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/classifier.c | 331 ++++++++++++++++++++++++++++--------------------------
1 files changed, 172 insertions(+), 159 deletions(-)
diff --git a/src/classifier.c b/src/classifier.c
index b42d010..e45f5a1 100644
--- a/src/classifier.c
+++ b/src/classifier.c
@@ -6,39 +6,22 @@
#include "assert.h"
#include "classifier.h"
#include "cuda.h"
+#ifdef WIN32
+#include <time.h>
+#include <winsock.h>
+#include "gettimeofday.h"
+#else
#include <sys/time.h>
+#endif
#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
+#include "opencv2/core/version.hpp"
+#ifndef CV_VERSION_EPOCH
+#include "opencv2/videoio/videoio_c.h"
#endif
-
-list *read_data_cfg(char *filename)
-{
- FILE *file = fopen(filename, "r");
- if(file == 0) file_error(filename);
- char *line;
- int nu = 0;
- list *options = make_list();
- while((line=fgetl(file)) != 0){
- ++ nu;
- strip(line);
- switch(line[0]){
- case '\0':
- case '#':
- case ';':
- free(line);
- break;
- default:
- if(!read_option(line, options)){
- fprintf(stderr, "Config file error line %d, could parse: %s\n", nu, line);
- free(line);
- }
- break;
- }
- }
- fclose(file);
- return options;
-}
+image get_image_from_stream(CvCapture *cap);
+#endif
float *get_regression_values(char **labels, int n)
{
@@ -52,30 +35,32 @@
return v;
}
-void train_classifier_multi(char *datacfg, char *cfgfile, char *weightfile, int *gpus, int ngpus, int clear)
+void train_classifier(char *datacfg, char *cfgfile, char *weightfile, int *gpus, int ngpus, int clear)
{
-#ifdef GPU
int i;
- srand(time(0));
float avg_loss = -1;
char *base = basecfg(cfgfile);
printf("%s\n", base);
printf("%d\n", ngpus);
network *nets = calloc(ngpus, sizeof(network));
+
+ srand(time(0));
+ int seed = rand();
for(i = 0; i < ngpus; ++i){
+ srand(seed);
+#ifdef GPU
cuda_set_device(gpus[i]);
+#endif
nets[i] = parse_network_cfg(cfgfile);
- if(clear) *nets[i].seen = 0;
if(weightfile){
load_weights(&nets[i], weightfile);
}
- }
- network net = nets[0];
- for(i = 0; i < ngpus; ++i){
- *nets[i].seen = *net.seen;
+ if(clear) *nets[i].seen = 0;
nets[i].learning_rate *= ngpus;
}
+ srand(time(0));
+ network net = nets[0];
int imgs = net.batch * net.subdivisions * ngpus;
@@ -97,10 +82,12 @@
load_args args = {0};
args.w = net.w;
args.h = net.h;
- args.threads = 16;
+ args.threads = 32;
+ args.hierarchy = net.hierarchy;
args.min = net.min_crop;
args.max = net.max_crop;
+ args.flip = net.flip;
args.angle = net.angle;
args.aspect = net.aspect;
args.exposure = net.exposure;
@@ -132,7 +119,16 @@
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
- float loss = train_networks(nets, ngpus, train, 4);
+ float loss = 0;
+#ifdef GPU
+ if(ngpus == 1){
+ loss = train_network(net, train);
+ } else {
+ loss = train_networks(nets, ngpus, train, 4);
+ }
+#else
+ loss = train_network(net, train);
+#endif
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
printf("%d, %.3f: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), (float)(*net.seen)/N, loss, avg_loss, get_current_rate(net), sec(clock()-time), *net.seen);
@@ -158,116 +154,119 @@
free_ptrs((void**)paths, plist->size);
free_list(plist);
free(base);
-#endif
}
-void train_classifier(char *datacfg, char *cfgfile, char *weightfile, int clear)
-{
- srand(time(0));
