From 028696bf15efeca3acb3db8c42a96f7b9e0f55ff Mon Sep 17 00:00:00 2001
From: iovodov <b@ovdv.ru>
Date: Thu, 03 May 2018 13:33:46 +0000
Subject: [PATCH] Output improvements for detector results: When printing detector results, output was done in random order, obfuscating results for interpreting. Now: 1. Text output includes coordinates of rects in (left,right,top,bottom in pixels) along with label and score 2. Text output is sorted by rect lefts to simplify finding appropriate rects on image 3. If several class probs are > thresh for some detection, the most probable is written first and coordinates for others are not repeated 4. Rects are imprinted in image in order by their best class prob, so most probable rects are always on top and not overlayed by less probable ones 5. Most probable label for rect is always written first Also: 6. Message about low GPU memory include required amount
---
src/yolo.c | 160 ++++++++++++++++-------------------------------------
1 files changed, 48 insertions(+), 112 deletions(-)
diff --git a/src/yolo.c b/src/yolo.c
index d62c533..238454e 100644
--- a/src/yolo.c
+++ b/src/yolo.c
@@ -4,20 +4,24 @@
#include "utils.h"
#include "parser.h"
#include "box.h"
+#include "demo.h"
#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"
+#endif
#endif
char *voc_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
-image voc_labels[20];
void train_yolo(char *cfgfile, char *weightfile)
{
- char *train_images = "data/voc.0712.trainval";
+ char *train_images = "/data/voc/train.txt";
char *backup_directory = "/home/pjreddie/backup/";
srand(time(0));
- data_seed = time(0);
char *base = basecfg(cfgfile);
printf("%s\n", base);
float avg_loss = -1;
@@ -53,6 +57,11 @@
args.d = &buffer;
args.type = REGION_DATA;
+ args.angle = net.angle;
+ args.exposure = net.exposure;
+ args.saturation = net.saturation;
+ args.hue = net.hue;
+
pthread_t load_thread = load_data_in_thread(args);
clock_t time;
//while(i*imgs < N*120){
@@ -71,7 +80,7 @@
avg_loss = avg_loss*.9 + loss*.1;
printf("%d: %f, %f avg, %f rate, %lf seconds, %d images\n", i, loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
- if(i%1000==0 || i == 600){
+ if(i%1000==0 || (i < 1000 && i%100 == 0)){
char buff[256];
sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
save_weights(net, buff);
@@ -83,34 +92,6 @@
save_weights(net, buff);
}
-void convert_yolo_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness)
-{
- int i,j,n;
- //int per_cell = 5*num+classes;
- for (i = 0; i < side*side; ++i){
- int row = i / side;
- int col = i % side;
- for(n = 0; n < num; ++n){
- int index = i*num + n;
- int p_index = side*side*classes + i*num + n;
- float scale = predictions[p_index];
- int box_index = side*side*(classes + num) + (i*num + n)*4;
- boxes[index].x = (predictions[box_index + 0] + col) / side * w;
- boxes[index].y = (predictions[box_index + 1] + row) / side * h;
- boxes[index].w = pow(predictions[box_index + 2], (square?2:1)) * w;
- boxes[index].h = pow(predictions[box_index + 3], (square?2:1)) * h;
- for(j = 0; j < classes; ++j){
- int class_index = i*classes;
- float prob = scale*predictions[class_index+j];
- probs[index][j] = (prob > thresh) ? prob : 0;
- }
- if(only_objectness){
- probs[index][0] = scale;
- }
- }
- }
-}
-
void print_yolo_detections(FILE **fps, char *id, box *boxes, float **probs, int total, int classes, int w, int h)
{
int i, j;
@@ -143,14 +124,13 @@
srand(time(0));
char *base = "results/comp4_det_test_";
- list *plist = get_paths("data/voc.2007.test");
+ //list *plist = get_paths("data/voc.2007.test");
+ list *plist = get_paths("/home/pjreddie/data/voc/2007_test.txt");
//list *plist = get_paths("data/voc.2012.test");
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
- int square = l.sqrt;
- int side = l.side;
int j;
FILE **fps = calloc(classes, sizeof(FILE *));
@@ -159,9 +139,9 @@
snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]);
fps[j] = fopen(buff, "w");
}
- box *boxes = calloc(side*side*l.n, sizeof(box));
- float **probs = calloc(side*side*l.n, sizeof(float *));
- for(j = 0; j < side*side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
+ box *boxes = calloc(l.side*l.side*l.n, sizeof(box));
+ float **probs = calloc(l.side*l.side*l.n, sizeof(float *));
+ for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
@@ -171,7 +151,7 @@
int nms = 1;
float iou_thresh = .5;
- int nthreads = 2;
+ int nthreads = 8;
image *val = calloc(nthreads, sizeof(image));
image *val_resized = calloc(nthreads, sizeof(image));
image *buf = calloc(nthreads, sizeof(image));
@@ -207,12 +187,12 @@
char *path = paths[i+t-nthreads];
char *id = basecfg(path);
float *X = val_resized[t].data;
- float *predictions = network_predict(net, X);
+ network_predict(net, X);
int w = val[t].w;
int h = val[t].h;
- convert_yolo_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0);
- if (nms) do_nms_sort(boxes, probs, side*side*l.n, classes, iou_thresh);
- print_yolo_detections(fps, id, boxes, probs, side*side*l.n, classes, w, h);
+ get_detection_boxes(l, w, h, thresh, probs, boxes, 0);
+ if (nms) do_nms_sort_v2(boxes, probs, l.side*l.side*l.n, classes, iou_thresh);
