From 033e934ce82826c73d851098baf7ce4b1a27c89a Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Wed, 21 Feb 2018 16:14:01 +0000
Subject: [PATCH] If there is excessive GPU-RAM consumption by CUDNN then then do not use Workspace
---
src/detector.c | 382 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 files changed, 369 insertions(+), 13 deletions(-)
diff --git a/src/detector.c b/src/detector.c
index 367b3a3..c851b38 100644
--- a/src/detector.c
+++ b/src/detector.c
@@ -11,15 +11,20 @@
#include "opencv2/highgui/highgui_c.h"
#include "opencv2/core/core_c.h"
#include "opencv2/core/version.hpp"
+
#ifndef CV_VERSION_EPOCH
#include "opencv2/videoio/videoio_c.h"
-#pragma comment(lib, "opencv_world320.lib")
+#define OPENCV_VERSION CVAUX_STR(CV_VERSION_MAJOR)""CVAUX_STR(CV_VERSION_MINOR)""CVAUX_STR(CV_VERSION_REVISION)
+#pragma comment(lib, "opencv_world" OPENCV_VERSION ".lib")
#else
-#pragma comment(lib, "opencv_core2413.lib")
-#pragma comment(lib, "opencv_imgproc2413.lib")
-#pragma comment(lib, "opencv_highgui2413.lib")
+#define OPENCV_VERSION CVAUX_STR(CV_VERSION_EPOCH)""CVAUX_STR(CV_VERSION_MAJOR)""CVAUX_STR(CV_VERSION_MINOR)
+#pragma comment(lib, "opencv_core" OPENCV_VERSION ".lib")
+#pragma comment(lib, "opencv_imgproc" OPENCV_VERSION ".lib")
+#pragma comment(lib, "opencv_highgui" OPENCV_VERSION ".lib")
#endif
+
#endif
+
static int coco_ids[] = {1,2,3,4,5,6,7,8,9,10,11,13,14,15,16,17,18,19,20,21,22,23,24,25,27,28,31,32,33,34,35,36,37,38,39,40,41,42,43,44,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,67,70,72,73,74,75,76,77,78,79,80,81,82,84,85,86,87,88,89,90};
void train_detector(char *datacfg, char *cfgfile, char *weightfile, int *gpus, int ngpus, int clear)
@@ -65,6 +70,9 @@
//int N = plist->size;
char **paths = (char **)list_to_array(plist);
+ int init_w = net.w;
+ int init_h = net.h;
+
load_args args = {0};
args.w = net.w;
args.h = net.h;
@@ -74,9 +82,10 @@
args.classes = classes;
args.jitter = jitter;
args.num_boxes = l.max_boxes;
+ args.small_object = l.small_object;
args.d = &buffer;
args.type = DETECTION_DATA;
- args.threads = 8;
+ args.threads = 4;// 8;
args.angle = net.angle;
args.exposure = net.exposure;
@@ -90,8 +99,9 @@
while(get_current_batch(net) < net.max_batches){
if(l.random && count++%10 == 0){
printf("Resizing\n");
- int dim = (rand() % 10 + 10) * 32;
- if (get_current_batch(net)+100 > net.max_batches) dim = 544;
+ int dim = (rand() % 12 + (init_w/32 - 5)) * 32; // +-160
+ //int dim = (rand() % 10 + 10) * 32;
+ //if (get_current_batch(net)+100 > net.max_batches) dim = 544;
//int dim = (rand() % 4 + 16) * 32;
printf("%d\n", dim);
args.w = dim;
@@ -147,7 +157,8 @@
i = get_current_batch(net);
printf("%d: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
- if (i % 1000 == 0 || (i < 1000 && i % 100 == 0)) {
+ //if (i % 1000 == 0 || (i < 1000 && i % 100 == 0)) {
+ if (i % 100 == 0) {
#ifdef GPU
if (ngpus != 1) sync_nets(nets, ngpus, 0);
#endif
@@ -253,7 +264,7 @@
int *map = 0;
if (mapf) map = read_map(mapf);
- network net = parse_network_cfg(cfgfile);
+ network net = parse_network_cfg_custom(cfgfile, 1);
if(weightfile){
load_weights(&net, weightfile);
}
@@ -304,6 +315,8 @@
float thresh = .005;
float nms = .45;
+ int detection_count = 0;
+
int nthreads = 4;
image *val = calloc(nthreads, sizeof(image));
image *val_resized = calloc(nthreads, sizeof(image));
@@ -345,6 +358,15 @@
int h = val[t].h;
get_region_boxes(l, w, h, thresh, probs, boxes, 0, map);
if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, nms);
+
+ int x, y;
+ for (x = 0; x < (l.w*l.h*l.n); ++x) {
+ for (y = 0; y < classes; ++y)
+ {
+ if (probs[x][y]) ++detection_count;
+ }
+ }
+
if (coco){
print_cocos(fp, path, boxes, probs, l.w*l.h*l.n, classes, w, h);
} else if (imagenet){
@@ -365,12 +387,13 @@
fprintf(fp, "\n]\n");
fclose(fp);
}
+ printf("\n detection_count = %d \n", detection_count);
