From f11480833d19c0a7e9e1f7b45a19ba5bb5d63666 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sun, 02 Aug 2015 00:26:53 +0000
Subject: [PATCH] Headers are important
---
src/detection.c | 93 ++++++++++++++++++----------------------------
1 files changed, 36 insertions(+), 57 deletions(-)
diff --git a/src/detection.c b/src/detection.c
index dc3d9a4..55c75de 100644
--- a/src/detection.c
+++ b/src/detection.c
@@ -8,19 +8,22 @@
char *class_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
-void draw_detection(image im, float *box, int side, char *label)
+void draw_detection(image im, float *box, int side, int objectness, char *label)
{
int classes = 20;
- int elems = 4+classes;
+ int elems = 4+classes+objectness;
int j;
int r, c;
for(r = 0; r < side; ++r){
for(c = 0; c < side; ++c){
j = (r*side + c) * elems;
+ float scale = 1;
+ if(objectness) scale = 1 - box[j++];
int class = max_index(box+j, classes);
- if(box[j+class] > 0.2){
- printf("%f %s\n", box[j+class], class_names[class]);
+ if(scale * box[j+class] > 0.2){
+ int width = box[j+class]*5 + 1;
+ printf("%f %s\n", scale * box[j+class], class_names[class]);
float red = get_color(0,class,classes);
float green = get_color(1,class,classes);
float blue = get_color(2,class,classes);
@@ -39,9 +42,7 @@
int right = (x+w/2)*im.w;
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);
+ draw_box_width(im, left, top, right, bot, width, red, green, blue);
}
}
}
@@ -50,9 +51,10 @@
void train_detection(char *cfgfile, char *weightfile)
{
+ char *train_images = "/home/pjreddie/data/voc/test/train.txt";
+ char *backup_directory = "/home/pjreddie/backup/";
srand(time(0));
data_seed = time(0);
- int imgnet = 0;
char *base = basecfg(cfgfile);
printf("%s\n", base);
float avg_loss = -1;
@@ -67,57 +69,56 @@
data train, buffer;
int classes = layer.classes;
- int background = (layer.background || layer.objectness);
- printf("%d\n", background);
+ int background = layer.objectness;
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/val_2012.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");
- }
+ list *plist = get_paths(train_images);
+ int N = plist->size;
+
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;
- while(1){
+ while(i*imgs < N*120){
i += 1;
time=clock();
pthread_join(load_thread, 0);
train = buffer;
load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, net.w, net.h, side, side, background, &buffer);
-/*
- image im = float_to_image(net.w, net.h, 3, train.X.vals[114]);
- image copy = copy_image(im);
- draw_detection(copy, train.y.vals[114], 7, "truth");
- cvWaitKey(0);
- free_image(copy);
- */
-
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
float loss = train_network(net, train);
net.seen += imgs;
if (avg_loss < 0) avg_loss = loss;
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){
+ if((i-1)*imgs <= N && i*imgs > N){
+ fprintf(stderr, "Starting second stage...\n");
net.learning_rate *= 10;
+ char buff[256];
+ sprintf(buff, "%s/%s_first_stage.weights", backup_directory, base);
+ save_weights(net, buff);
+ }
+ if((i-1)*imgs <= 80*N && i*imgs > N*80){
+ fprintf(stderr, "Second stage done.\n");
+ net.learning_rate *= .1;
+ char buff[256];
+ sprintf(buff, "%s/%s_second_stage.weights", backup_directory, base);
+ save_weights(net, buff);
+ return;
}
if(i%1000==0){
char buff[256];
- sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
+ 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 convert_detections(float *predictions, int classes, int objectness, int background, int num_boxes, int w, int h, float thresh, float **probs, box *boxes)
@@ -142,26 +143,6 @@
}
}
-void do_nms(box *boxes, float **probs, int num_boxes, int classes, float thresh)
-{
- int i, j, k;
- for(i = 0; i < num_boxes*num_boxes; ++i){
- int any = 0;
- for(k = 0; k < classes; ++k) any = any || (probs[i][k] > 0);
- if(!any) {
- continue;
- }
- for(j = i+1; j < num_boxes*num_boxes; ++j){
- if (box_iou(boxes[i], boxes[j]) > thresh){
- for(k = 0; k < classes; ++k){
- if (probs[i][k] < probs[j][k]) probs[i][k] = 0;
- else probs[j][k] = 0;
- }
- }
- }
- }
-}
-
void print_detections(FILE **fps, char *id, box *boxes, float **probs, int num_boxes, int classes, int w, int h)
{
int i, j;
@@ -175,7 +156,7 @@
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);
@@ -268,8 +249,6 @@
load_weights(&net, weightfile);
}
detection_layer layer = get_network_detection_layer(net);
- if (!layer.joint) fprintf(stderr, "Detection layer should use joint prediction to draw correctly.\n");
- int im_size = 448;
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
@@ -284,12 +263,12 @@
strtok(input, "\n");
}
image im = load_image_color(input,0,0);
- image sized = resize_image(im, im_size, im_size);
+ image sized = resize_image(im, net.w, net.h);
float *X = sized.data;
time=clock();
float *predictions = network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
- draw_detection(im, predictions, 7, "predictions");
+ draw_detection(im, predictions, 7, layer.objectness, "predictions");
free_image(im);
free_image(sized);
#ifdef OPENCV
--
Gitblit v1.10.0