From 372980d690f84aade1ebfd1a92750ed327ab1c8d Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Mon, 04 May 2015 18:29:21 +0000
Subject: [PATCH] i don't know what's going on anymore
---
src/detection.c | 16 ++-
src/imagenet.c | 2
src/data.c | 18 ++--
src/detection_layer.c | 168 +++++++++++++++++++++++++++++++----------
4 files changed, 146 insertions(+), 58 deletions(-)
diff --git a/src/data.c b/src/data.c
index f1f5b80..79c203e 100644
--- a/src/data.c
+++ b/src/data.c
@@ -166,8 +166,10 @@
w = constrain(0, 1, w);
h = constrain(0, 1, h);
if (w == 0 || h == 0) continue;
- w = sqrt(w);
- h = sqrt(h);
+ if(1){
+ w = sqrt(w);
+ h = sqrt(h);
+ }
int index = (i+j*num_boxes)*(4+classes+background);
if(truth[index+classes+background+2]) continue;
@@ -316,13 +318,13 @@
float sx = (float)swidth / ow;
float sy = (float)sheight / oh;
-
+
/*
- float angle = rand_uniform()*.1 - .05;
- image rot = rotate_image(orig, angle);
- free_image(orig);
- orig = rot;
- */
+ float angle = rand_uniform()*.1 - .05;
+ image rot = rotate_image(orig, angle);
+ free_image(orig);
+ orig = rot;
+ */
int flip = rand_r(&data_seed)%2;
image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
diff --git a/src/detection.c b/src/detection.c
index f61da67..93e9fe1 100644
--- a/src/detection.c
+++ b/src/detection.c
@@ -81,7 +81,8 @@
if (imgnet){
plist = get_paths("/home/pjreddie/data/imagenet/det.train.list");
}else{
- plist = get_paths("/home/pjreddie/data/voc/trainall.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");
}
@@ -131,12 +132,12 @@
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);
+ 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 = w*w;
+ h = h*h;
float prob = scale*pred.vals[j][k+class+background+nuisance];
if(prob < threshold) continue;
printf("%d %d %f %f %f %f %f\n", offset + j, class, prob, y, x, h, w);
@@ -156,7 +157,8 @@
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/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");
diff --git a/src/detection_layer.c b/src/detection_layer.c
index 7eaabb4..831439e 100644
--- a/src/detection_layer.c
+++ b/src/detection_layer.c
@@ -165,28 +165,117 @@
di.dx = dover.dx*h;
di.dh = dover.dh*w;
di.dy = dover.dy*w;
- if(h < 0 || w < 0){
- di.dx = dover.dx;
- di.dy = dover.dy;
- }
+
return di;
}
dbox dunion(box a, box b)
{
- dbox du = {0,0,0,0};;
- float w = overlap(a.x, a.w, b.x, b.w);
- float h = overlap(a.y, a.h, b.y, b.h);
- if(w > 0 && h > 0){
- dbox di = dintersect(a, b);
- du.dw = h - di.dw;
- du.dh = w - di.dw;
- du.dx = -di.dx;
- du.dy = -di.dy;
- }
+ dbox du;
+
+ dbox di = dintersect(a, b);
+ du.dw = a.h - di.dw;
+ du.dh = a.w - di.dh;
+ du.dx = -di.dx;
+ du.dy = -di.dy;
+
return du;
}
+dbox diou(box a, box b);
+
+void test_dunion()
+{
+ box a = {0, 0, 1, 1};
+ box dxa= {0+.0001, 0, 1, 1};
+ box dya= {0, 0+.0001, 1, 1};
+ box dwa= {0, 0, 1+.0001, 1};
+ box dha= {0, 0, 1, 1+.0001};
