#include "region_layer.h"
|
#include "activations.h"
|
#include "softmax_layer.h"
|
#include "blas.h"
|
#include "box.h"
|
#include "cuda.h"
|
#include "utils.h"
|
#include <stdio.h>
|
#include <assert.h>
|
#include <string.h>
|
#include <stdlib.h>
|
|
region_layer make_region_layer(int batch, int inputs, int n, int side, int classes, int coords, int rescore)
|
{
|
region_layer l = {0};
|
l.type = REGION;
|
|
l.n = n;
|
l.batch = batch;
|
l.inputs = inputs;
|
l.classes = classes;
|
l.coords = coords;
|
l.rescore = rescore;
|
l.side = side;
|
assert(side*side*((1 + l.coords)*l.n + l.classes) == inputs);
|
l.cost = calloc(1, sizeof(float));
|
l.outputs = l.inputs;
|
l.truths = l.side*l.side*(1+l.coords+l.classes);
|
l.output = calloc(batch*l.outputs, sizeof(float));
|
l.delta = calloc(batch*l.outputs, sizeof(float));
|
#ifdef GPU
|
l.output_gpu = cuda_make_array(l.output, batch*l.outputs);
|
l.delta_gpu = cuda_make_array(l.delta, batch*l.outputs);
|
#endif
|
|
fprintf(stderr, "Region Layer\n");
|
srand(0);
|
|
return l;
|
}
|
|
void forward_region_layer(const region_layer l, network_state state)
|
{
|
int locations = l.side*l.side;
|
int i,j;
|
memcpy(l.output, state.input, l.outputs*l.batch*sizeof(float));
|
int b;
|
if (l.softmax){
|
for(b = 0; b < l.batch; ++b){
|
int index = b*l.inputs;
|
for (i = 0; i < locations; ++i) {
|
int offset = i*l.classes;
|
softmax_array(l.output + index + offset, l.classes,
|
l.output + index + offset);
|
}
|
int offset = locations*l.classes;
|
activate_array(l.output + index + offset, locations*l.n*(1+l.coords), LOGISTIC);
|
}
|
}
|
if (l.object_logistic) {
|
for(b = 0; b < l.batch; ++b){
|
int index = b*l.inputs;
|
int p_index = index + locations*l.classes;
|
activate_array(l.output + p_index, locations*l.n, LOGISTIC);
|
}
|
}
|
|
if (l.coord_logistic) {
|
for(b = 0; b < l.batch; ++b){
|
int index = b*l.inputs;
|
int coord_index = index + locations*(l.classes + l.n);
|
activate_array(l.output + coord_index, locations*l.n*l.coords, LOGISTIC);
|
}
|
}
|
|
if (l.class_logistic) {
|
for(b = 0; b < l.batch; ++b){
|
int class_index = b*l.inputs;
|
activate_array(l.output + class_index, locations*l.classes, LOGISTIC);
|
}
|
}
|
|
if(state.train){
|
float avg_iou = 0;
|
float avg_cat = 0;
|
float avg_allcat = 0;
|
float avg_obj = 0;
|
float avg_anyobj = 0;
|
int count = 0;
|
*(l.cost) = 0;
|
int size = l.inputs * l.batch;
|
memset(l.delta, 0, size * sizeof(float));
|
for (b = 0; b < l.batch; ++b){
|
int index = b*l.inputs;
|
for (i = 0; i < locations; ++i) {
|
int truth_index = (b*locations + i)*(1+l.coords+l.classes);
|
int is_obj = state.truth[truth_index];
|
for (j = 0; j < l.n; ++j) {
|
int p_index = index + locations*l.classes + i*l.n + j;
|
l.delta[p_index] = l.noobject_scale*(0 - l.output[p_index]);
|
*(l.cost) += l.noobject_scale*pow(l.output[p_index], 2);
|
avg_anyobj += l.output[p_index];
|
}
|
|
int best_index = -1;
|
float best_iou = 0;
|
float best_rmse = 20;
|
|
if (!is_obj){
|
continue;
|
}
|
|
int class_index = index + i*l.classes;
|
for(j = 0; j < l.classes; ++j) {
|
l.delta[class_index+j] = l.class_scale * (state.truth[truth_index+1+j] - l.output[class_index+j]);
|
*(l.cost) += l.class_scale * pow(state.truth[truth_index+1+j] - l.output[class_index+j], 2);
|
if(state.truth[truth_index + 1 + j]) avg_cat += l.output[class_index+j];
|
avg_allcat += l.output[class_index+j];
|
}
|
|
box truth = float_to_box(state.truth + truth_index + 1 + l.classes);
|
truth.x /= l.side;
|
truth.y /= l.side;
|
|
for(j = 0; j < l.n; ++j){
|
int box_index = index + locations*(l.classes + l.n) + (i*l.n + j) * l.coords;
|
box out = float_to_box(l.output + box_index);
|
out.x /= l.side;
|
out.y /= l.side;
|
|
if (l.sqrt){
|
out.w = out.w*out.w;
|
out.h = out.h*out.h;
|
}
|
|
float iou = box_iou(out, truth);
