From 168af40fe9a3cc81c6ee16b3e81f154780c36bdb Mon Sep 17 00:00:00 2001
From: Scheaven <xuepengqiang>
Date: 星期四, 03 六月 2021 15:03:27 +0800
Subject: [PATCH] up new v4
---
lib/detecter_tools/darknet/yolo.c | 736 ++++++++++++++++++++++++++++----------------------------
1 files changed, 368 insertions(+), 368 deletions(-)
diff --git a/lib/detecter_tools/darknet/yolo.c b/lib/detecter_tools/darknet/yolo.c
index 739e3a2..384c487 100644
--- a/lib/detecter_tools/darknet/yolo.c
+++ b/lib/detecter_tools/darknet/yolo.c
@@ -1,368 +1,368 @@
-#include "network.h"
-#include "detection_layer.h"
-#include "cost_layer.h"
-#include "utils.h"
-#include "parser.h"
-#include "box.h"
-#include "demo.h"
-
-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 = "data/voc/train.txt";
- char* backup_directory = "backup/";
- srand(time(0));
- char *base = basecfg(cfgfile);
- printf("%s\n", base);
- float avg_loss = -1;
- network net = parse_network_cfg(cfgfile);
- if(weightfile){
- load_weights(&net, weightfile);
- }
- printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- int imgs = net.batch*net.subdivisions;
- int i = *net.seen/imgs;
- data train, buffer;
-
-
- 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;
- args.h = net.h;
- args.paths = paths;
- args.n = imgs;
- args.m = plist->size;
- args.classes = classes;
- args.jitter = jitter;
- args.num_boxes = side;
- 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){
- while(get_current_batch(net) < net.max_batches){
- i += 1;
- time=clock();
- pthread_join(load_thread, 0);
- train = buffer;
- 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, %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);
- }
- free_data(train);
- }
- char buff[256];
- sprintf(buff, "%s/%s_final.weights", backup_directory, base);
- save_weights(net, buff);
-}
-
-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 < 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.;
- float ymax = boxes[i].y + boxes[i].h/2.;
-
- if (xmin < 0) xmin = 0;
- if (ymin < 0) ymin = 0;
- if (xmax > w) xmax = w;
- if (ymax > h) ymax = h;
-
- for(j = 0; j < classes; ++j){
- if (probs[i][j]) fprintf(fps[j], "%s %f %f %f %f %f\n", id, probs[i][j],
- xmin, ymin, xmax, ymax);
- }
- }
-}
-
-void validate_yolo(char *cfgfile, char *weightfile)
-{
- network net = parse_network_cfg(cfgfile);
- 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));
-
- char *base = "results/comp4_det_test_";
- //list *plist = get_paths("data/voc.2007.test");
- list* plist = get_paths("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 j;
- FILE** fps = (FILE**)xcalloc(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 = (box*)xcalloc(l.side * l.side * l.n, sizeof(box));
- float** probs = (float**)xcalloc(l.side * l.side * l.n, sizeof(float*));
- for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = (float*)xcalloc(classes, sizeof(float));
-
- int m = plist->size;
- int i=0;
- int t;
-
- float thresh = .001;
- int nms = 1;
- float iou_thresh = .5;
-
- int nthreads = 8;
- image* val = (image*)xcalloc(nthreads, sizeof(image));
- image* val_resized = (image*)xcalloc(nthreads, sizeof(image));
- image* buf = (image*)xcalloc(nthreads, sizeof(image));
- image* buf_resized = (image*)xcalloc(nthreads, sizeof(image));
- pthread_t* thr = (pthread_t*)xcalloc(nthreads, sizeof(pthread_t));
-
- load_args args = {0};
- args.w = net.w;
- args.h = net.h;
- args.type = IMAGE_DATA;
-
- 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){
- char *path = paths[i+t-nthreads];
- char *id = basecfg(path);
- float *X = val_resized[t].data;
- network_predict(net, X);
- int w = val[t].w;
- int h = val[t].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]);
- }
- }
-
- if (fps) free(fps);
- if (val) free(val);
- if (val_resized) free(val_resized);
- if (buf) free(buf);
- if (buf_resized) free(buf_resized);