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
}
void validate_detector_recall(char *datacfg, char *cfgfile, char *weightfile)
{
- network net = parse_network_cfg(cfgfile);
+ network net = parse_network_cfg_custom(cfgfile, 1);
if(weightfile){
load_weights(&net, weightfile);
}
@@ -394,10 +417,12 @@
int m = plist->size;
int i=0;
- float thresh = .2;// .001;
+ float thresh = .001;// .001; // .2;
float iou_thresh = .5;
float nms = .4;
+ int detection_count = 0, truth_count = 0;
+
int total = 0;
int correct = 0;
int proposals = 0;
@@ -421,6 +446,7 @@
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
+ truth_count += num_labels;
for(k = 0; k < l.w*l.h*l.n; ++k){
if(probs[k][0] > thresh){
++proposals;
@@ -447,6 +473,329 @@
free_image(orig);
free_image(sized);
}
+ printf("\n truth_count = %d \n", truth_count);
+}
+
+typedef struct {
+ box b;
+ float p;
+ int class_id;
+ int image_index;
+ int truth_flag;
+ int unique_truth_index;
+} box_prob;
+
+int detections_comparator(const void *pa, const void *pb)
+{
+ box_prob a = *(box_prob *)pa;
+ box_prob b = *(box_prob *)pb;
+ float diff = a.p - b.p;
+ if (diff < 0) return 1;
+ else if (diff > 0) return -1;
+ return 0;
+}
+
+void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile)
+{
+ int j;
+ list *options = read_data_cfg(datacfg);
+ char *valid_images = option_find_str(options, "valid", "data/train.txt");
+ char *difficult_valid_images = option_find_str(options, "difficult", NULL);
+ char *name_list = option_find_str(options, "names", "data/names.list");
+ char **names = get_labels(name_list);
+ char *mapf = option_find_str(options, "map", 0);
+ int *map = 0;
+ if (mapf) map = read_map(mapf);
+
+ network net = parse_network_cfg_custom(cfgfile, 1);
+ if (weightfile) {
+ load_weights(&net, weightfile);
+ }
+ 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));
+
+ list *plist = get_paths(valid_images);
+ char **paths = (char **)list_to_array(plist);
+
+ char **paths_dif = NULL;
+ if (difficult_valid_images) {
+ list *plist_dif = get_paths(difficult_valid_images);
+ paths_dif = (char **)list_to_array(plist_dif);
+ }
+
+
+ layer l = net.layers[net.n - 1];
+ int classes = l.classes;
+
+ box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
+ float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
+ for (j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
+
+ int m = plist->size;
+ int i = 0;
+ int t;
+
+ const float thresh = .005;
+ const float nms = .45;
+ const float iou_thresh = 0.5;
+
+ int nthreads = 4;
+ image *val = calloc(nthreads, sizeof(image));
+ image *val_resized = calloc(nthreads, sizeof(image));
+ image *buf = calloc(nthreads, sizeof(image));
+ image *buf_resized = calloc(nthreads, sizeof(image));
+ pthread_t *thr = calloc(nthreads, sizeof(pthread_t));
+
+ load_args args = { 0 };
+ args.w = net.w;
+ args.h = net.h;
+ args.type = IMAGE_DATA;
+
+ const float thresh_calc_avg_iou = 0.24;
+ float avg_iou = 0;
+ int tp_for_thresh = 0;
+ int fp_for_thresh = 0;
+
+ box_prob *detections = calloc(1, sizeof(box_prob));
+ int detections_count = 0;
+ int unique_truth_count = 0;
+
+ int *truth_classes_count = calloc(classes, sizeof(int));
+
+ for (t = 0; t < nthreads; ++t) {
+ args.path = paths[i + t];
+ args.im = &buf[t];
+ args.resized = &buf_resized[t];
+ thr[t] = load_data_in_thread(args);
+ }
+ time_t start = time(0);
+ for (i = nthreads; i < m + nthreads; i += nthreads) {
+ fprintf(stderr, "%d\n", i);
+ for (t = 0; t < nthreads && i + t - nthreads < m; ++t) {
+ pthread_join(thr[t], 0);
+ val[t] = buf[t];
+ val_resized[t] = buf_resized[t];
+ }
+ for (t = 0; t < nthreads && i + t < m; ++t) {
+ args.path = paths[i + t];
+ args.im = &buf[t];
+ args.resized = &buf_resized[t];
+ thr[t] = load_data_in_thread(args);
+ }
+ for (t = 0; t < nthreads && i + t - nthreads < m; ++t) {
+ const int image_index = i + t - nthreads;
