From ae43c2bc32fbb838bfebeeaf2c2b058ccab5c83c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@burninator.cs.washington.edu>
Date: Thu, 23 Jun 2016 05:31:14 +0000
Subject: [PATCH] hi
---
src/classifier.c | 179 +++++++++++++++++++++++++++++++++++++++++++++++++----------
1 files changed, 147 insertions(+), 32 deletions(-)
diff --git a/src/classifier.c b/src/classifier.c
index fdbe534..2d0d0e0 100644
--- a/src/classifier.c
+++ b/src/classifier.c
@@ -3,6 +3,8 @@
#include "parser.h"
#include "option_list.h"
#include "blas.h"
+#include "classifier.h"
+#include <sys/time.h>
#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
@@ -36,7 +38,7 @@
return options;
}
-void train_classifier(char *datacfg, char *cfgfile, char *weightfile)
+void train_classifier(char *datacfg, char *cfgfile, char *weightfile, int clear)
{
data_seed = time(0);
srand(time(0));
@@ -47,8 +49,9 @@
if(weightfile){
load_weights(&net, weightfile);
}
+ if(clear) *net.seen = 0;
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- int imgs = 1024;
+ int imgs = net.batch*net.subdivisions;
list *options = read_data_cfg(datacfg);
@@ -71,7 +74,7 @@
args.w = net.w;
args.h = net.h;
- args.min = net.w;
+ args.min = net.min_crop;
args.max = net.max_crop;
args.size = net.w;
@@ -94,14 +97,14 @@
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
-/*
- int u;
- for(u = 0; u < net.batch; ++u){
- image im = float_to_image(net.w, net.h, 3, train.X.vals[u]);
- show_image(im, "loaded");
- cvWaitKey(0);
- }
- */
+ /*
+ int u;
+ for(u = 0; u < net.batch; ++u){
+ image im = float_to_image(net.w, net.h, 3, train.X.vals[u]);
+ show_image(im, "loaded");
+ cvWaitKey(0);
+ }
+ */
float loss = train_network(net, train);
if(avg_loss == -1) avg_loss = loss;
@@ -114,7 +117,7 @@
sprintf(buff, "%s/%s_%d.weights",backup_directory,base, epoch);
save_weights(net, buff);
}
- if(*net.seen%100 == 0){
+ if(get_current_batch(net)%100 == 0){
char buff[256];
sprintf(buff, "%s/%s.backup",backup_directory,base);
save_weights(net, buff);
@@ -239,8 +242,8 @@
}
int w = net.w;
int h = net.h;
- image im = load_image_color(paths[i], w, h);
int shift = 32;
+ image im = load_image_color(paths[i], w+shift, h+shift);
image images[10];
images[0] = crop_image(im, -shift, -shift, w, h);
images[1] = crop_image(im, shift, -shift, w, h);
@@ -299,6 +302,7 @@
float avg_topk = 0;
int *indexes = calloc(topk, sizeof(int));
+ int size = net.w;
for(i = 0; i < m; ++i){
int class = -1;
char *path = paths[i];
@@ -309,13 +313,15 @@
}
}
image im = load_image_color(paths[i], 0, 0);
- resize_network(&net, im.w, im.h);
+ image resized = resize_min(im, size);
+ resize_network(&net, resized.w, resized.h);
//show_image(im, "orig");
//show_image(crop, "cropped");
//cvWaitKey(0);
- float *pred = network_predict(net, im.data);
+ float *pred = network_predict(net, resized.data);
free_image(im);
+ free_image(resized);
top_k(pred, classes, topk, indexes);
if(indexes[0] == class) avg_acc += 1;
@@ -332,10 +338,10 @@
{
int i, j;
network net = parse_network_cfg(filename);
- set_batch_network(&net, 1);
if(weightfile){
load_weights(&net, weightfile);
}
+ set_batch_network(&net, 1);
srand(time(0));
list *options = read_data_cfg(datacfg);
@@ -373,8 +379,8 @@
//cvWaitKey(0);
float *pred = network_predict(net, crop.data);
+ if(resized.data != im.data) free_image(resized);
free_image(im);
- free_image(resized);
free_image(crop);
top_k(pred, classes, topk, indexes);
@@ -406,7 +412,7 @@
char **labels = get_labels(label_list);
list *plist = get_paths(valid_list);
- int scales[] = {224, 256, 384, 480, 512};
+ int scales[] = {192, 224, 288, 320, 352};
int nscales = sizeof(scales)/sizeof(scales[0]);
char **paths = (char **)list_to_array(plist);
@@ -429,22 +435,14 @@
float *pred = calloc(classes, sizeof(float));
image im = load_image_color(paths[i], 0, 0);
for(j = 0; j < nscales; ++j){
- int w, h;
- if(im.w < im.h){
- w = scales[j];
- h = (im.h*w)/im.w;
- } else {
- h = scales[j];
- w = (im.w * h) / im.h;
- }
- resize_network(&net, w, h);
- image r = resize_image(im, w, h);
+ image r = resize_min(im, scales[j]);
+ resize_network(&net, r.w, r.h);
float *p = network_predict(net, r.data);
axpy_cpu(classes, 1, p, 1, pred, 1);
flip_image(r);
p = network_predict(net, r.data);
axpy_cpu(classes, 1, p, 1, pred, 1);
- free_image(r);
+ if(r.data != im.data) free_image(r);
}
free_image(im);
top_k(pred, classes, topk, indexes);
@@ -479,6 +477,7 @@