- if (thr) free(thr);
-
- fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
- for(j = 0; j < classes; ++j){
- fclose(fps[j]);
- }
- free(fps);
-}
-
-void validate_yolo_recall(char *cfgfile, char *weightfile)
-{
- network net = parse_network_cfg(cfgfile);
- 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("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;
- box* boxes = (box*)xcalloc(side * side * l.n, sizeof(box));
- float** probs = (float**)xcalloc(side * side * l.n, sizeof(float*));
- for(j = 0; j < side*side*l.n; ++j) {
- probs[j] = (float*)xcalloc(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];
- replace_image_to_label(path, 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);
- char buff[256];
- char *input = buff;
- int j;
- float nms=.4;
- box* boxes = (box*)xcalloc(l.side * l.side * l.n, sizeof(box));
- float** probs = (float**)xcalloc(l.side * l.side * l.n, sizeof(float*));
- for(j = 0; j < l.side*l.side*l.n; ++j) {
- probs[j] = (float*)xcalloc(l.classes, sizeof(float));
- }
- while(1){
- if(filename){
- strncpy(input, filename, 256);
- } else {
- printf("Enter Image Path: ");
- fflush(stdout);
- 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;
- clock_t time=clock();
- network_predict(net, X);
- printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
- 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);
-
- wait_until_press_key_cv();
- destroy_all_windows_cv();
-
- if (filename) break;
- }
- free(boxes);
- for(j = 0; j < l.side*l.side*l.n; ++j) {
- free(probs[j]);
- }
- free(probs);
-}
-
-void run_yolo(int argc, char **argv)
-{
- int dont_show = find_arg(argc, argv, "-dont_show");
- int mjpeg_port = find_int_arg(argc, argv, "-mjpeg_port", -1);
- int json_port = find_int_arg(argc, argv, "-json_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);
- int ext_output = find_arg(argc, argv, "-ext_output");
- if(argc < 4){
- fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
- return;
- }
-
- char *cfg = argv[3];
- char *weights = (argc > 4) ? argv[4] : 0;
- char *filename = (argc > 5) ? argv[5]: 0;
- 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, mjpeg_port, 0, json_port, dont_show, ext_output, 0, 0, 0, 0, 0);
-}
+#include "network.h"
+#include "detection_layer.h"
+#include "cost_layer.h"
+#include "utils.h"
+#include "parser.h"
+#include "box.h"
+#include "demo.h"
+
+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 = "data/voc/train.txt";
+ char* backup_directory = "backup/";
+ srand(time(0));
+ char *base = basecfg(cfgfile);
+ printf("%s\n", base);
+ float avg_loss = -1;
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+ int imgs = net.batch*net.subdivisions;
+ int i = *net.seen/imgs;
+ data train, buffer;
+
+
+ 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;
+ args.h = net.h;
+ args.paths = paths;
+ args.n = imgs;
+ args.m = plist->size;
+ args.classes = classes;
+ args.jitter = jitter;
+ args.num_boxes = side;
+ 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){
+ while(get_current_batch(net) < net.max_batches){
+ i += 1;
+ time=clock();
+ pthread_join(load_thread, 0);
+ train = buffer;
+ 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, %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);
+ }
+ free_data(train);
+ }
+ char buff[256];
+ sprintf(buff, "%s/%s_final.weights", backup_directory, base);
+ save_weights(net, buff);
+}
+
+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 < 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.;
+ float ymax = boxes[i].y + boxes[i].h/2.;
+
+ if (xmin < 0) xmin = 0;
+ if (ymin < 0) ymin = 0;
+ if (xmax > w) xmax = w;
+ if (ymax > h) ymax = h;
+
+ for(j = 0; j < classes; ++j){
+ if (probs[i][j]) fprintf(fps[j], "%s %f %f %f %f %f\n", id, probs[i][j],
+ xmin, ymin, xmax, ymax);
+ }
+ }
+}
+
+void validate_yolo(char *cfgfile, char *weightfile)