+ char *path = paths[image_index];
+ char *id = basecfg(path);
+ float *X = val_resized[t].data;
+ network_predict(net, X);
+ get_region_boxes(l, 1, 1, thresh, probs, boxes, 0, map);
+ if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, 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);
+ find_replace(labelpath, ".png", ".txt", labelpath);
+ int num_labels = 0;
+ box_label *truth = read_boxes(labelpath, &num_labels);
+ int i, j;
+ for (j = 0; j < num_labels; ++j) {
+ truth_classes_count[truth[j].id]++;
+ }
+
+ // difficult
+ box_label *truth_dif = NULL;
+ int num_labels_dif = 0;
+ if (paths_dif)
+ {
+ char *path_dif = paths_dif[image_index];
+
+ char labelpath_dif[4096];
+ find_replace(path_dif, "images", "labels", labelpath_dif);
+ find_replace(labelpath_dif, "JPEGImages", "labels", labelpath_dif);
+ find_replace(labelpath_dif, ".jpg", ".txt", labelpath_dif);
+ find_replace(labelpath_dif, ".JPEG", ".txt", labelpath_dif);
+ find_replace(labelpath_dif, ".png", ".txt", labelpath_dif);
+ truth_dif = read_boxes(labelpath_dif, &num_labels_dif);
+ }
+
+ for (i = 0; i < (l.w*l.h*l.n); ++i) {
+
+ int class_id;
+ for (class_id = 0; class_id < classes; ++class_id) {
+ float prob = probs[i][class_id];
+ if (prob > 0) {
+ detections_count++;
+ detections = realloc(detections, detections_count * sizeof(box_prob));
+ detections[detections_count - 1].b = boxes[i];
+ detections[detections_count - 1].p = prob;
+ detections[detections_count - 1].image_index = image_index;
+ detections[detections_count - 1].class_id = class_id;
+ detections[detections_count - 1].truth_flag = 0;
+ detections[detections_count - 1].unique_truth_index = -1;
+
+ int truth_index = -1;
+ float max_iou = 0;
+ for (j = 0; j < num_labels; ++j)
+ {
+ box t = { truth[j].x, truth[j].y, truth[j].w, truth[j].h };
+ //printf(" IoU = %f, prob = %f, class_id = %d, truth[j].id = %d \n",
+ // box_iou(boxes[i], t), prob, class_id, truth[j].id);
+ float current_iou = box_iou(boxes[i], t);
+ if (current_iou > iou_thresh && class_id == truth[j].id) {
+ if (current_iou > max_iou) {
+ max_iou = current_iou;
+ truth_index = unique_truth_count + j;
+ }
+ }
+ }
+
+ // best IoU
+ if (truth_index > -1) {
+ detections[detections_count - 1].truth_flag = 1;
+ detections[detections_count - 1].unique_truth_index = truth_index;
+ }
+ else {
+ // if object is difficult then remove detection
+ for (j = 0; j < num_labels_dif; ++j) {
+ box t = { truth_dif[j].x, truth_dif[j].y, truth_dif[j].w, truth_dif[j].h };
+ float current_iou = box_iou(boxes[i], t);
+ if (current_iou > iou_thresh && class_id == truth_dif[j].id) {
+ --detections_count;
+ break;
+ }
+ }
+ }
+
+ // calc avg IoU, true-positives, false-positives for required Threshold
+ if (prob > thresh_calc_avg_iou) {
+ if (truth_index > -1) {
+ avg_iou += max_iou;
+ ++tp_for_thresh;
+ }
+ else
+ fp_for_thresh++;
+ }
+ }
+ }
+ }
+
+ unique_truth_count += num_labels;
+
+ free(id);
+ free_image(val[t]);
+ free_image(val_resized[t]);
+ }
+ }
+
+ avg_iou = avg_iou / (tp_for_thresh + fp_for_thresh);
+
+
+ // SORT(detections)
+ qsort(detections, detections_count, sizeof(box_prob), detections_comparator);
+
+ typedef struct {
+ double precision;
+ double recall;
+ int tp, fp, fn;
+ } pr_t;
+
+ // for PR-curve
+ pr_t **pr = calloc(classes, sizeof(pr_t*));
+ for (i = 0; i < classes; ++i) {
+ pr[i] = calloc(detections_count, sizeof(pr_t));
+ }
+ printf("detections_count = %d, unique_truth_count = %d \n", detections_count, unique_truth_count);
+
+
+ int *truth_flags = calloc(unique_truth_count, sizeof(int));
+
+ int rank;
+ for (rank = 0; rank < detections_count; ++rank) {
+ if(rank % 100 == 0)
+ printf(" rank = %d of ranks = %d \r", rank, detections_count);
+
+ if (rank > 0) {
+ int class_id;
+ for (class_id = 0; class_id < classes; ++class_id) {
+ pr[class_id][rank].tp = pr[class_id][rank - 1].tp;
