From 1b5afb45838e603fa6780762eb8cc59246dc2d81 Mon Sep 17 00:00:00 2001
From: IlyaOvodov <b@ovdv.ru>
Date: Tue, 08 May 2018 11:09:35 +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 | 309 +++++++++++++++++++++++++++------------------------
1 files changed, 163 insertions(+), 146 deletions(-)
diff --git a/src/yolo.c b/src/yolo.c
index 61a5344..238454e 100644
--- a/src/yolo.c
+++ b/src/yolo.c
@@ -4,60 +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_class_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
-
-void draw_yolo(image im, float *box, int side, int objectness, char *label, float thresh)
-{
- int classes = 20;
- int elems = 4+classes+objectness;
- int j;
- int r, c;
-
- for(r = 0; r < side; ++r){
- for(c = 0; c < side; ++c){
- j = (r*side + c) * elems;
- float scale = 1;
- if(objectness) scale = 1 - box[j++];
- int class = max_index(box+j, classes);
- if(scale * box[j+class] > thresh){
- int width = sqrt(scale*box[j+class])*5 + 1;
- printf("%f %s\n", scale * box[j+class], voc_class_names[class]);
- float red = get_color(0,class,classes);
- float green = get_color(1,class,classes);
- float blue = get_color(2,class,classes);
-
- j += classes;
- float x = box[j+0];
- float y = box[j+1];
- x = (x+c)/side;
- y = (y+r)/side;
- float w = box[j+2]; //*maxwidth;
- float h = box[j+3]; //*maxheight;
- h = h*h;
- w = w*w;
-
- int left = (x-w/2)*im.w;
- int right = (x+w/2)*im.w;
- int top = (y-h/2)*im.h;
- int bot = (y+h/2)*im.h;
- draw_box_width(im, left, top, right, bot, width, red, green, blue);
- }
- }
- }
- show_image(im, label);
-}
+char *voc_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
void train_yolo(char *cfgfile, char *weightfile)
{
- char *train_images = "/home/pjreddie/data/voc/test/train.txt";
+ 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;
@@ -65,28 +29,21 @@
if(weightfile){
load_weights(&net, weightfile);
}
- detection_layer layer = get_network_detection_layer(net);
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- int imgs = 128;
+ int imgs = net.batch*net.subdivisions;
int i = *net.seen/imgs;
-
- char **paths;
- list *plist = get_paths(train_images);
- int N = plist->size;
- paths = (char **)list_to_array(plist);
-
- if(i*imgs > N*80){
- net.layers[net.n-1].joint = 1;
- net.layers[net.n-1].objectness = 0;
- }
- if(i*imgs > N*120){
- net.layers[net.n-1].rescore = 1;
- }
data train, buffer;
- int classes = layer.classes;
- int background = layer.objectness;
- int side = sqrt(get_detection_layer_locations(layer));
+
+ layer l = net.layers[net.n - 1];
+
+ int side = l.side;
+ int classes = l.classes;
+ float jitter = l.jitter;
+
+ list *plist = get_paths(train_images);
+ //int N = plist->size;
+ char **paths = (char **)list_to_array(plist);
load_args args = {0};
args.w = net.w;
@@ -95,14 +52,20 @@
args.n = imgs;
args.m = plist->size;
args.classes = classes;
+ args.jitter = jitter;
args.num_boxes = side;
- args.background = background;
args.d = &buffer;
- args.type = DETECTION_DATA;
+ 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*130){
+ //while(i*imgs < N*120){
+ while(get_current_batch(net) < net.max_batches){
i += 1;
time=clock();
pthread_join(load_thread, 0);
@@ -110,46 +73,14 @@
load_thread = load_data_in_thread(args);
printf("Loaded: %lf seconds\n", sec(clock()-time));
+
time=clock();
float loss = train_network(net, train);
if (avg_loss < 0) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
- printf("%d: %f, %f avg, %lf seconds, %d images, epoch: %f\n", i, loss, avg_loss, sec(clock()-time), i*imgs, ((float)i)*imgs/N);
-
- if((i-1)*imgs <= N && i*imgs > N){
- fprintf(stderr, "First stage done\n");
- net.learning_rate *= 10;
- char buff[256];
- sprintf(buff, "%s/%s_first_stage.weights", backup_directory, base);
- save_weights(net, buff);
- }
-
- if((i-1)*imgs <= 80*N && i*imgs > N*80){
- fprintf(stderr, "Second stage done.\n");
- net.learning_rate *= .1;
- char buff[256];
- sprintf(buff, "%s/%s_second_stage.weights", backup_directory, base);
- save_weights(net, buff);
- net.layers[net.n-1].joint = 1;
- net.layers[net.n-1].objectness = 0;
- background = 0;
-
- pthread_join(load_thread, 0);
- free_data(buffer);
- args.background = background;
- load_thread = load_data_in_thread(args);
- }
-
- if((i-1)*imgs <= 120*N && i*imgs > N*120){
- fprintf(stderr, "Third stage done.\n");
- char buff[256];
- sprintf(buff, "%s/%s_final.weights", backup_directory, base);
- net.layers[net.n-1].rescore = 1;
- save_weights(net, buff);
- }
-
- if(i%1000==0){
+ 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 < 1000 && i%100 == 0)){
char buff[256];
sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
save_weights(net, buff);
@@ -157,36 +88,14 @@
free_data(train);
}
char buff[256];
- sprintf(buff, "%s/%s_rescore.weights", backup_directory, base);
+ sprintf(buff, "%s/%s_final.weights", backup_directory, base);
save_weights(net, buff);
}
-void convert_yolo_detections(float *predictions, int classes, int objectness, int background, int num_boxes, int w, int h, float thresh, float **probs, box *boxes)
-{
- int i,j;
- int per_box = 4+classes+(background || objectness);
- for (i = 0; i < num_boxes*num_boxes; ++i){
- float scale = 1;
- if(objectness) scale = 1-predictions[i*per_box];
- int offset = i*per_box+(background||objectness);
