From a4485b8a6656c2a2fa0b78ca7c035523c8149b8c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 10 Jun 2015 15:49:25 +0000
Subject: [PATCH] Merge branch 'master' of pjreddie.com:jnet
---
src/detection.c | 206 +++++++++++++++++++++++++++++++--------------------
1 files changed, 125 insertions(+), 81 deletions(-)
diff --git a/src/detection.c b/src/detection.c
index e927140..a3b40ca 100644
--- a/src/detection.c
+++ b/src/detection.c
@@ -1,13 +1,15 @@
#include "network.h"
+#include "detection_layer.h"
+#include "cost_layer.h"
#include "utils.h"
#include "parser.h"
-char *class_names[] = {"bg", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
-#define AMNT 3
-void draw_detection(image im, float *box, int side)
+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)
{
- int classes = 21;
+ int classes = 20;
int elems = 4+classes;
int j;
int r, c;
@@ -15,43 +17,41 @@
for(r = 0; r < side; ++r){
for(c = 0; c < side; ++c){
j = (r*side + c) * elems;
- //printf("%d\n", j);
- //printf("Prob: %f\n", box[j]);
int class = max_index(box+j, classes);
- if(box[j+class] > .02 || 1){
- //int z;
- //for(z = 0; z < classes; ++z) printf("%f %s\n", box[j+z], class_names[z]);
+ if(box[j+class] > .2){
printf("%f %s\n", 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);
- //float maxheight = distance_from_edge(r, side);
- //float maxwidth = distance_from_edge(c, side);
j += classes;
- float y = box[j+0];
- float x = box[j+1];
+ float x = box[j+0];
+ float y = box[j+1];
x = (x+c)/side;
y = (y+r)/side;
- float h = box[j+2]; //*maxheight;
- float w = box[j+3]; //*maxwidth;
- //printf("coords %f %f %f %f\n", x, y, w, h);
+ float w = box[j+2]; //*maxwidth;
+ float h = box[j+3]; //*maxheight;
+ h = h*h;
+ w = w*w;
int left = (x-w/2)*im.w;
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);
}
}
}
- //printf("Done\n");
- show_image(im, "box");
- cvWaitKey(0);
+ show_image(im, label);
}
void train_detection(char *cfgfile, char *weightfile)
{
+ srand(time(0));
+ data_seed = time(0);
+ int imgnet = 0;
char *base = basecfg(cfgfile);
printf("%s\n", base);
float avg_loss = -1;
@@ -59,30 +59,45 @@
if(weightfile){
load_weights(&net, weightfile);
}
- //net.seen = 0;
+ 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;
- srand(time(0));
- //srand(23410);
int i = net.seen/imgs;
- list *plist = get_paths("/home/pjreddie/data/voc/train.txt");
- char **paths = (char **)list_to_array(plist);
- printf("%d\n", plist->size);
data train, buffer;
- int im_dim = 448;
- int classes = 20;
- int background = 1;
- pthread_t load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, im_dim, im_dim, 7, 7, background, &buffer);
+
+ int classes = layer.classes;
+ int background = (layer.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");
+ }
+ 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){
i += 1;
time=clock();
pthread_join(load_thread, 0);
train = buffer;
- load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, im_dim, im_dim, 7, 7, background, &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(im_dim, im_dim, 3, train.X.vals[114]);
- //draw_detection(im, train.y.vals[114], 7);
+/*
+ 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();
@@ -91,7 +106,10 @@
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==0){
+ if(i == 100){
+ net.learning_rate *= 10;
+ }
+ if(i%1000==0){
char buff[256];
sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
save_weights(net, buff);
@@ -100,70 +118,91 @@
}
}
+void predict_detections(network net, data d, float threshold, int offset, int classes, int objectness, 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){
+ for(k = 0; k < pred.cols; k += per_box){
+ float scale = 1.;
+ int index = k/per_box;
+ int row = index / num_boxes;
+ int col = index % num_boxes;
+ if (objectness) scale = 1.-pred.vals[j][k];
+ for (class = 0; class < classes; ++class){
+ int ci = k+classes+(background || objectness);
+ float x = (pred.vals[j][ci + 0] + col)/num_boxes;
+ float y = (pred.vals[j][ci + 1] + row)/num_boxes;