|
//iou = 0;
|
float rmse = box_rmse(out, truth);
|
if(best_iou > 0 || iou > 0){
|
if(iou > best_iou){
|
best_iou = iou;
|
best_index = j;
|
}
|
}else{
|
if(rmse < best_rmse){
|
best_rmse = rmse;
|
best_index = j;
|
}
|
}
|
}
|
|
if(l.forced){
|
if(truth.w*truth.h < .1){
|
best_index = 1;
|
}else{
|
best_index = 0;
|
}
|
}
|
|
int box_index = index + locations*(l.classes + l.n) + (i*l.n + best_index) * l.coords;
|
int tbox_index = truth_index + 1 + l.classes;
|
|
box out = float_to_box(l.output + box_index);
|
out.x /= l.side;
|
out.y /= l.side;
|
if (l.sqrt) {
|
out.w = out.w*out.w;
|
out.h = out.h*out.h;
|
}
|
float iou = box_iou(out, truth);
|
|
//printf("%d", best_index);
|
int p_index = index + locations*l.classes + i*l.n + best_index;
|
*(l.cost) -= l.noobject_scale * pow(l.output[p_index], 2);
|
*(l.cost) += l.object_scale * pow(1-l.output[p_index], 2);
|
avg_obj += l.output[p_index];
|
l.delta[p_index] = l.object_scale * (1.-l.output[p_index]);
|
|
if(l.rescore){
|
l.delta[p_index] = l.object_scale * (iou - l.output[p_index]);
|
}
|
|
l.delta[box_index+0] = l.coord_scale*(state.truth[tbox_index + 0] - l.output[box_index + 0]);
|
l.delta[box_index+1] = l.coord_scale*(state.truth[tbox_index + 1] - l.output[box_index + 1]);
|
l.delta[box_index+2] = l.coord_scale*(state.truth[tbox_index + 2] - l.output[box_index + 2]);
|
l.delta[box_index+3] = l.coord_scale*(state.truth[tbox_index + 3] - l.output[box_index + 3]);
|
if(l.sqrt){
|
l.delta[box_index+2] = l.coord_scale*(sqrt(state.truth[tbox_index + 2]) - l.output[box_index + 2]);
|
l.delta[box_index+3] = l.coord_scale*(sqrt(state.truth[tbox_index + 3]) - l.output[box_index + 3]);
|
}
|
|
*(l.cost) += pow(1-iou, 2);
|
avg_iou += iou;
|
++count;
|
}
|
if(l.softmax){
|
gradient_array(l.output + index + locations*l.classes, locations*l.n*(1+l.coords),
|
LOGISTIC, l.delta + index + locations*l.classes);
|
}
|
if (l.object_logistic) {
|
int p_index = index + locations*l.classes;
|
gradient_array(l.output + p_index, locations*l.n, LOGISTIC, l.delta + p_index);
|
}
|
|
if (l.class_logistic) {
|
int class_index = index;
|
gradient_array(l.output + class_index, locations*l.classes, LOGISTIC, l.delta + class_index);
|
}
|
|
if (l.coord_logistic) {
|
int coord_index = index + locations*(l.classes + l.n);
|
gradient_array(l.output + coord_index, locations*l.n*l.coords, LOGISTIC, l.delta + coord_index);
|
}
|
//printf("\n");
|
}
|
printf("Region Avg IOU: %f, Pos Cat: %f, All Cat: %f, Pos Obj: %f, Any Obj: %f, count: %d\n", avg_iou/count, avg_cat/count, avg_allcat/(count*l.classes), avg_obj/count, avg_anyobj/(l.batch*locations*l.n), count);
|
}
|
}
|
|
void backward_region_layer(const region_layer l, network_state state)
|
{
|
axpy_cpu(l.batch*l.inputs, 1, l.delta, 1, state.delta, 1);
|
}
|
|
#ifdef GPU
|
|
void forward_region_layer_gpu(const region_layer l, network_state state)
|
{
|
float *in_cpu = calloc(l.batch*l.inputs, sizeof(float));
|
float *truth_cpu = 0;
|
if(state.truth){
|
int num_truth = l.batch*l.side*l.side*(1+l.coords+l.classes);
|
truth_cpu = calloc(num_truth, sizeof(float));
|
cuda_pull_array(state.truth, truth_cpu, num_truth);
|
}
|
cuda_pull_array(state.input, in_cpu, l.batch*l.inputs);
|
network_state cpu_state;
|
cpu_state.train = state.train;
|
cpu_state.truth = truth_cpu;
|
cpu_state.input = in_cpu;
|
forward_region_layer(l, cpu_state);
|
cuda_push_array(l.output_gpu, l.output, l.batch*l.outputs);
|
cuda_push_array(l.delta_gpu, l.delta, l.batch*l.inputs);
|
free(cpu_state.input);
|
if(cpu_state.truth) free(cpu_state.truth);
|
}
|
|
void backward_region_layer_gpu(region_layer l, network_state state)
|
{
|
axpy_ongpu(l.batch*l.inputs, 1, l.delta_gpu, 1, state.delta, 1);
|
//copy_ongpu(l.batch*l.inputs, l.delta_gpu, 1, state.delta, 1);
|
}
|
#endif
|