- for(j = 0; j < classes; ++j){
- float prob = scale*predictions[offset+j];
- probs[i][j] = (prob > thresh) ? prob : 0;
- }
- int row = i / num_boxes;
- int col = i % num_boxes;
- offset += classes;
- boxes[i].x = (predictions[offset + 0] + col) / num_boxes * w;
- boxes[i].y = (predictions[offset + 1] + row) / num_boxes * h;
- boxes[i].w = pow(predictions[offset + 2], 2) * w;
- boxes[i].h = pow(predictions[offset + 3], 2) * h;
- }
-}
-
-void print_yolo_detections(FILE **fps, char *id, box *boxes, float **probs, int num_boxes, int classes, int w, int h)
+void print_yolo_detections(FILE **fps, char *id, box *boxes, float **probs, int total, int classes, int w, int h)
{
int i, j;
- for(i = 0; i < num_boxes*num_boxes; ++i){
+ for(i = 0; i < total; ++i){
float xmin = boxes[i].x - boxes[i].w/2.;
float xmax = boxes[i].x + boxes[i].w/2.;
float ymin = boxes[i].y - boxes[i].h/2.;
@@ -211,29 +120,28 @@
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
- detection_layer layer = get_network_detection_layer(net);
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
srand(time(0));
char *base = "results/comp4_det_test_";
- list *plist = get_paths("/home/pjreddie/data/voc/test/2007_test.txt");
+ //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);
- int classes = layer.classes;
- int objectness = layer.objectness;
- int background = layer.background;
- int num_boxes = sqrt(get_detection_layer_locations(layer));
+ layer l = net.layers[net.n-1];
+ int classes = l.classes;
int j;
FILE **fps = calloc(classes, sizeof(FILE *));
for(j = 0; j < classes; ++j){
char buff[1024];
- snprintf(buff, 1024, "%s%s.txt", base, voc_class_names[j]);
+ snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]);
fps[j] = fopen(buff, "w");
}
- box *boxes = calloc(num_boxes*num_boxes, sizeof(box));
- float **probs = calloc(num_boxes*num_boxes, sizeof(float *));
- for(j = 0; j < num_boxes*num_boxes; ++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;
@@ -279,12 +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, objectness, background, num_boxes, w, h, thresh, probs, boxes);
- if (nms) do_nms(boxes, probs, num_boxes*num_boxes, classes, iou_thresh);
- print_yolo_detections(fps, id, boxes, probs, num_boxes, 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]);
@@ -293,34 +201,133 @@
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
}
-void test_yolo(char *cfgfile, char *weightfile, char *filename, float thresh)
+void validate_yolo_recall(char *cfgfile, char *weightfile)
{
-
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
- detection_layer layer = get_network_detection_layer(net);
+ set_batch_network(&net, 1);
+ fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+ srand(time(0));
+
+ char *base = "results/comp4_det_test_";
+ list *plist = get_paths("data/voc.2007.test");
+ char **paths = (char **)list_to_array(plist);
+
+ layer l = net.layers[net.n-1];
+ int classes = l.classes;
+ int side = l.side;
+
+ int j, k;
+ FILE **fps = calloc(classes, sizeof(FILE *));
+ for(j = 0; j < classes; ++j){
+ char buff[1024];
+ 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 *));
+
+ int m = plist->size;
+ int i=0;
+
+ float thresh = .001;
+ float iou_thresh = .5;
+ float nms = 0;
+
+ int total = 0;
+ int correct = 0;
+ int proposals = 0;
+ float avg_iou = 0;
+
+ for(i = 0; i < m; ++i){
+ char *path = paths[i];
+ image orig = load_image_color(path, 0, 0);
+ image sized = resize_image(orig, net.w, net.h);
+ char *id = basecfg(path);
+ 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[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);
+ for(k = 0; k < side*side*l.n; ++k){
+ if(probs[k][0] > thresh){
+ ++proposals;
+ }
+ }
+ for (j = 0; j < num_labels; ++j) {
+ ++total;
+ box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
+ float best_iou = 0;
+ for(k = 0; k < side*side*l.n; ++k){
+ float iou = box_iou(boxes[k], t);
+ if(probs[k][0] > thresh && iou > best_iou){
+ best_iou = iou;
+ }
+ }
+ avg_iou += best_iou;
+ if(best_iou > iou_thresh){
+ ++correct;
+ }
+ }
+
+ fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total);
+ free(id);
+ free_image(orig);
+ free_image(sized);
+ }
+}
+
+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);
+ }
+ detection_layer l = net.layers[net.n-1];
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
- char input[256];
+ char buff[256];
+ char *input = buff;
+ int j;
+ 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 *));
while(1){
if(filename){
strncpy(input, filename, 256);
} else {
printf("Enter Image Path: ");
fflush(stdout);
- fgets(input, 256, stdin);
+ input = fgets(input, 256, stdin);
+ if(!input) return;
strtok(input, "\n");
}
image im = load_image_color(input,0,0);
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));
- draw_yolo(im, predictions, 7, layer.objectness, "predictions", thresh);
+ 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");
+
free_image(im);
free_image(sized);
#ifdef OPENCV
@@ -333,7 +340,14 @@
void run_yolo(int argc, char **argv)
{
+ 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;
@@ -345,4 +359,7 @@
if(0==strcmp(argv[2], "test")) test_yolo(cfg, weights, filename, thresh);
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(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