- float avg_loss = -1;
- char *base = basecfg(cfgfile);
- printf("%s\n", base);
- network net = parse_network_cfg(cfgfile);
- if(weightfile){
- load_weights(&net, weightfile);
- }
- if(clear) *net.seen = 0;
+/*
+ void train_classifier(char *datacfg, char *cfgfile, char *weightfile, int clear)
+ {
+ srand(time(0));
+ float avg_loss = -1;
+ char *base = basecfg(cfgfile);
+ printf("%s\n", base);
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ if(clear) *net.seen = 0;
- int imgs = net.batch * net.subdivisions;
+ int imgs = net.batch * net.subdivisions;
- printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- list *options = read_data_cfg(datacfg);
+ printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+ list *options = read_data_cfg(datacfg);
- char *backup_directory = option_find_str(options, "backup", "/backup/");
- char *label_list = option_find_str(options, "labels", "data/labels.list");
- char *train_list = option_find_str(options, "train", "data/train.list");
- int classes = option_find_int(options, "classes", 2);
+ char *backup_directory = option_find_str(options, "backup", "/backup/");
+ char *label_list = option_find_str(options, "labels", "data/labels.list");
+ char *train_list = option_find_str(options, "train", "data/train.list");
+ int classes = option_find_int(options, "classes", 2);
- char **labels = get_labels(label_list);
- list *plist = get_paths(train_list);
- char **paths = (char **)list_to_array(plist);
- printf("%d\n", plist->size);
- int N = plist->size;
- clock_t time;
+ char **labels = get_labels(label_list);
+ list *plist = get_paths(train_list);
+ char **paths = (char **)list_to_array(plist);
+ printf("%d\n", plist->size);
+ int N = plist->size;
+ clock_t time;
- load_args args = {0};
- args.w = net.w;
- args.h = net.h;
- args.threads = 8;
+ load_args args = {0};
+ args.w = net.w;
+ args.h = net.h;
+ args.threads = 8;
- args.min = net.min_crop;
- args.max = net.max_crop;
- args.angle = net.angle;
- args.aspect = net.aspect;
- args.exposure = net.exposure;
- args.saturation = net.saturation;
- args.hue = net.hue;
- args.size = net.w;
+ args.min = net.min_crop;
+ args.max = net.max_crop;
+ args.flip = net.flip;
+ args.angle = net.angle;
+ args.aspect = net.aspect;
+ args.exposure = net.exposure;
+ args.saturation = net.saturation;
+ args.hue = net.hue;
+ args.size = net.w;
+ args.hierarchy = net.hierarchy;
- args.paths = paths;
- args.classes = classes;
- args.n = imgs;
- args.m = N;
- args.labels = labels;
- args.type = CLASSIFICATION_DATA;
+ args.paths = paths;
+ args.classes = classes;
+ args.n = imgs;
+ args.m = N;
+ args.labels = labels;
+ args.type = CLASSIFICATION_DATA;
- data train;
- data buffer;
- pthread_t load_thread;
- args.d = &buffer;
- load_thread = load_data(args);
+ data train;
+ data buffer;
+ pthread_t load_thread;
+ args.d = &buffer;
+ load_thread = load_data(args);
- int epoch = (*net.seen)/N;
- while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
- time=clock();
+ int epoch = (*net.seen)/N;
+ while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
+ time=clock();
- pthread_join(load_thread, 0);
- train = buffer;
- load_thread = load_data(args);
+ pthread_join(load_thread, 0);
+ train = buffer;
+ load_thread = load_data(args);