+
+ box b = {.5, .5, .2, .2};
+ dbox di = dunion(a,b);
+ printf("Union: %f %f %f %f\n", di.dx, di.dy, di.dw, di.dh);
+ float inter = box_union(a, b);
+ float xinter = box_union(dxa, b);
+ float yinter = box_union(dya, b);
+ float winter = box_union(dwa, b);
+ float hinter = box_union(dha, b);
+ xinter = (xinter - inter)/(.0001);
+ yinter = (yinter - inter)/(.0001);
+ winter = (winter - inter)/(.0001);
+ hinter = (hinter - inter)/(.0001);
+ printf("Union Manual %f %f %f %f\n", xinter, yinter, winter, hinter);
+}
+void test_dintersect()
+{
+ box a = {0, 0, 1, 1};
+ box dxa= {0+.0001, 0, 1, 1};
+ box dya= {0, 0+.0001, 1, 1};
+ box dwa= {0, 0, 1+.0001, 1};
+ box dha= {0, 0, 1, 1+.0001};
+
+ box b = {.5, .5, .2, .2};
+ dbox di = dintersect(a,b);
+ printf("Inter: %f %f %f %f\n", di.dx, di.dy, di.dw, di.dh);
+ float inter = box_intersection(a, b);
+ float xinter = box_intersection(dxa, b);
+ float yinter = box_intersection(dya, b);
+ float winter = box_intersection(dwa, b);
+ float hinter = box_intersection(dha, b);
+ xinter = (xinter - inter)/(.0001);
+ yinter = (yinter - inter)/(.0001);
+ winter = (winter - inter)/(.0001);
+ hinter = (hinter - inter)/(.0001);
+ printf("Inter Manual %f %f %f %f\n", xinter, yinter, winter, hinter);
+}
+
+void test_box()
+{
+ test_dintersect();
+ test_dunion();
+ box a = {0, 0, 1, 1};
+ box dxa= {0+.00001, 0, 1, 1};
+ box dya= {0, 0+.00001, 1, 1};
+ box dwa= {0, 0, 1+.00001, 1};
+ box dha= {0, 0, 1, 1+.00001};
+
+ box b = {.5, 0, .2, .2};
+
+ float iou = box_iou(a,b);
+ iou = (1-iou)*(1-iou);
+ printf("%f\n", iou);
+ dbox d = diou(a, b);
+ printf("%f %f %f %f\n", d.dx, d.dy, d.dw, d.dh);
+
+ float xiou = box_iou(dxa, b);
+ float yiou = box_iou(dya, b);
+ float wiou = box_iou(dwa, b);
+ float hiou = box_iou(dha, b);
+ xiou = ((1-xiou)*(1-xiou) - iou)/(.00001);
+ yiou = ((1-yiou)*(1-yiou) - iou)/(.00001);
+ wiou = ((1-wiou)*(1-wiou) - iou)/(.00001);
+ hiou = ((1-hiou)*(1-hiou) - iou)/(.00001);
+ printf("manual %f %f %f %f\n", xiou, yiou, wiou, hiou);
+ /*
+
+ while(count++ < 300){
+ dbox d = diou(a, b);
+ printf("%f %f %f %f\n", a.x, a.y, a.w, a.h);
+ a.x += .1*d.dx;
+ a.w += .1*d.dw;
+ a.y += .1*d.dy;
+ a.h += .1*d.dh;
+ printf("inter: %f\n", box_intersection(a, b));
+ printf("union: %f\n", box_union(a, b));
+ printf("IOU: %f\n", box_iou(a, b));
+ if(d.dx==0 && d.dw==0 && d.dy==0 && d.dh==0) {
+ printf("break!!!\n");
+ break;
+ }
+ }
+ */
+}
+
dbox diou(box a, box b)
{
float u = box_union(a,b);
@@ -194,13 +283,15 @@
dbox di = dintersect(a,b);
dbox du = dunion(a,b);
dbox dd = {0,0,0,0};
- if(i < 0) {
+
+ if(i <= 0 || 1) {
dd.dx = b.x - a.x;
dd.dy = b.y - a.y;
dd.dw = b.w - a.w;
dd.dh = b.h - a.h;
return dd;
}
+
dd.dx = 2*pow((1-(i/u)),1)*(di.dx*u - du.dx*i)/(u*u);
dd.dy = 2*pow((1-(i/u)),1)*(di.dy*u - du.dy*i)/(u*u);
dd.dw = 2*pow((1-(i/u)),1)*(di.dw*u - du.dw*i)/(u*u);
@@ -208,28 +299,6 @@
return dd;
