame(output_video, disp); // comment this line to improve FPS !!!
+ printf("\n cvWriteFrame \n");
+ }
+
+ cvReleaseImage(&disp);
+}
#endif
void show_image(image p, const char *name)
@@ -501,6 +633,20 @@
return im;
}
+image get_image_from_stream_resize(CvCapture *cap, int w, int h, IplImage** in_img)
+{
+ IplImage* src = cvQueryFrame(cap);
+ if (!src) return make_empty_image(0, 0, 0);
+ IplImage* new_img = cvCreateImage(cvSize(w, h), IPL_DEPTH_8U, 3);
+ *in_img = cvCreateImage(cvSize(src->width, src->height), IPL_DEPTH_8U, 3);
+ cvResize(src, *in_img, CV_INTER_LINEAR);
+ cvResize(src, new_img, CV_INTER_LINEAR);
+ image im = ipl_to_image(new_img);
+ cvReleaseImage(&new_img);
+ rgbgr_image(im);
+ return im;
+}
+
void save_image_jpg(image p, const char *name)
{
image copy = copy_image(p);
@@ -525,11 +671,8 @@
}
#endif
-void save_image(image im, const char *name)
+void save_image_png(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);
@@ -543,6 +686,14 @@
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(image im, const char *name)
+{
+#ifdef OPENCV
+ save_image_jpg(im, name);
+#else
+ save_image_png(im, name);
#endif
}
@@ -741,6 +892,67 @@
#endif
}
+void fill_image(image m, float s)
+{
+ int i;
+ for (i = 0; i < m.h*m.w*m.c; ++i) m.data[i] = s;
+}
+
+void letterbox_image_into(image im, int w, int h, image boxed)
+{
+ int new_w = im.w;
+ int new_h = im.h;
+ if (((float)w / im.w) < ((float)h / im.h)) {
+ new_w = w;
+ new_h = (im.h * w) / im.w;
+ }
+ else {
+ new_h = h;
+ new_w = (im.w * h) / im.h;
+ }
+ image resized = resize_image(im, new_w, new_h);
+ embed_image(resized, boxed, (w - new_w) / 2, (h - new_h) / 2);
+ free_image(resized);
+}
+
+image letterbox_image(image im, int w, int h)
+{
+ int new_w = im.w;
+ int new_h = im.h;
+ if (((float)w / im.w) < ((float)h / im.h)) {
+ new_w = w;
+ new_h = (im.h * w) / im.w;
+ }
+ else {
+ new_h = h;
+ new_w = (im.w * h) / im.h;
+ }
+ image resized = resize_image(im, new_w, new_h);
+ image boxed = make_image(w, h, im.c);
+ fill_image(boxed, .5);
+ //int i;
+ //for(i = 0; i < boxed.w*boxed.h*boxed.c; ++i) boxed.data[i] = 0;
+ embed_image(resized, boxed, (w - new_w) / 2, (h - new_h) / 2);
+ free_image(resized);
+ return boxed;
+}
+
+image resize_max(image im, int max)
+{
+ int w = im.w;
+ int h = im.h;
+ if(w > h){
+ h = (h * max) / w;
+ w = max;
+ } else {
+ w = (w * max) / h;
+ h = max;
+ }
+ if(w == im.w && h == im.h) return im;
+ image resized = resize_image(im, w, h);
+ return resized;
+}
+
image resize_min(image im, int min)
{
int w = im.w;
@@ -999,7 +1211,7 @@
void random_distort_image(image im, float hue, float saturation, float exposure)
{
- float dhue = rand_uniform(-hue, hue);
+ float dhue = rand_uniform_strong(-hue, hue);
float dsat = rand_scale(saturation);
float dexp = rand_scale(exposure);
distort_image(im, dhue, dsat, dexp);
@@ -1099,7 +1311,7 @@
show_image(c4, "C4");
#ifdef OPENCV
while(1){
- image aug = random_augment_image(im, 0, 320, 448, 320, .75);
+ image aug = random_augment_image(im, 0, .75, 320, 448, 320);
show_image(aug, "aug");
free_image(aug);
@@ -1151,9 +1363,16 @@
image load_image(char *filename, int w, int h, int c)
{
#ifdef OPENCV
- image out = load_image_cv(filename, c);
+
+#ifndef CV_VERSION_EPOCH
+ //image out = load_image_stb(filename, c); // OpenCV 3.x
+ image out = load_image_cv(filename, c);
#else
- image out = load_image_stb(filename, c);
+ image out = load_image_cv(filename, c); // OpenCV 2.4.x
+#endif
+
+#else
+ image out = load_image_stb(filename, c); // without OpenCV
#endif
if((h && w) && (h != out.h || w != out.w)){
--
Gitblit v1.10.0