Try to use avx_hs() - slow and requires alignment 4096 bits < (l.size*l.siz...

AlexeyAB

2018-08-08 a284a7da8d1facbf984a22302665a2a50295a687

 src/detection_layer.h

@@ -10,6 +10,7 @@
void forward_detection_layer(const detection_layer l, network_state state);
void backward_detection_layer(const detection_layer l, network_state state);
void get_detection_boxes(layer l, int w, int h, float thresh, float **probs, box *boxes, int only_objectness);
void get_detection_detections(layer l, int w, int h, float thresh, detection *dets);

#ifdef GPU
void forward_detection_layer_gpu(const detection_layer l, network_state state);