int *indexes = calloc(top, sizeof(int));
char buff[256];
char *input = buff;
+ int size = net.w;
while(1){
if(filename){
strncpy(input, filename, 256);
@@ -489,8 +488,12 @@
if(!input) return;
strtok(input, "\n");
}
- image im = load_image_color(input, net.w, net.h);
- float *X = im.data;
+ image im = load_image_color(input, 0, 0);
+ 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);
@@ -499,11 +502,52 @@
int index = indexes[i];
printf("%s: %f\n", names[index], predictions[index]);
}
+ if(r.data != im.data) free_image(r);
free_image(im);
if (filename) break;
}
}
+
+void label_classifier(char *datacfg, char *filename, char *weightfile)
+{
+ int i;
+ network net = parse_network_cfg(filename);
+ set_batch_network(&net, 1);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ srand(time(0));
+
+ list *options = read_data_cfg(datacfg);
+
+ char *label_list = option_find_str(options, "names", "data/labels.list");
+ char *test_list = option_find_str(options, "test", "data/train.list");
+ int classes = option_find_int(options, "classes", 2);
+
+ char **labels = get_labels(label_list);
+ list *plist = get_paths(test_list);
+
+ char **paths = (char **)list_to_array(plist);
+ int m = plist->size;
+ free_list(plist);
+
+ for(i = 0; i < m; ++i){
+ image im = load_image_color(paths[i], 0, 0);
+ image resized = resize_min(im, net.w);
+ image crop = crop_image(resized, (resized.w - net.w)/2, (resized.h - net.h)/2, net.w, net.h);
+ float *pred = network_predict(net, crop.data);
+
+ if(resized.data != im.data) free_image(resized);
+ free_image(im);
+ free_image(crop);
+ int ind = max_index(pred, classes);
+
+ printf("%s\n", labels[ind]);
+ }
+}
+
+
void test_classifier(char *datacfg, char *cfgfile, char *weightfile, int target_layer)
{
int curr = 0;
@@ -577,6 +621,73 @@
}
+void demo_classifier(char *datacfg, char *cfgfile, char *weightfile, int cam_index, const char *filename)
+{
+#ifdef OPENCV
+ printf("Classifier Demo\n");
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ set_batch_network(&net, 1);
+ list *options = read_data_cfg(datacfg);
+
+ srand(2222222);
+ CvCapture * cap;
+
+ if(filename){
+ cap = cvCaptureFromFile(filename);
+ }else{
+ cap = cvCaptureFromCAM(cam_index);
+ }
+
+ int top = option_find_int(options, "top", 1);
+
+ char *name_list = option_find_str(options, "names", 0);
+ char **names = get_labels(name_list);
+
+ int *indexes = calloc(top, sizeof(int));
+
+ if(!cap) error("Couldn't connect to webcam.\n");
+ cvNamedWindow("Classifier", CV_WINDOW_NORMAL);
+ cvResizeWindow("Classifier", 512, 512);
+ float fps = 0;
+ int i;
+
+ while(1){
+ struct timeval tval_before, tval_after, tval_result;
+ gettimeofday(&tval_before, NULL);
+
+ image in = get_image_from_stream(cap);
+ image in_s = resize_image(in, net.w, net.h);
+ show_image(in, "Classifier");
+
+ float *predictions = network_predict(net, in_s.data);
+ top_predictions(net, top, indexes);
+
+ printf("\033[2J");
+ printf("\033[1;1H");
+ printf("\nFPS:%.0f\n",fps);
+
+ for(i = 0; i < top; ++i){
+ int index = indexes[i];
+ printf("%.1f%%: %s\n", predictions[index]*100, names[index]);
+ }
+
+ free_image(in_s);
+ free_image(in);
+
+ cvWaitKey(10);
+
+ gettimeofday(&tval_after, NULL);
+ timersub(&tval_after, &tval_before, &tval_result);
+ float curr = 1000000.f/((long int)tval_result.tv_usec);
+ fps = .9*fps + .1*curr;
+ }
+#endif
+}
+
+
void run_classifier(int argc, char **argv)
{
if(argc < 4){
@@ -584,6 +695,8 @@
return;
}
+ int cam_index = find_int_arg(argc, argv, "-c", 0);
+ int clear = find_arg(argc, argv, "-clear");
char *data = argv[3];
char *cfg = argv[4];
char *weights = (argc > 5) ? argv[5] : 0;
@@ -591,8 +704,10 @@
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);
- else if(0==strcmp(argv[2], "train")) train_classifier(data, cfg, weights);
+ else if(0==strcmp(argv[2], "train")) train_classifier(data, cfg, weights, clear);
+ else if(0==strcmp(argv[2], "demo")) demo_classifier(data, cfg, weights, cam_index, filename);
else if(0==strcmp(argv[2], "test")) test_classifier(data, cfg, weights, layer);
+ else if(0==strcmp(argv[2], "label")) label_classifier(data, cfg, weights);
else if(0==strcmp(argv[2], "valid")) validate_classifier(data, cfg, weights);
else if(0==strcmp(argv[2], "valid10")) validate_classifier_10(data, cfg, weights);
else if(0==strcmp(argv[2], "validmulti")) validate_classifier_multi(data, cfg, weights);
--
Gitblit v1.10.0