+{
+ network net = parse_network_cfg(cfgfile);
+ 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));
+
+ char *base = "results/comp4_det_test_";
+ //list *plist = get_paths("data/voc.2007.test");
+ list* plist = get_paths("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 j;
+ FILE** fps = (FILE**)xcalloc(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 = (box*)xcalloc(l.side * l.side * l.n, sizeof(box));
+ float** probs = (float**)xcalloc(l.side * l.side * l.n, sizeof(float*));
+ for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = (float*)xcalloc(classes, sizeof(float));
+
+ int m = plist->size;
+ int i=0;
+ int t;
+
+ float thresh = .001;
+ int nms = 1;
+ float iou_thresh = .5;
+
+ int nthreads = 8;
+ image* val = (image*)xcalloc(nthreads, sizeof(image));
+ image* val_resized = (image*)xcalloc(nthreads, sizeof(image));
+ image* buf = (image*)xcalloc(nthreads, sizeof(image));
+ image* buf_resized = (image*)xcalloc(nthreads, sizeof(image));
+ pthread_t* thr = (pthread_t*)xcalloc(nthreads, sizeof(pthread_t));
+
+ load_args args = {0};
+ args.w = net.w;
+ args.h = net.h;
+ args.type = IMAGE_DATA;
+
+ 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){
+ char *path = paths[i+t-nthreads];
+ char *id = basecfg(path);
+ float *X = val_resized[t].data;
+ network_predict(net, X);
+ int w = val[t].w;
+ int h = val[t].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]);
+ }
+ }
+
+ if (fps) free(fps);
+ if (val) free(val);
+ if (val_resized) free(val_resized);
+ if (buf) free(buf);
+ if (buf_resized) free(buf_resized);
+ if (thr) free(thr);
+
+ fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
+ for(j = 0; j < classes; ++j){
+ fclose(fps[j]);
+ }
+ free(fps);
+}
+
+void validate_yolo_recall(char *cfgfile, char *weightfile)
+{
+ network net = parse_network_cfg(cfgfile);
+ 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("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;
+ box* boxes = (box*)xcalloc(side * side * l.n, sizeof(box));
+ float** probs = (float**)xcalloc(side * side * l.n, sizeof(float*));
+ for(j = 0; j < side*side*l.n; ++j) {
+ probs[j] = (float*)xcalloc(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];
+ replace_image_to_label(path, 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);
+ char buff[256];
+ char *input = buff;
+ int j;
+ float nms=.4;
+ box* boxes = (box*)xcalloc(l.side * l.side * l.n, sizeof(box));
+ float** probs = (float**)xcalloc(l.side * l.side * l.n, sizeof(float*));
+ for(j = 0; j < l.side*l.side*l.n; ++j) {
+ probs[j] = (float*)xcalloc(l.classes, sizeof(float));
+ }
+ while(1){
+ if(filename){
+ strncpy(input, filename, 256);
+ } else {
+ printf("Enter Image Path: ");
+ fflush(stdout);
+ 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;
+ clock_t time=clock();
+ network_predict(net, X);
+ printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
+ 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);
+
+ wait_until_press_key_cv();
+ destroy_all_windows_cv();
+
+ if (filename) break;
+ }
+ free(boxes);
+ for(j = 0; j < l.side*l.side*l.n; ++j) {
+ free(probs[j]);
+ }
+ free(probs);
+}
+
+void run_yolo(int argc, char **argv)
+{
+ int dont_show = find_arg(argc, argv, "-dont_show");
+ int mjpeg_port = find_int_arg(argc, argv, "-mjpeg_port", -1);
+ int json_port = find_int_arg(argc, argv, "-json_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);
+ int ext_output = find_arg(argc, argv, "-ext_output");
+ if(argc < 4){
+ fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
+ return;
+ }
+
+ char *cfg = argv[3];
+ char *weights = (argc > 4) ? argv[4] : 0;
+ char *filename = (argc > 5) ? argv[5]: 0;
+ 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, 1, frame_skip,
+ prefix, out_filename, mjpeg_port, 0, json_port, dont_show, ext_output, 0, 0, 0, 0, 0);
+}
--
Gitblit v1.8.0