+ pr[class_id][rank].fp = pr[class_id][rank - 1].fp;
+ }
+ }
+
+ box_prob d = detections[rank];
+ // if (detected && isn't detected before)
+ if (d.truth_flag == 1) {
+ if (truth_flags[d.unique_truth_index] == 0)
+ {
+ truth_flags[d.unique_truth_index] = 1;
+ pr[d.class_id][rank].tp++; // true-positive
+ }
+ }
+ else {
+ pr[d.class_id][rank].fp++; // false-positive
+ }
+
+ for (i = 0; i < classes; ++i)
+ {
+ const int tp = pr[i][rank].tp;
+ const int fp = pr[i][rank].fp;
+ const int fn = truth_classes_count[i] - tp; // false-negative = objects - true-positive
+ pr[i][rank].fn = fn;
+
+ if ((tp + fp) > 0) pr[i][rank].precision = (double)tp / (double)(tp + fp);
+ else pr[i][rank].precision = 0;
+
+ if ((tp + fn) > 0) pr[i][rank].recall = (double)tp / (double)(tp + fn);
+ else pr[i][rank].recall = 0;
+ }
+ }
+
+ free(truth_flags);
+
+
+ double mean_average_precision = 0;
+
+ for (i = 0; i < classes; ++i) {
+ double avg_precision = 0;
+ int point;
+ for (point = 0; point < 11; ++point) {
+ double cur_recall = point * 0.1;
+ double cur_precision = 0;
+ for (rank = 0; rank < detections_count; ++rank)
+ {
+ if (pr[i][rank].recall >= cur_recall) { // > or >=
+ if (pr[i][rank].precision > cur_precision) {
+ cur_precision = pr[i][rank].precision;
+ }
+ }
+ }
+ //printf("point = %d, cur_recall = %.4f, cur_precision = %.4f \n", point, cur_recall, cur_precision);
+
+ avg_precision += cur_precision;
+ }
+ avg_precision = avg_precision / 11;
+ printf("class = %d, name = %s, \t ap = %2.2f %% \n", i, names[i], avg_precision*100);
+ mean_average_precision += avg_precision;
+ }
+
+ printf(" for thresh = %0.2f, TP = %d, FP = %d, FN = %d, average IoU = %2.2f %% \n",
+ thresh_calc_avg_iou, tp_for_thresh, fp_for_thresh, unique_truth_count - tp_for_thresh, avg_iou * 100);
+
+ mean_average_precision = mean_average_precision / classes;
+ printf("\n mean average precision (mAP) = %f, or %2.2f %% \n", mean_average_precision, mean_average_precision*100);
+
+
+ for (i = 0; i < classes; ++i) {
+ free(pr[i]);
+ }
+ free(pr);
+ free(detections);
+ free(truth_classes_count);
+
+ fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
}
void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh)
@@ -456,7 +805,7 @@
char **names = get_labels(name_list);
image **alphabet = load_alphabet();
- network net = parse_network_cfg(cfgfile);
+ network net = parse_network_cfg_custom(cfgfile, 1);
if(weightfile){
load_weights(&net, weightfile);
}
@@ -470,6 +819,7 @@
while(1){
if(filename){
strncpy(input, filename, 256);
+ if (input[strlen(input) - 1] == 0x0d) input[strlen(input) - 1] = 0;
} else {
printf("Enter Image Path: ");
fflush(stdout);
@@ -509,6 +859,7 @@
void run_detector(int argc, char **argv)
{
+ 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", .24);
@@ -546,16 +897,21 @@
char *datacfg = argv[3];
char *cfg = argv[4];
char *weights = (argc > 5) ? argv[5] : 0;
+ if(weights)
+ if (weights[strlen(weights) - 1] == 0x0d) weights[strlen(weights) - 1] = 0;
char *filename = (argc > 6) ? argv[6]: 0;
if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh);
else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, gpus, ngpus, clear);
else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights);
else if(0==strcmp(argv[2], "recall")) validate_detector_recall(datacfg, cfg, weights);
+ else if(0==strcmp(argv[2], "map")) validate_detector_map(datacfg, cfg, weights);
else if(0==strcmp(argv[2], "demo")) {
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 20);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
- demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, out_filename);
+ if(filename)
+ if (filename[strlen(filename) - 1] == 0x0d) filename[strlen(filename) - 1] = 0;
+ demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, out_filename, http_stream_port);
}
}
--
Gitblit v1.10.0