From d41fbf638e070d9fcf26a4c55a58fc1d015179c5 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 11 Jun 2015 18:04:48 +0000
Subject: [PATCH] stuff
---
src/detection_layer.c | 155 ++++++++++++++++-----------------------------------
1 files changed, 48 insertions(+), 107 deletions(-)
diff --git a/src/detection_layer.c b/src/detection_layer.c
index dd68244..c628f18 100644
--- a/src/detection_layer.c
+++ b/src/detection_layer.c
@@ -10,15 +10,15 @@
int get_detection_layer_locations(detection_layer l)
{
- return l.inputs / (l.classes+l.coords+l.rescore+l.background);
+ return l.inputs / (l.classes+l.coords+l.joint+(l.background || l.objectness));
}
int get_detection_layer_output_size(detection_layer l)
{
- return get_detection_layer_locations(l)*(l.background + l.classes + l.coords);
+ return get_detection_layer_locations(l)*((l.background || l.objectness) + l.classes + l.coords);
}
-detection_layer make_detection_layer(int batch, int inputs, int classes, int coords, int rescore, int background, int nuisance)
+detection_layer make_detection_layer(int batch, int inputs, int classes, int coords, int joint, int rescore, int background, int objectness)
{
detection_layer l = {0};
l.type = DETECTION;
@@ -28,7 +28,8 @@
l.classes = classes;
l.coords = coords;
l.rescore = rescore;
- l.nuisance = nuisance;
+ l.objectness = objectness;
+ l.joint = joint;
l.cost = calloc(1, sizeof(float));
l.does_cost=1;
l.background = background;
@@ -47,28 +48,6 @@
return l;
}
-void dark_zone(detection_layer l, int class, int start, network_state state)
-{
- int index = start+l.background+class;
- int size = l.classes+l.coords+l.background;
- int location = (index%(7*7*size)) / size ;
- int r = location / 7;
- int c = location % 7;
- int dr, dc;
- for(dr = -1; dr <= 1; ++dr){
- for(dc = -1; dc <= 1; ++dc){
- if(!(dr || dc)) continue;
- if((r + dr) > 6 || (r + dr) < 0) continue;
- if((c + dc) > 6 || (c + dc) < 0) continue;
- int di = (dr*7 + dc) * size;
- if(state.truth[index+di]) continue;
- l.output[index + di] = 0;
- //if(!state.truth[start+di]) continue;
- //l.output[start + di] = 1;
- }
- }
-}
-
typedef struct{
float dx, dy, dw, dh;
} dbox;
@@ -258,24 +237,6 @@
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)
@@ -308,10 +269,10 @@
int locations = get_detection_layer_locations(l);
int i,j;
for(i = 0; i < l.batch*locations; ++i){
- int mask = (!state.truth || state.truth[out_i + l.background + l.classes + 2]);
+ int mask = (!state.truth || state.truth[out_i + (l.background || l.objectness) + l.classes + 2]);
float scale = 1;
- if(l.rescore) scale = state.input[in_i++];
- else if(l.nuisance){
+ if(l.joint) scale = state.input[in_i++];
+ else if(l.objectness){
l.output[out_i++] = 1-state.input[in_i++];
scale = mask;
}
@@ -320,7 +281,7 @@
for(j = 0; j < l.classes; ++j){
l.output[out_i++] = scale*state.input[in_i++];
}
- if(l.nuisance){
+ if(l.objectness){
}else if(l.background){
softmax_array(l.output + out_i - l.classes-l.background, l.classes+l.background, l.output + out_i - l.classes-l.background);
@@ -330,77 +291,57 @@
l.output[out_i++] = mask*state.input[in_i++];
}
}
+ float avg_iou = 0;
+ int count = 0;
if(l.does_cost && state.train){
- int count = 0;
*(l.cost) = 0;
int size = get_detection_layer_output_size(l) * l.batch;
memset(l.delta, 0, size * sizeof(float));
for (i = 0; i < l.batch*locations; ++i) {
- int classes = l.nuisance+l.classes;
+ int classes = l.objectness+l.classes;
int offset = i*(classes+l.coords);
for (j = offset; j < offset+classes; ++j) {
*(l.cost) += pow(state.truth[j] - l.output[j], 2);
l.delta[j] = state.truth[j] - l.output[j];