- printf("Loaded: %lf seconds\n", sec(clock()-time));
- time=clock();
+ printf("Loaded: %lf seconds\n", sec(clock()-time));
+ time=clock();
#ifdef OPENCV
- if(0){
- int u;
- for(u = 0; u < imgs; ++u){
- image im = float_to_image(net.w, net.h, 3, train.X.vals[u]);
- show_image(im, "loaded");
- cvWaitKey(0);
- }
- }
+if(0){
+int u;
+for(u = 0; u < imgs; ++u){
+ image im = float_to_image(net.w, net.h, 3, train.X.vals[u]);
+ show_image(im, "loaded");
+ cvWaitKey(0);
+}
+}
#endif
- float loss = train_network(net, train);
- free_data(train);
+float loss = train_network(net, train);
+free_data(train);
- if(avg_loss == -1) avg_loss = loss;
- avg_loss = avg_loss*.9 + loss*.1;
- printf("%d, %.3f: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), (float)(*net.seen)/N, loss, avg_loss, get_current_rate(net), sec(clock()-time), *net.seen);
- if(*net.seen/N > epoch){
- epoch = *net.seen/N;
- char buff[256];
- sprintf(buff, "%s/%s_%d.weights",backup_directory,base, epoch);
- save_weights(net, buff);
- }
- if(get_current_batch(net)%100 == 0){
- char buff[256];
- sprintf(buff, "%s/%s.backup",backup_directory,base);
- save_weights(net, buff);
- }
- }
+if(avg_loss == -1) avg_loss = loss;
+avg_loss = avg_loss*.9 + loss*.1;
+printf("%d, %.3f: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), (float)(*net.seen)/N, loss, avg_loss, get_current_rate(net), sec(clock()-time), *net.seen);
+if(*net.seen/N > epoch){
+ epoch = *net.seen/N;
char buff[256];
- sprintf(buff, "%s/%s.weights", backup_directory, base);
+ sprintf(buff, "%s/%s_%d.weights",backup_directory,base, epoch);
save_weights(net, buff);
-
- free_network(net);
- free_ptrs((void**)labels, classes);
- free_ptrs((void**)paths, plist->size);
- free_list(plist);
- free(base);
}
+if(get_current_batch(net)%100 == 0){
+ char buff[256];
+ sprintf(buff, "%s/%s.backup",backup_directory,base);
+ save_weights(net, buff);
+}
+}
+char buff[256];
+sprintf(buff, "%s/%s.weights", backup_directory, base);
+save_weights(net, buff);
+
+free_network(net);
+free_ptrs((void**)labels, classes);
+free_ptrs((void**)paths, plist->size);
+free_list(plist);
+free(base);
+}
+*/
void validate_classifier_crop(char *datacfg, char *filename, char *weightfile)
{
@@ -365,11 +364,11 @@
int *indexes = calloc(topk, sizeof(int));
for(i = 0; i < m; ++i){
- int class = -1;
+ int class_id = -1;
char *path = paths[i];
for(j = 0; j < classes; ++j){
if(strstr(path, labels[j])){
- class = j;
+ class_id = j;
break;
}
}
@@ -392,15 +391,16 @@
float *pred = calloc(classes, sizeof(float));
for(j = 0; j < 10; ++j){
float *p = network_predict(net, images[j].data);
+ if(net.hierarchy) hierarchy_predictions(p, net.outputs, net.hierarchy, 1);
axpy_cpu(classes, 1, p, 1, pred, 1);
free_image(images[j]);
}
free_image(im);
top_k(pred, classes, topk, indexes);
free(pred);
- if(indexes[0] == class) avg_acc += 1;
+ if(indexes[0] == class_id) avg_acc += 1;
for(j = 0; j < topk; ++j){
- if(indexes[j] == class) avg_topk += 1;
+ if(indexes[j] == class_id) avg_topk += 1;
}
printf("%d: top 1: %f, top %d: %f\n", i, avg_acc/(i+1), topk, avg_topk/(i+1));
@@ -437,11 +437,11 @@
int size = net.w;
for(i = 0; i < m; ++i){
- int class = -1;
+ int class_id = -1;
char *path = paths[i];
for(j = 0; j < classes; ++j){
if(strstr(path, labels[j])){
