From 28d5a4a913b662172c03985e57bbd4ecc5e00c73 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sun, 31 May 2015 20:49:50 +0000
Subject: [PATCH] more detection stuff
---
src/detection.c | 144 +++++++++++++++++++++++++++++++++++++++--------
1 files changed, 118 insertions(+), 26 deletions(-)
diff --git a/src/detection.c b/src/detection.c
index dafecec..0dbedb1 100644
--- a/src/detection.c
+++ b/src/detection.c
@@ -21,7 +21,7 @@
//printf("%d\n", j);
//printf("Prob: %f\n", box[j]);
int class = max_index(box+j, classes);
- if(box[j+class] > .4){
+ if(box[j+class] > .05){
//int z;
//for(z = 0; z < classes; ++z) printf("%f %s\n", box[j+z], class_names[z]);
printf("%f %s\n", box[j+class], class_names[class]);
@@ -47,6 +47,8 @@
int top = (y-h/2)*im.h;
int bot = (y+h/2)*im.h;
draw_box(im, left, top, right, bot, red, green, blue);
+ draw_box(im, left+1, top+1, right+1, bot+1, red, green, blue);
+ draw_box(im, left-1, top-1, right-1, bot-1, red, green, blue);
}
}
}
@@ -115,7 +117,12 @@
time=clock();
float loss = train_network(net, train);
+ //TODO
+ #ifdef GPU
float *out = get_network_output_gpu(net);
+ #else
+ float *out = get_network_output(net);
+ #endif
image im = float_to_image(net.w, net.h, 3, train.X.vals[127]);
image copy = copy_image(im);
draw_localization(copy, &(out[63*80]));
@@ -149,7 +156,7 @@
if(weightfile){
load_weights(&net, weightfile);
}
- detection_layer *layer = get_network_detection_layer(net);
+ detection_layer layer = get_network_detection_layer(net);
net.learning_rate = 0;
net.decay = 0;
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
@@ -157,9 +164,9 @@
int i = net.seen/imgs;
data train, buffer;
- int classes = layer->classes;
- int background = layer->background;
- int side = sqrt(get_detection_layer_locations(*layer));
+ int classes = layer.classes;
+ int background = layer.background;
+ int side = sqrt(get_detection_layer_locations(layer));
char **paths;
list *plist;
@@ -174,7 +181,7 @@
paths = (char **)list_to_array(plist);
pthread_t load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, net.w, net.h, side, side, background, &buffer);
clock_t time;
- cost_layer clayer = *((cost_layer *)net.layers[net.n-1]);
+ cost_layer clayer = net.layers[net.n-1];
while(1){
i += 1;
time=clock();
@@ -212,7 +219,7 @@
avg_loss = avg_loss*.9 + loss*.1;
printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), i*imgs);
if(i == 100){
- net.learning_rate *= 10;
+ //net.learning_rate *= 10;
}
if(i%100==0){
char buff[256];
@@ -235,23 +242,23 @@
if(weightfile){
load_weights(&net, weightfile);
}
- detection_layer *layer = get_network_detection_layer(net);
+ 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 i = net.seen/imgs;
data train, buffer;
- int classes = layer->classes;
- int background = layer->background;
- int side = sqrt(get_detection_layer_locations(*layer));
+ int classes = layer.classes;
+ int background = layer.background;
+ int side = sqrt(get_detection_layer_locations(layer));
char **paths;
list *plist;
if (imgnet){
plist = get_paths("/home/pjreddie/data/imagenet/det.train.list");
}else{
- plist = get_paths("/home/pjreddie/data/voc/no_2012_val.txt");
- //plist = get_paths("/home/pjreddie/data/voc/no_2007_test.txt");
+ //plist = get_paths("/home/pjreddie/data/voc/no_2012_val.txt");
+ plist = get_paths("/home/pjreddie/data/voc/no_2007_test.txt");
//plist = get_paths("/home/pjreddie/data/coco/trainval.txt");
//plist = get_paths("/home/pjreddie/data/voc/all2007-2012.txt");
}
@@ -282,7 +289,7 @@
if(i == 100){
net.learning_rate *= 10;
}
- if(i%100==0){
+ if(i%1000==0){
char buff[256];
sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
save_weights(net, buff);
@@ -325,21 +332,21 @@
if(weightfile){
load_weights(&net, weightfile);
}
- detection_layer *layer = get_network_detection_layer(net);
+ 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));
- //list *plist = get_paths("/home/pjreddie/data/voc/test_2007.txt");
- list *plist = get_paths("/home/pjreddie/data/voc/val_2012.txt");
+ list *plist = get_paths("/home/pjreddie/data/voc/test_2007.txt");
+ //list *plist = get_paths("/home/pjreddie/data/voc/val_2012.txt");
//list *plist = get_paths("/home/pjreddie/data/voc/test.txt");
//list *plist = get_paths("/home/pjreddie/data/voc/val.expanded.txt");
//list *plist = get_paths("/home/pjreddie/data/voc/train.txt");
char **paths = (char **)list_to_array(plist);
- int classes = layer->classes;
- int nuisance = layer->nuisance;