}
+
box truth;
- truth.x = state.truth[j+0];
- truth.y = state.truth[j+1];
- truth.w = state.truth[j+2];
- truth.h = state.truth[j+3];
+ truth.x = state.truth[j+0]/7;
+ truth.y = state.truth[j+1]/7;
+ truth.w = pow(state.truth[j+2], 2);
+ truth.h = pow(state.truth[j+3], 2);
box out;
- out.x = l.output[j+0];
- out.y = l.output[j+1];
- out.w = l.output[j+2];
- out.h = l.output[j+3];
+ out.x = l.output[j+0]/7;
+ out.y = l.output[j+1]/7;
+ out.w = pow(l.output[j+2], 2);
+ out.h = pow(l.output[j+3], 2);
+
if(!(truth.w*truth.h)) continue;
- l.delta[j+0] = (truth.x - out.x);
- l.delta[j+1] = (truth.y - out.y);
- l.delta[j+2] = (truth.w - out.w);
- l.delta[j+3] = (truth.h - out.h);
- *(l.cost) += pow((out.x - truth.x), 2);
- *(l.cost) += pow((out.y - truth.y), 2);
- *(l.cost) += pow((out.w - truth.w), 2);
- *(l.cost) += pow((out.h - truth.h), 2);
-
-/*
- l.delta[j+0] = .1 * (truth.x - out.x) / (49 * truth.w * truth.w);
- l.delta[j+1] = .1 * (truth.y - out.y) / (49 * truth.h * truth.h);
- l.delta[j+2] = .1 * (truth.w - out.w) / ( truth.w * truth.w);
- l.delta[j+3] = .1 * (truth.h - out.h) / ( truth.h * truth.h);
-
- *(l.cost) += pow((out.x - truth.x)/truth.w/7., 2);
- *(l.cost) += pow((out.y - truth.y)/truth.h/7., 2);
- *(l.cost) += pow((out.w - truth.w)/truth.w, 2);
- *(l.cost) += pow((out.h - truth.h)/truth.h, 2);
- */
+ float iou = box_iou(out, truth);
+ avg_iou += iou;
++count;
+ dbox delta = diou(out, truth);
+
+ l.delta[j+0] = 10 * delta.dx/7;
+ l.delta[j+1] = 10 * delta.dy/7;
+ l.delta[j+2] = 10 * delta.dw * 2 * sqrt(out.w);
+ l.delta[j+3] = 10 * delta.dh * 2 * sqrt(out.h);
+
+
+ *(l.cost) += pow((1-iou), 2);
+ l.delta[j+0] = 4 * (state.truth[j+0] - l.output[j+0]);
+ l.delta[j+1] = 4 * (state.truth[j+1] - l.output[j+1]);
+ l.delta[j+2] = 4 * (state.truth[j+2] - l.output[j+2]);
+ l.delta[j+3] = 4 * (state.truth[j+3] - l.output[j+3]);
+ if(l.rescore){
+ for (j = offset; j < offset+classes; ++j) {
+ if(state.truth[j]) state.truth[j] = iou;
+ l.delta[j] = state.truth[j] - l.output[j];
+ }
+ }
}
+ printf("Avg IOU: %f\n", avg_iou/count);
}
- /*
- int count = 0;
- for(i = 0; i < l.batch*locations; ++i){
- for(j = 0; j < l.classes+l.background; ++j){
- printf("%f, ", l.output[count++]);
- }
- printf("\n");
- for(j = 0; j < l.coords; ++j){
- printf("%f, ", l.output[count++]);
- }
- printf("\n");
- }
- */
- /*
- if(l.background || 1){
- for(i = 0; i < l.batch*locations; ++i){
- int index = i*(l.classes+l.coords+l.background);
- for(j= 0; j < l.classes; ++j){
- if(state.truth[index+j+l.background]){
-//dark_zone(l, j, index, state);
-}
-}
-}
-}
- */
}
void backward_detection_layer(const detection_layer l, network_state state)
@@ -412,21 +353,21 @@
for(i = 0; i < l.batch*locations; ++i){
float scale = 1;
float latent_delta = 0;
- if(l.rescore) scale = state.input[in_i++];
- else if (l.nuisance) state.delta[in_i++] = -l.delta[out_i++];
+ if(l.joint) scale = state.input[in_i++];
+ else if (l.objectness) state.delta[in_i++] = -l.delta[out_i++];
else if (l.background) state.delta[in_i++] = scale*l.delta[out_i++];
for(j = 0; j < l.classes; ++j){
latent_delta += state.input[in_i]*l.delta[out_i];
state.delta[in_i++] = scale*l.delta[out_i++];
}
- if (l.nuisance) {
+ if (l.objectness) {
}else if (l.background) gradient_array(l.output + out_i, l.coords, LOGISTIC, l.delta + out_i);
for(j = 0; j < l.coords; ++j){
state.delta[in_i++] = l.delta[out_i++];
}
- if(l.rescore) state.delta[in_i-l.coords-l.classes-l.rescore-l.background] = latent_delta;
+ if(l.joint) state.delta[in_i-l.coords-l.classes-l.joint] = latent_delta;
}
}
--
Gitblit v1.10.0