- class = j;
+ class_id = j;
break;
}
}
@@ -452,14 +452,15 @@
//show_image(crop, "cropped");
//cvWaitKey(0);
float *pred = network_predict(net, resized.data);
+ if(net.hierarchy) hierarchy_predictions(pred, net.outputs, net.hierarchy, 1);
free_image(im);
free_image(resized);
top_k(pred, classes, topk, indexes);
- if(indexes[0] == class) avg_acc += 1;
+ if(indexes[0] == class_id) avg_acc += 1;
for(j = 0; j < topk; ++j){
- if(indexes[j] == class) avg_topk += 1;
+ if(indexes[j] == class_id) avg_topk += 1;
}
printf("%d: top 1: %f, top %d: %f\n", i, avg_acc/(i+1), topk, avg_topk/(i+1));
@@ -480,6 +481,8 @@
list *options = read_data_cfg(datacfg);
char *label_list = option_find_str(options, "labels", "data/labels.list");
+ char *leaf_list = option_find_str(options, "leaves", 0);
+ if(leaf_list) change_leaves(net.hierarchy, leaf_list);
char *valid_list = option_find_str(options, "valid", "data/train.list");
int classes = option_find_int(options, "classes", 2);
int topk = option_find_int(options, "top", 1);
@@ -496,11 +499,11 @@
int *indexes = calloc(topk, sizeof(int));
for(i = 0; i < m; ++i){
- int class = -1;
+ int class_id = -1;
char *path = paths[i];
for(j = 0; j < classes; ++j){
if(strstr(path, labels[j])){
- class = j;
+ class_id = j;
break;
}
}
@@ -511,15 +514,16 @@
//show_image(crop, "cropped");
//cvWaitKey(0);
float *pred = network_predict(net, crop.data);
+ if(net.hierarchy) hierarchy_predictions(pred, net.outputs, net.hierarchy, 1);
if(resized.data != im.data) free_image(resized);
free_image(im);
free_image(crop);
top_k(pred, classes, topk, indexes);
- if(indexes[0] == class) avg_acc += 1;
+ if(indexes[0] == class_id) avg_acc += 1;
for(j = 0; j < topk; ++j){
- if(indexes[j] == class) avg_topk += 1;
+ if(indexes[j] == class_id) avg_topk += 1;
}
printf("%d: top 1: %f, top %d: %f\n", i, avg_acc/(i+1), topk, avg_topk/(i+1));
@@ -557,11 +561,11 @@
int *indexes = calloc(topk, sizeof(int));
for(i = 0; i < m; ++i){
- int class = -1;
+ int class_id = -1;
char *path = paths[i];
for(j = 0; j < classes; ++j){
if(strstr(path, labels[j])){
- class = j;
+ class_id = j;
break;
}
}
@@ -571,6 +575,7 @@
image r = resize_min(im, scales[j]);
resize_network(&net, r.w, r.h);
float *p = network_predict(net, r.data);
+ if(net.hierarchy) hierarchy_predictions(p, net.outputs, net.hierarchy, 1);
axpy_cpu(classes, 1, p, 1, pred, 1);
flip_image(r);
p = network_predict(net, r.data);
@@ -580,9 +585,9 @@
free_image(im);
top_k(pred, classes, topk, indexes);
free(pred);
- if(indexes[0] == class) avg_acc += 1;
+ if(indexes[0] == class_id) avg_acc += 1;
for(j = 0; j < topk; ++j){
- if(indexes[j] == class) avg_topk += 1;
+ if(indexes[j] == class_id) avg_topk += 1;
}
printf("%d: top 1: %f, top %d: %f\n", i, avg_acc/(i+1), topk, avg_topk/(i+1));
@@ -670,8 +675,7 @@
}
}
-
-void predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename)
+void predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename, int top)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
@@ -684,7 +688,7 @@
char *name_list = option_find_str(options, "names", 0);
if(!name_list) name_list = option_find_str(options, "labels", "data/labels.list");
- int top = option_find_int(options, "top", 1);
+ if(top == 0) top = option_find_int(options, "top", 1);
int i = 0;