+ print_yolo_detections(fps, id, boxes, probs, l.side*l.side*l.n, classes, w, h);
free(id);
free_image(val[t]);
free_image(val_resized[t]);
@@ -237,7 +217,6 @@
layer l = net.layers[net.n-1];
int classes = l.classes;
- int square = l.sqrt;
int side = l.side;
int j, k;
@@ -255,9 +234,8 @@
int i=0;
float thresh = .001;
- int nms = 0;
float iou_thresh = .5;
- float nms_thresh = .5;
+ float nms = 0;
int total = 0;
int correct = 0;
@@ -269,14 +247,15 @@
image orig = load_image_color(path, 0, 0);
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
- float *predictions = network_predict(net, sized.data);
- convert_yolo_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 1);
- if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms_thresh);
+ network_predict(net, sized.data);
+ get_detection_boxes(l, orig.w, orig.h, thresh, probs, boxes, 1);
+ if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms);
- char *labelpath = find_replace(path, "images", "labels");
- labelpath = find_replace(labelpath, "JPEGImages", "labels");
- labelpath = find_replace(labelpath, ".jpg", ".txt");
- labelpath = find_replace(labelpath, ".JPEG", ".txt");
+ char labelpath[4096];
+ find_replace(path, "images", "labels", labelpath);
+ find_replace(labelpath, "JPEGImages", "labels", labelpath);
+ find_replace(labelpath, ".jpg", ".txt", labelpath);
+ find_replace(labelpath, ".JPEG", ".txt", labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
@@ -310,7 +289,7 @@
void test_yolo(char *cfgfile, char *weightfile, char *filename, float thresh)
{
-
+ image **alphabet = load_alphabet();
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
@@ -322,7 +301,7 @@
char buff[256];
char *input = buff;
int j;
- float nms=.5;
+ float nms=.4;
box *boxes = calloc(l.side*l.side*l.n, sizeof(box));
float **probs = calloc(l.side*l.side*l.n, sizeof(float *));
for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float *));
@@ -340,14 +319,15 @@
image sized = resize_image(im, net.w, net.h);
float *X = sized.data;
time=clock();
- float *predictions = network_predict(net, X);
+ network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
- convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
- if (nms) do_nms_sort(boxes, probs, l.side*l.side*l.n, l.classes, nms);
- draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, voc_labels, 20);
+ get_detection_boxes(l, 1, 1, thresh, probs, boxes, 0);
+ if (nms) do_nms_sort_v2(boxes, probs, l.side*l.side*l.n, l.classes, nms);
+ //draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, alphabet, 20);
+ draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, alphabet, 20);
+ save_image(im, "predictions");
show_image(im, "predictions");
- show_image(sized, "resized");
free_image(im);
free_image(sized);
#ifdef OPENCV
@@ -358,61 +338,16 @@
}
}
-/*
-#ifdef OPENCV
-image ipl_to_image(IplImage* src);
-#include "opencv2/highgui/highgui_c.h"
-#include "opencv2/imgproc/imgproc_c.h"
-
-void demo_swag(char *cfgfile, char *weightfile, float thresh)
-{
-network net = parse_network_cfg(cfgfile);
-if(weightfile){
-load_weights(&net, weightfile);
-}
-detection_layer layer = net.layers[net.n-1];
-CvCapture *capture = cvCaptureFromCAM(-1);
-set_batch_network(&net, 1);
-srand(2222222);
-while(1){
-IplImage* frame = cvQueryFrame(capture);
-image im = ipl_to_image(frame);
-cvReleaseImage(&frame);
-rgbgr_image(im);
-
-image sized = resize_image(im, net.w, net.h);
-float *X = sized.data;
-float *predictions = network_predict(net, X);
-draw_swag(im, predictions, layer.side, layer.n, "predictions", thresh);
-free_image(im);
-free_image(sized);
-cvWaitKey(10);
-}
-}
-#else
-void demo_swag(char *cfgfile, char *weightfile, float thresh){}
-#endif
- */
-
-void demo_yolo(char *cfgfile, char *weightfile, float thresh, int cam_index);
-#ifndef GPU
-void demo_yolo(char *cfgfile, char *weightfile, float thresh, int cam_index)
-{
- fprintf(stderr, "Darknet must be compiled with CUDA for YOLO demo.\n");
-}
-#endif
-
void run_yolo(int argc, char **argv)
{
- int i;
- for(i = 0; i < 20; ++i){
- char buff[256];
- sprintf(buff, "data/labels/%s.png", voc_names[i]);
- voc_labels[i] = load_image_color(buff, 0, 0);
- }
-
+ int dont_show = find_arg(argc, argv, "-dont_show");
+ int http_stream_port = find_int_arg(argc, argv, "-http_port", -1);
+ char *out_filename = find_char_arg(argc, argv, "-out_filename", 0);
+ char *prefix = find_char_arg(argc, argv, "-prefix", 0);
float thresh = find_float_arg(argc, argv, "-thresh", .2);
+ float hier_thresh = find_float_arg(argc, argv, "-hier", .5);
int cam_index = find_int_arg(argc, argv, "-c", 0);
+ int frame_skip = find_int_arg(argc, argv, "-s", 0);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
@@ -425,5 +360,6 @@
else if(0==strcmp(argv[2], "train")) train_yolo(cfg, weights);
else if(0==strcmp(argv[2], "valid")) validate_yolo(cfg, weights);
else if(0==strcmp(argv[2], "recall")) validate_yolo_recall(cfg, weights);
- else if(0==strcmp(argv[2], "demo")) demo_yolo(cfg, weights, thresh, cam_index);
+ else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, hier_thresh, cam_index, filename, voc_names, 20, frame_skip,
+ prefix, out_filename, http_stream_port, dont_show);
}
--
Gitblit v1.10.0