From 2ce6460c79e06caa33eab3991ee3e7fd9f0909d6 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Tue, 10 Apr 2018 18:08:24 +0000
Subject: [PATCH] Remove truth only if smaller than 1x1 pix during training
---
src/image.c | 520 +++++++++++++++++++++++++++++++++++++++++++++++++++++---
1 files changed, 485 insertions(+), 35 deletions(-)
diff --git a/src/image.c b/src/image.c
index 09718fb..d29f0c1 100644
--- a/src/image.c
+++ b/src/image.c
@@ -13,8 +13,14 @@
#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"
+#include "http_stream.h"
#endif
-
+#include "http_stream.h"
+#endif
int windows = 0;
@@ -53,6 +59,7 @@
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 +77,13 @@
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;
@@ -85,26 +93,38 @@
return b;
}
+image get_label_v3(image **characters, char *string, int size)
+{
+ size = size / 10;
+ if (size > 7) size = 7;
+ image label = make_empty_image(0, 0, 0);
+ while (*string) {
+ image l = characters[size][(int)*string];
+ image n = tile_images(label, l, -size - 1 + (size + 1) / 2);
+ free_image(label);
+ label = n;
+ ++string;
+ }
+ image b = border_image(label, label.h*.25);
+ free_image(label);
+ return b;
+}
+
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)
@@ -164,30 +184,121 @@
}
}
-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_v3(image im, detection *dets, int num, float thresh, char **names, image **alphabet, int classes)
+{
+ int i, j;
+
+ for (i = 0; i < num; ++i) {
+ char labelstr[4096] = { 0 };
+ int class_id = -1;
+ for (j = 0; j < classes; ++j) {
+ if (dets[i].prob[j] > thresh) {
+ if (class_id < 0) {
+ strcat(labelstr, names[j]);
+ class_id = j;
+ }
+ else {
+ strcat(labelstr, ", ");
+ strcat(labelstr, names[j]);
+ }
+ printf("%s: %.0f%%\n", names[j], dets[i].prob[j] * 100);
+ }
+ }
+ if (class_id >= 0) {
+ int width = im.h * .006;
+
+ /*
+ if(0){
+ width = pow(prob, 1./2.)*10+1;
+ alphabet = 0;
+ }
+ */
+
+ //printf("%d %s: %.0f%%\n", i, names[class_id], prob*100);
+ int offset = class_id * 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 = dets[i].bbox;
+ //printf("%f %f %f %f\n", b.x, b.y, b.w, b.h);
+
+ 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 (alphabet) {
+ image label = get_label_v3(alphabet, labelstr, (im.h*.03));
+ draw_label(im, top + width, left, label, rgb);
+ free_image(label);
+ }
+ if (dets[i].mask) {
+ image mask = float_to_image(14, 14, 1, dets[i].mask);
+ image resized_mask = resize_image(mask, b.w*im.w, b.h*im.h);
+ image tmask = threshold_image(resized_mask, .5);
+ embed_image(tmask, im, left, top);
+ free_image(mask);
+ free_image(resized_mask);
+ free_image(tmask);
+ }
+ }
+ }
+}
+
+void draw_detections(image im, 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];
+ int class_id = max_index(probs[i], classes);
+ float prob = probs[i][class_id];
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;
- printf("%s: %.0f%%\n", names[class], prob*100);
- int offset = class*1 % classes;
+
+ if(0){
+ width = pow(prob, 1./2.)*10+1;
+ alphabet = 0;
+ }
+
+ int offset = class_id*123457 % classes;
float red = get_color(2,offset,classes);
float green = get_color(1,offset,classes);
float blue = get_color(0,offset,classes);
@@ -209,16 +320,250 @@
if(right > im.w-1) right = im.w-1;
if(top < 0) top = 0;
if(bot > im.h-1) bot = im.h-1;
+ printf("%s: %.0f%%", names[class_id], prob * 100);
+
+ //printf(" - id: %d, x_center: %d, y_center: %d, width: %d, height: %d",
+ // class_id, (right + left) / 2, (bot - top) / 2, right - left, bot - top);
+ printf("\n");
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_id], (im.h*.03)/10);
draw_label(im, top + width, left, label, rgb);
}
}
}
}
+#ifdef OPENCV
+
+void draw_detections_cv_v3(IplImage* show_img, detection *dets, int num, float thresh, char **names, image **alphabet, int classes)
+{
+ int i, j;
+ if (!show_img) return;
+
+ for (i = 0; i < num; ++i) {
+ char labelstr[4096] = { 0 };
+ int class_id = -1;
+ for (j = 0; j < classes; ++j) {
+ if (dets[i].prob[j] > thresh) {
+ if (class_id < 0) {
+ strcat(labelstr, names[j]);
+ class_id = j;
+ }
+ else {
+ strcat(labelstr, ", ");
+ strcat(labelstr, names[j]);
+ }
+ printf("%s: %.0f%%\n", names[j], dets[i].prob[j] * 100);
+ }
+ }
+ if (class_id >= 0) {
+ int width = show_img->height * .006;
+
+ /*
+ if(0){
+ width = pow(prob, 1./2.)*10+1;
+ alphabet = 0;
+ }
+ */
+
+ //printf("%d %s: %.0f%%\n", i, names[class_id], prob*100);
+ int offset = class_id * 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 = dets[i].bbox;