char **names = get_labels(name_list);
@@ -704,18 +708,21 @@
strtok(input, "\n");
}
image im = load_image_color(input, 0, 0);
- image r = resize_min(im, size);
- resize_network(&net, r.w, r.h);
+ image r = letterbox_image(im, net.w, net.h);
+ //image r = resize_min(im, size);
+ //resize_network(&net, r.w, r.h);
printf("%d %d\n", r.w, r.h);
float *X = r.data;
time=clock();
float *predictions = network_predict(net, X);
- top_predictions(net, top, indexes);
+ if(net.hierarchy) hierarchy_predictions(predictions, net.outputs, net.hierarchy, 0);
+ top_k(predictions, net.outputs, top, indexes);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
for(i = 0; i < top; ++i){
int index = indexes[i];
- printf("%s: %f\n", names[index], predictions[index]);
+ if(net.hierarchy) printf("%d, %s: %f, parent: %s \n",index, names[index], predictions[index], (net.hierarchy->parent[index] >= 0) ? names[net.hierarchy->parent[index]] : "Root");
+ else printf("%s: %f\n",names[index], predictions[index]);
}
if(r.data != im.data) free_image(r);
free_image(im);
@@ -897,15 +904,15 @@
float curr_threat = 0;
if(1){
curr_threat = predictions[0] * 0 +
- predictions[1] * .6 +
- predictions[2];
+ predictions[1] * .6 +
+ predictions[2];
} else {
curr_threat = predictions[218] +
- predictions[539] +
- predictions[540] +
- predictions[368] +
- predictions[369] +
- predictions[370];
+ predictions[539] +
+ predictions[540] +
+ predictions[368] +
+ predictions[369] +
+ predictions[370];
}
threat = roll * curr_threat + (1-roll) * threat;
@@ -1090,6 +1097,7 @@
show_image(in, "Classifier");
float *predictions = network_predict(net, in_s.data);
+ if(net.hierarchy) hierarchy_predictions(predictions, net.outputs, net.hierarchy, 1);
top_predictions(net, top, indexes);
printf("\033[2J");
@@ -1124,6 +1132,7 @@
char *gpu_list = find_char_arg(argc, argv, "-gpus", 0);
int *gpus = 0;
+ int gpu = 0;
int ngpus = 0;
if(gpu_list){
printf("%s\n", gpu_list);
@@ -1138,9 +1147,14 @@
gpus[i] = atoi(gpu_list);
gpu_list = strchr(gpu_list, ',')+1;
}
+ } else {
+ gpu = gpu_index;
+ gpus = &gpu;
+ ngpus = 1;
}
int cam_index = find_int_arg(argc, argv, "-c", 0);
+ int top = find_int_arg(argc, argv, "-t", 0);
int clear = find_arg(argc, argv, "-clear");
char *data = argv[3];
char *cfg = argv[4];
@@ -1148,10 +1162,9 @@
char *filename = (argc > 6) ? argv[6]: 0;
char *layer_s = (argc > 7) ? argv[7]: 0;
int layer = layer_s ? atoi(layer_s) : -1;
- if(0==strcmp(argv[2], "predict")) predict_classifier(data, cfg, weights, filename);
+ if(0==strcmp(argv[2], "predict")) predict_classifier(data, cfg, weights, filename, top);
else if(0==strcmp(argv[2], "try")) try_classifier(data, cfg, weights, filename, atoi(layer_s));
- else if(0==strcmp(argv[2], "train")) train_classifier(data, cfg, weights, clear);
- else if(0==strcmp(argv[2], "trainm")) train_classifier_multi(data, cfg, weights, gpus, ngpus, clear);
+ else if(0==strcmp(argv[2], "train")) train_classifier(data, cfg, weights, gpus, ngpus, clear);
else if(0==strcmp(argv[2], "demo")) demo_classifier(data, cfg, weights, cam_index, filename);
else if(0==strcmp(argv[2], "gun")) gun_classifier(data, cfg, weights, cam_index, filename);
else if(0==strcmp(argv[2], "threat")) threat_classifier(data, cfg, weights, cam_index, filename);
--
Gitblit v1.10.0