mirror/darknet
1
0
Fork 0
mirror of https://github.com/pjreddie/darknet.git synced 2023-08-10 21:13:14 +03:00
Code Issues Projects Releases Wiki Activity

Added Focal loss. Use focal_loss=1 in the [region] layer in your cfg-file.

Browse Source 
alpha = 0.5, gamma = 2
This commit is contained in:
AlexeyAB
2018-03-05 19:59:29 +03:00
parent f0bc634a74
commit 5e448c00f3
3 changed files with 31 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/layer.h
View File

@ -85,6 +85,7 @@ struct layer{
float exposure; float exposure;
float shift; float shift;
float ratio; float ratio;
int focal_loss;
int softmax; int softmax;
int classes; int classes;
int coords; int coords;

1
src/parser.c
View File

@ -250,6 +250,7 @@ layer parse_region(list *options, size_params params)
l.small_object = option_find_int_quiet(options, "small_object", 0); l.small_object = option_find_int_quiet(options, "small_object", 0);
l.softmax = option_find_int(options, "softmax", 0); l.softmax = option_find_int(options, "softmax", 0);
l.focal_loss = option_find_int_quiet(options, "focal_loss", 0);
//l.max_boxes = option_find_int_quiet(options, "max",30); //l.max_boxes = option_find_int_quiet(options, "max",30);
l.jitter = option_find_float(options, "jitter", .2); l.jitter = option_find_float(options, "jitter", .2);
l.rescore = option_find_int_quiet(options, "rescore",0); l.rescore = option_find_int_quiet(options, "rescore",0);

38
src/region_layer.c
View File

@ -110,7 +110,7 @@ float delta_region_box(box truth, float *x, float *biases, int n, int index, int
return iou; return iou;
} }
void delta_region_class(float *output, float *delta, int index, int class_id, int classes, tree *hier, float scale, float *avg_cat) void delta_region_class(float *output, float *delta, int index, int class_id, int classes, tree *hier, float scale, float *avg_cat, int focal_loss)
{ {
int i, n; int i, n;
if(hier){ if(hier){
@ -127,11 +127,31 @@ void delta_region_class(float *output, float *delta, int index, int class_id, in
class_id = hier->parent[class_id]; class_id = hier->parent[class_id];
} }
*avg_cat += pred; *avg_cat += pred;
} else { } else {
for(n = 0; n < classes; ++n){ // Focal loss
delta[index + n] = scale * (((n == class_id)?1 : 0) - output[index + n]); if (focal_loss) {
if(n == class_id) *avg_cat += output[index + n]; // Focal Loss for Dense Object Detection: http://blog.csdn.net/linmingan/article/details/77885832
} //printf("Used Focal-loss \n");
float alpha = 0.5; // 0.25
float gamma = 2.0;
int ti = index + class_id;
float grad = -gamma * (1 - output[ti])*logf(fmaxf(output[ti], 0.0000001))*output[ti] + (1 - output[ti])*(1 - output[ti]);
for (n = 0; n < classes; ++n) {
delta[index + n] = scale * (((n == class_id) ? 1 : 0) - output[index + n]);
delta[index + n] *= alpha*grad;
if (n == class_id) *avg_cat += output[index + n];
}
}
else {
// default
for (n = 0; n < classes; ++n) {
delta[index + n] = scale * (((n == class_id) ? 1 : 0) - output[index + n]);
if (n == class_id) *avg_cat += output[index + n];
}
}
} }
} }
@ -209,7 +229,7 @@ void forward_region_layer(const region_layer l, network_state state)
} }
} }
int index = size*maxi + b*l.outputs + 5; int index = size*maxi + b*l.outputs + 5;
delta_region_class(l.output, l.delta, index, class_id, l.classes, l.softmax_tree, l.class_scale, &avg_cat); delta_region_class(l.output, l.delta, index, class_id, l.classes, l.softmax_tree, l.class_scale, &avg_cat, l.focal_loss);
++class_count; ++class_count;
onlyclass_id = 1; onlyclass_id = 1;
break; break;
@ -240,7 +260,7 @@ void forward_region_layer(const region_layer l, network_state state)
if (best_iou > l.thresh) { if (best_iou > l.thresh) {
l.delta[index + 4] = 0; l.delta[index + 4] = 0;
if(l.classfix > 0){ if(l.classfix > 0){
delta_region_class(l.output, l.delta, index + 5, best_class_id, l.classes, l.softmax_tree, l.class_scale*(l.classfix == 2 ? l.output[index + 4] : 1), &avg_cat); delta_region_class(l.output, l.delta, index + 5, best_class_id, l.classes, l.softmax_tree, l.class_scale*(l.classfix == 2 ? l.output[index + 4] : 1), &avg_cat, l.focal_loss);
++class_count; ++class_count;
} }
} }
@ -312,7 +332,7 @@ void forward_region_layer(const region_layer l, network_state state)
int class_id = state.truth[t*5 + b*l.truths + 4]; int class_id = state.truth[t*5 + b*l.truths + 4];
if (l.map) class_id = l.map[class_id]; if (l.map) class_id = l.map[class_id];
delta_region_class(l.output, l.delta, best_index + 5, class_id, l.classes, l.softmax_tree, l.class_scale, &avg_cat); delta_region_class(l.output, l.delta, best_index + 5, class_id, l.classes, l.softmax_tree, l.class_scale, &avg_cat, l.focal_loss);
++count; ++count;
++class_count; ++class_count;
} }