}
-void test_box()
-{
- box a = {1, 1, 1, 1};
- box b = {0, 0, .5, .2};
- int count = 0;
- while(count++ < 300){
- dbox d = diou(a, b);
- printf("%f %f %f %f\n", a.x, a.y, a.w, a.h);
- a.x += .1*d.dx;
- a.w += .1*d.dw;
- a.y += .1*d.dy;
- a.h += .1*d.dh;
- printf("inter: %f\n", box_intersection(a, b));
- printf("union: %f\n", box_union(a, b));
- printf("IOU: %f\n", box_iou(a, b));
- if(d.dx==0 && d.dw==0 && d.dy==0 && d.dh==0) {
- printf("break!!!\n");
- break;
- }
- }
-}
-
void forward_detection_layer(const detection_layer layer, network_state state)
{
int in_i = 0;
@@ -250,7 +319,7 @@
layer.output[out_i++] = scale*state.input[in_i++];
}
if(layer.nuisance){
-
+
}else if(layer.background){
softmax_array(layer.output + out_i - layer.classes-layer.background, layer.classes+layer.background, layer.output + out_i - layer.classes-layer.background);
activate_array(state.input+in_i, layer.coords, LOGISTIC);
@@ -259,14 +328,16 @@
layer.output[out_i++] = mask*state.input[in_i++];
}
}
- if(layer.does_cost){
+ if(layer.does_cost && state.train && 0){
+ int count = 0;
+ float avg = 0;
*(layer.cost) = 0;
int size = get_detection_layer_output_size(layer) * layer.batch;
memset(layer.delta, 0, size * sizeof(float));
- for(i = 0; i < layer.batch*locations; ++i){
+ for (i = 0; i < layer.batch*locations; ++i) {
int classes = layer.nuisance+layer.classes;
int offset = i*(classes+layer.coords);
- for(j = offset; j < offset+classes; ++j){
+ for (j = offset; j < offset+classes; ++j) {
*(layer.cost) += pow(state.truth[j] - layer.output[j], 2);
layer.delta[j] = state.truth[j] - layer.output[j];
}
@@ -281,15 +352,26 @@
out.w = layer.output[j+2];
out.h = layer.output[j+3];
if(!(truth.w*truth.h)) continue;
- float iou = box_iou(truth, out);
//printf("iou: %f\n", iou);
- *(layer.cost) += pow((1-iou), 2);
dbox d = diou(out, truth);
layer.delta[j+0] = d.dx;
layer.delta[j+1] = d.dy;
layer.delta[j+2] = d.dw;
layer.delta[j+3] = d.dh;
+
+ int sqr = 1;
+ if(sqr){
+ truth.w *= truth.w;
+ truth.h *= truth.h;
+ out.w *= out.w;
+ out.h *= out.h;
+ }
+ float iou = box_iou(truth, out);
+ *(layer.cost) += pow((1-iou), 2);
+ avg += iou;
+ ++count;
}
+ fprintf(stderr, "Avg IOU: %f\n", avg/count);
}
/*
int count = 0;
diff --git a/src/imagenet.c b/src/imagenet.c
index 3f88b36..8e70c28 100644
--- a/src/imagenet.c
+++ b/src/imagenet.c
@@ -14,6 +14,7 @@
load_weights(&net, weightfile);
}
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+ //net.seen=0;
int imgs = 1024;
int i = net.seen/imgs;
char **labels = get_labels("/home/pjreddie/data/imagenet/cls.labels.list");
@@ -46,6 +47,7 @@
avg_loss = avg_loss*.9 + loss*.1;
printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), net.seen);
free_data(train);
+ if((i % 20000) == 0) net.learning_rate *= .1;
//if(i%100 == 0 && net.learning_rate > .00001) net.learning_rate *= .97;
if(i%1000==0){
char buff[256];
--
Gitblit v1.10.0