+ float w = pred.vals[j][ci + 2]; // distance_from_edge(row, num_boxes);
+ float h = pred.vals[j][ci + 3]; // distance_from_edge(col, num_boxes);
+ w = pow(w, 2);
+ h = pow(h, 2);
+ float prob = scale*pred.vals[j][k+class+(background || objectness)];
+ if(prob < threshold) continue;
+ printf("%d %d %f %f %f %f %f\n", offset + j, class, prob, x, y, w, h);
+ }
+ }
+ }
+ free_matrix(pred);
+}
+
void validate_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/val.txt");
- //list *plist = get_paths("/home/pjreddie/data/voc/train.txt");
+ list *plist = get_paths("/home/pjreddie/data/voc/test.txt");
char **paths = (char **)list_to_array(plist);
- int im_size = 448;
- int classes = 20;
- int background = 0;
- int nuisance = 1;
- int num_boxes = 7;
- int per_box = 4+classes+background+nuisance;
+
+ int classes = layer.classes;
+ int objectness = layer.objectness;
+ int background = layer.background;
+ int num_boxes = sqrt(get_detection_layer_locations(layer));
+
+ int per_box = 4+classes+(background || objectness);
int num_output = num_boxes*num_boxes*per_box;
int m = plist->size;
int i = 0;
int splits = 100;
- int num = (i+1)*m/splits - i*m/splits;
- fprintf(stderr, "%d\n", m);
- data val, buffer;
- pthread_t load_thread = load_data_thread(paths, num, 0, 0, num_output, im_size, im_size, &buffer);
- clock_t time;
- for(i = 1; i <= splits; ++i){
- time=clock();
- pthread_join(load_thread, 0);
- val = buffer;
+ int nthreads = 4;
+ int t;
+ data *val = calloc(nthreads, sizeof(data));
+ data *buf = calloc(nthreads, sizeof(data));
+ pthread_t *thr = calloc(nthreads, sizeof(data));
- num = (i+1)*m/splits - i*m/splits;
- char **part = paths+(i*m/splits);
- if(i != splits) load_thread = load_data_thread(part, num, 0, 0, num_output, im_size, im_size, &buffer);
+ time_t start = time(0);
- fprintf(stderr, "%d: Loaded: %lf seconds\n", i, sec(clock()-time));
- matrix pred = network_predict_data(net, val);
- int j, k, class;
- for(j = 0; j < pred.rows; ++j){
- for(k = 0; k < pred.cols; k += per_box){
- float scale = 1.;
- int index = k/per_box;
- int row = index / num_boxes;
- int col = index % num_boxes;
- if (nuisance) scale = 1.-pred.vals[j][k];
- for (class = 0; class < classes; ++class){
- int ci = k+classes+background+nuisance;
- float y = (pred.vals[j][ci + 0] + row)/num_boxes;
- float x = (pred.vals[j][ci + 1] + col)/num_boxes;
- float h = pred.vals[j][ci + 2]; //* distance_from_edge(row, num_boxes);
- h = h*h;
- float w = pred.vals[j][ci + 3]; //* distance_from_edge(col, num_boxes);
- w = w*w;
- printf("%d %d %f %f %f %f %f\n", (i-1)*m/splits + j, class, scale*pred.vals[j][k+class+background+nuisance], y, x, h, w);
- }
- }
+ 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]));
+ }
+
+ for(i = nthreads; i <= splits; i += nthreads){
+ 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]));
}
- time=clock();
- free_data(val);
+ fprintf(stderr, "%d\n", i);
+ for(t = 0; t < nthreads; ++t){
+ predict_detections(net, val[t], .001, (i-nthreads+t)*m/splits, classes, objectness, background, num_boxes, per_box);
+ free_data(val[t]);
+ }
}
+ fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
}
void test_detection(char *cfgfile, char *weightfile)
@@ -172,6 +211,8 @@
if(weightfile){
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);
@@ -180,16 +221,19 @@
while(1){
fgets(filename, 256, stdin);
strtok(filename, "\n");
- image im = load_image_color(filename, im_size, im_size);
- translate_image(im, -128);
- scale_image(im, 1/128.);
+ image im = load_image_color(filename,0,0);
+ image sized = resize_image(im, im_size, im_size);
printf("%d %d %d\n", im.h, im.w, im.c);
- float *X = im.data;
+ float *X = sized.data;
time=clock();
float *predictions = network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", filename, sec(clock()-time));
- draw_detection(im, predictions, 7);
+ draw_detection(im, predictions, 7, "predictions");
free_image(im);
+ free_image(sized);
+ #ifdef OPENCV
+ cvWaitKey(0);
+ #endif
}
}
--
Gitblit v1.10.0