+ //printf("%f %f %f %f\n", b.x, b.y, b.w, b.h);
+
+ 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_id, names[class_id]);
+ 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_id], pt_text, &font, black_color);
+ }
+ }
+}
+
+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_id = max_index(probs[i], classes);
+ float prob = probs[i][class_id];
+ 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_id], prob * 100);
+ int offset = class_id * 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_id, names[class_id]);
+ 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_id], pt_text, &font, black_color);
+ }
+ }
+}
+
+IplImage* draw_train_chart(float max_img_loss, int max_batches, int number_of_lines, int img_size)
+{
+ int img_offset = 50;
+ int draw_size = img_size - img_offset;
+ IplImage* img = cvCreateImage(cvSize(img_size, img_size), 8, 3);
+ cvSet(img, CV_RGB(255, 255, 255), 0);
+ CvPoint pt1, pt2, pt_text;
+ CvFont font;
+ cvInitFont(&font, CV_FONT_HERSHEY_COMPLEX_SMALL, 0.7, 0.7, 0, 1, CV_AA);
+ char char_buff[100];
+ int i;
+ // vertical lines
+ pt1.x = img_offset; pt2.x = img_size, pt_text.x = 10;
+ for (i = 1; i <= number_of_lines; ++i) {
+ pt1.y = pt2.y = (float)i * draw_size / number_of_lines;
+ cvLine(img, pt1, pt2, CV_RGB(224, 224, 224), 1, 8, 0);
+ if (i % 10 == 0) {
+ sprintf(char_buff, "%2.1f", max_img_loss*(number_of_lines - i) / number_of_lines);
+ pt_text.y = pt1.y + 5;
+ cvPutText(img, char_buff, pt_text, &font, CV_RGB(0, 0, 0));
+ cvLine(img, pt1, pt2, CV_RGB(128, 128, 128), 1, 8, 0);
+ }
+ }
+ // horizontal lines
+ pt1.y = draw_size; pt2.y = 0, pt_text.y = draw_size + 15;
+ for (i = 0; i <= number_of_lines; ++i) {
+ pt1.x = pt2.x = img_offset + (float)i * draw_size / number_of_lines;
+ cvLine(img, pt1, pt2, CV_RGB(224, 224, 224), 1, 8, 0);
+ if (i % 10 == 0) {
+ sprintf(char_buff, "%d", max_batches * i / number_of_lines);
+ pt_text.x = pt1.x - 20;
+ cvPutText(img, char_buff, pt_text, &font, CV_RGB(0, 0, 0));
+ cvLine(img, pt1, pt2, CV_RGB(128, 128, 128), 1, 8, 0);
+ }
+ }
+ cvPutText(img, "Iteration number", cvPoint(draw_size / 2, img_size - 10), &font, CV_RGB(0, 0, 0));
+ cvPutText(img, "Press 's' to save: chart.jpg", cvPoint(5, img_size - 10), &font, CV_RGB(0, 0, 0));
+ printf(" If error occurs - run training with flag: -dont_show \n");
+ cvNamedWindow("average loss", CV_WINDOW_NORMAL);
+ cvMoveWindow("average loss", 0, 0);
+ cvResizeWindow("average loss", img_size, img_size);
+ cvShowImage("average loss", img);
+ cvWaitKey(20);
+ return img;
+}
+
+void draw_train_loss(IplImage* img, int img_size, float avg_loss, float max_img_loss, int current_batch, int max_batches)
+{
+ int img_offset = 50;
+ int draw_size = img_size - img_offset;
+ CvFont font;
+ cvInitFont(&font, CV_FONT_HERSHEY_COMPLEX_SMALL, 0.7, 0.7, 0, 1, CV_AA);
+ char char_buff[100];
+ CvPoint pt1, pt2;
+ pt1.x = img_offset + draw_size * (float)current_batch / max_batches;
+ pt1.y = draw_size * (1 - avg_loss / max_img_loss);
+ if (pt1.y < 0) pt1.y = 1;
+ cvCircle(img, pt1, 1, CV_RGB(0, 0, 255), CV_FILLED, 8, 0);
+
+ sprintf(char_buff, "current avg loss = %2.4f", avg_loss);
+ pt1.x = img_size / 2, pt1.y = 30;
+ pt2.x = pt1.x + 250, pt2.y = pt1.y + 20;
+ cvRectangle(img, pt1, pt2, CV_RGB(255, 255, 255), CV_FILLED, 8, 0);
+ pt1.y += 15;
+ cvPutText(img, char_buff, pt1, &font, CV_RGB(0, 0, 0));
+ cvShowImage("average loss", img);
+ int k = cvWaitKey(20);
+ if (k == 's') cvSaveImage("chart.jpg", img, 0);
+}
+#endif // OPENCV
+
void transpose_image(image im)
{
assert(im.w == im.h);
@@ -430,8 +775,23 @@
cvReleaseImage(&buffer);
}
cvShowImage(buff, disp);
+
cvReleaseImage(&disp);
}
+
+
+void show_image_cv_ipl(IplImage *disp, const char *name)
+{
+ 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);
+ //cvReleaseImage(&disp);
+}
#endif
void show_image(image p, const char *name)
@@ -501,6 +861,23 @@
return im;
}
+image get_image_from_stream_resize(CvCapture *cap, int w, int h, IplImage** in_img, int use_webcam)
+{
+ IplImage* src;
+ if (use_webcam) src = get_webcam_frame(cap);
+ else 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 +902,8 @@
}
#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 +917,14 @@
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 +1123,67 @@
#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 +1442,7 @@
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 +1542,7 @@
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 +1594,16 @@
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