From 76e258520edb50e8bb897ba15aa9467579e70a6a Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Wed, 20 Jun 2018 10:28:25 +0000
Subject: [PATCH] Minor fix
---
src/yolo_layer.c | 61 +++++++++++++++++++++++-------
1 files changed, 46 insertions(+), 15 deletions(-)
diff --git a/src/yolo_layer.c b/src/yolo_layer.c
index a735932..f79bc41 100644
--- a/src/yolo_layer.c
+++ b/src/yolo_layer.c
@@ -55,7 +55,7 @@
l.delta_gpu = cuda_make_array(l.delta, batch*l.outputs);
#endif
- fprintf(stderr, "detection\n");
+ fprintf(stderr, "yolo\n");
srand(0);
return l;
@@ -109,18 +109,41 @@
}
-void delta_yolo_class(float *output, float *delta, int index, int class, int classes, int stride, float *avg_cat)
+void delta_yolo_class(float *output, float *delta, int index, int class_id, int classes, int stride, float *avg_cat, int focal_loss)
{
int n;
- if (delta[index]){
- delta[index + stride*class] = 1 - output[index + stride*class];
- if(avg_cat) *avg_cat += output[index + stride*class];
+ if (delta[index + stride*class_id]){
+ delta[index + stride*class_id] = 1 - output[index + stride*class_id];
+ if(avg_cat) *avg_cat += output[index + stride*class_id];
return;
}
- for(n = 0; n < classes; ++n){
- delta[index + stride*n] = ((n == class)?1 : 0) - output[index + stride*n];
- if(n == class && avg_cat) *avg_cat += output[index + stride*n];
- }
+ // Focal loss
+ if (focal_loss) {
+ // Focal Loss
+ float alpha = 0.5; // 0.25 or 0.5
+ //float gamma = 2; // hardcoded in many places of the grad-formula
+
+ int ti = index + stride*class_id;
+ float pt = output[ti] + 0.000000000000001F;
+ // http://fooplot.com/#W3sidHlwZSI6MCwiZXEiOiItKDEteCkqKDIqeCpsb2coeCkreC0xKSIsImNvbG9yIjoiIzAwMDAwMCJ9LHsidHlwZSI6MTAwMH1d
+ float grad = -(1 - pt) * (2 * pt*logf(pt) + pt - 1); // http://blog.csdn.net/linmingan/article/details/77885832
+ //float grad = (1 - pt) * (2 * pt*logf(pt) + pt - 1); // https://github.com/unsky/focal-loss
+
+ for (n = 0; n < classes; ++n) {
+ delta[index + stride*n] = (((n == class_id) ? 1 : 0) - output[index + stride*n]);
+
+ delta[index + stride*n] *= alpha*grad;
+
+ if (n == class_id) *avg_cat += output[index + stride*n];
+ }
+ }
+ else {
+ // default
+ for (n = 0; n < classes; ++n) {
+ delta[index + stride*n] = ((n == class_id) ? 1 : 0) - output[index + stride*n];
+ if (n == class_id && avg_cat) *avg_cat += output[index + stride*n];
+ }
+ }
}
static int entry_index(layer l, int batch, int location, int entry)
@@ -177,6 +200,12 @@
int best_t = 0;
for(t = 0; t < l.max_boxes; ++t){
box truth = float_to_box_stride(state.truth + t*(4 + 1) + b*l.truths, 1);
+ int class_id = state.truth[t*(4 + 1) + b*l.truths + 4];
+ if (class_id >= l.classes) {
+ printf(" Warning: in txt-labels class_id=%d >= classes=%d in cfg-file. In txt-labels class_id should be [from 0 to %d] \n", class_id, l.classes, l.classes - 1);
+ getchar();
+ continue; // if label contains class_id more than number of classes in the cfg-file
+ }
if(!truth.x) break;
float iou = box_iou(pred, truth);
if (iou > best_iou) {
@@ -193,10 +222,10 @@
if (best_iou > l.truth_thresh) {
l.delta[obj_index] = 1 - l.output[obj_index];
- int class = state.truth[best_t*(4 + 1) + b*l.truths + 4];
- if (l.map) class = l.map[class];
+ int class_id = state.truth[best_t*(4 + 1) + b*l.truths + 4];
+ if (l.map) class_id = l.map[class_id];
int class_index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 4 + 1);
- delta_yolo_class(l.output, l.delta, class_index, class, l.classes, l.w*l.h, 0);
+ delta_yolo_class(l.output, l.delta, class_index, class_id, l.classes, l.w*l.h, 0, l.focal_loss);
box truth = float_to_box_stride(state.truth + best_t*(4 + 1) + b*l.truths, 1);
delta_yolo_box(truth, l.output, l.biases, l.mask[n], box_index, i, j, l.w, l.h, state.net.w, state.net.h, l.delta, (2-truth.w*truth.h), l.w*l.h);
}
@@ -205,6 +234,8 @@
}
for(t = 0; t < l.max_boxes; ++t){
box truth = float_to_box_stride(state.truth + t*(4 + 1) + b*l.truths, 1);
+ int class_id = state.truth[t*(4 + 1) + b*l.truths + 4];
+ if (class_id >= l.classes) continue; // if label contains class_id more than number of classes in the cfg-file
if(!truth.x) break;
float best_iou = 0;
@@ -233,10 +264,10 @@
avg_obj += l.output[obj_index];
l.delta[obj_index] = 1 - l.output[obj_index];
- int class = state.truth[t*(4 + 1) + b*l.truths + 4];
- if (l.map) class = l.map[class];
+ int class_id = state.truth[t*(4 + 1) + b*l.truths + 4];
+ if (l.map) class_id = l.map[class_id];
int class_index = entry_index(l, b, mask_n*l.w*l.h + j*l.w + i, 4 + 1);
- delta_yolo_class(l.output, l.delta, class_index, class, l.classes, l.w*l.h, &avg_cat);
+ delta_yolo_class(l.output, l.delta, class_index, class_id, l.classes, l.w*l.h, &avg_cat, l.focal_loss);
++count;
++class_count;
--
Gitblit v1.10.0