- int background = (layer->background && !nuisance);
- int num_boxes = sqrt(get_detection_layer_locations(*layer));
+ int classes = layer.classes;
+ int nuisance = layer.nuisance;
+ int background = (layer.background && !nuisance);
+ int num_boxes = sqrt(get_detection_layer_locations(layer));
int per_box = 4+classes+background+nuisance;
int num_output = num_boxes*num_boxes*per_box;
@@ -381,6 +388,89 @@
}
}
+void do_mask(network net, data d, int offset, int classes, int nuisance, int background, int num_boxes, int per_box)
+{
+ matrix pred = network_predict_data(net, d);
+ int j, k, class;
+ for(j = 0; j < pred.rows; ++j){
+ printf("%d ", offset + j);
+ for(k = 0; k < pred.cols; k += per_box){
+ float scale = 1.;
+ if (nuisance) scale = 1.-pred.vals[j][k];
+ float max_prob = 0;
+ for (class = 0; class < classes; ++class){
+ float prob = scale*pred.vals[j][k+class+background+nuisance];
+ if(prob > max_prob) max_prob = prob;
+ }
+ printf("%f ", max_prob);
+ }
+ printf("\n");
+ }
+ free_matrix(pred);
+}
+
+void mask_detection(char *cfgfile, char *weightfile)
+{
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ 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));
+
+ list *plist = get_paths("/home/pjreddie/data/voc/test_2007.txt");
+ //list *plist = get_paths("/home/pjreddie/data/voc/val_2012.txt");
+ //list *plist = get_paths("/home/pjreddie/data/voc/test.txt");
+ //list *plist = get_paths("/home/pjreddie/data/voc/val.expanded.txt");
+ //list *plist = get_paths("/home/pjreddie/data/voc/train.txt");
+ char **paths = (char **)list_to_array(plist);
+
+ int classes = layer.classes;
+ int nuisance = layer.nuisance;
+ int background = (layer.background && !nuisance);
+ int num_boxes = sqrt(get_detection_layer_locations(layer));
+
+ int per_box = 4+classes+background+nuisance;
+ int num_output = num_boxes*num_boxes*per_box;
+
+ int m = plist->size;
+ int i = 0;
+ int splits = 100;
+
+ int nthreads = 4;
+ int t;
+ data *val = calloc(nthreads, sizeof(data));
+ data *buf = calloc(nthreads, sizeof(data));
+ pthread_t *thr = calloc(nthreads, sizeof(data));
+ for(t = 0; t < nthreads; ++t){
+ int num = (i+1+t)*m/splits - (i+t)*m/splits;
+ char **part = paths+((i+t)*m/splits);
+ thr[t] = load_data_thread(part, num, 0, 0, num_output, net.w, net.h, &(buf[t]));
+ }
+
+ clock_t time;
+ for(i = nthreads; i <= splits; i += nthreads){
+ time=clock();
+ for(t = 0; t < nthreads; ++t){
+ pthread_join(thr[t], 0);
+ val[t] = buf[t];
+ }
+ for(t = 0; t < nthreads && i < splits; ++t){
+ int num = (i+1+t)*m/splits - (i+t)*m/splits;
+ char **part = paths+((i+t)*m/splits);
+ thr[t] = load_data_thread(part, num, 0, 0, num_output, net.w, net.h, &(buf[t]));
+ }
+
+ fprintf(stderr, "%d: Loaded: %lf seconds\n", i, sec(clock()-time));
+ for(t = 0; t < nthreads; ++t){
+ do_mask(net, val[t], (i-nthreads+t)*m/splits, classes, nuisance, background, num_boxes, per_box);
+ free_data(val[t]);
+ }
+ time=clock();
+ }
+}
+
void validate_detection_post(char *cfgfile, char *weightfile)
{
network net = parse_network_cfg(cfgfile);
@@ -393,7 +483,7 @@
load_weights(&post, "/home/pjreddie/imagenet_backup/localize_1000.weights");
set_batch_network(&post, 1);
- detection_layer *layer = get_network_detection_layer(net);
+ 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));
@@ -404,10 +494,10 @@
//list *plist = get_paths("/home/pjreddie/data/voc/train.txt");
char **paths = (char **)list_to_array(plist);
- int classes = layer->classes;
- int nuisance = layer->nuisance;
- int background = (layer->background && !nuisance);
- int num_boxes = sqrt(get_detection_layer_locations(*layer));
+ int classes = layer.classes;
+ int nuisance = layer.nuisance;
+ int background = (layer.background && !nuisance);
+ int num_boxes = sqrt(get_detection_layer_locations(layer));
int per_box = 4+classes+background+nuisance;
@@ -527,6 +617,7 @@
printf("%s: Predicted in %f seconds.\n", filename, sec(clock()-time));
draw_detection(im, predictions, 7, "detections");
free_image(im);
+ cvWaitKey(0);
}
}
@@ -544,5 +635,6 @@
else if(0==strcmp(argv[2], "teststuff")) train_detection_teststuff(cfg, weights);
else if(0==strcmp(argv[2], "trainloc")) train_localization(cfg, weights);
else if(0==strcmp(argv[2], "valid")) validate_detection(cfg, weights);
+ else if(0==strcmp(argv[2], "mask")) mask_detection(cfg, weights);
else if(0==strcmp(argv[2], "validpost")) validate_detection_post(cfg, weights);
}
--
Gitblit v1.10.0