void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *boxes, int only_objectness, int *map)
{
int i;
float *const predictions = l.output;
#pragma omp parallel for
for (i = 0; i < l.w*l.h; ++i){
int j, n;
int row = i / l.w;
int col = i % l.w;
for(n = 0; n < l.n; ++n){
int index = i*l.n + n;
int p_index = index * (l.classes + 5) + 4;
float scale = predictions[p_index];
if(l.classfix == -1 && scale < .5) scale = 0;
int box_index = index * (l.classes + 5);
boxes[index] = get_region_box(predictions, l.biases, n, box_index, col, row, l.w, l.h);
boxes[index].x *= w;
boxes[index].y *= h;
boxes[index].w *= w;
boxes[index].h *= h;
int class_index = index * (l.classes + 5) + 5;
if(l.softmax_tree){
hierarchy_predictions(predictions + class_index, l.classes, l.softmax_tree, 0);
int found = 0;
if(map){
for(j = 0; j < 200; ++j){
float prob = scale*predictions[class_index+map[j]];
probs[index][j] = (prob > thresh) ? prob : 0;
}
} else {
for(j = l.classes - 1; j >= 0; --j){
if(!found && predictions[class_index + j] > .5){
found = 1;
} else {
predictions[class_index + j] = 0;
}
float prob = predictions[class_index+j];
probs[index][j] = (scale > thresh) ? prob : 0;
}
}
} else {
for(j = 0; j < l.classes; ++j){
float prob = scale*predictions[class_index+j];
probs[index][j] = (prob > thresh) ? prob : 0;
}
}
if(only_objectness){
probs[index][0] = scale;
}
}
}
}
float delta_region_box(box truth, float *x, float *biases, int n, int index, int i, int j, int w, int h, float *delta, float scale, int stride)
{
box pred = get_region_box(x, biases, n, index, i, j, w, h, stride);
float iou = box_iou(pred, truth);
float tx = (truth.x*w - i);
float ty = (truth.y*h - j);
float tw = log(truth.w*w / biases[2*n]);
float th = log(truth.h*h / biases[2*n + 1]);
delta[index + 0*stride] = scale * (tx - x[index + 0*stride]);
delta[index + 1*stride] = scale * (ty - x[index + 1*stride]);
delta[index + 2*stride] = scale * (tw - x[index + 2*stride]);
delta[index + 3*stride] = scale * (th - x[index + 3*stride]);
return iou;
}
float delta_region_box(box truth, float *x, float *biases, int n, int index, int i, int j, int w, int h, float *delta, float scale)
{
box pred = get_region_box(x, biases, n, index, i, j, w, h);
float iou = box_iou(pred, truth);
float tx = (truth.x*w - i);
float ty = (truth.y*h - j);
float tw = log(truth.w / biases[2*n]);
float th = log(truth.h / biases[2*n + 1]);
if(DOABS){
tw = log(truth.w*w / biases[2*n]);
th = log(truth.h*h / biases[2*n + 1]);
}
delta[index + 0] = scale * (tx - logistic_activate(x[index + 0])) * logistic_gradient(logistic_activate(x[index + 0]));
delta[index + 1] = scale * (ty - logistic_activate(x[index + 1])) * logistic_gradient(logistic_activate(x[index + 1]));
delta[index + 2] = scale * (tw - x[index + 2]);
delta[index + 3] = scale * (th - x[index + 3]);
return iou;
}
void get_region_detections(layer l, int w, int h, int netw, int neth, float thresh, int *map, float tree_thresh, int relative, detection *dets)
{
int i, j, n, z;
float *predictions = l.output;
if (l.batch == 2) {
float *flip = l.output + l.outputs;
for (j = 0; j < l.h; ++j) {
for (i = 0; i < l.w / 2; ++i) {
for (n = 0; n < l.n; ++n) {
for (z = 0; z < l.classes + l.coords + 1; ++z) {
int i1 = z*l.w*l.h*l.n + n*l.w*l.h + j*l.w + i;
int i2 = z*l.w*l.h*l.n + n*l.w*l.h + j*l.w + (l.w - i - 1);
float swap = flip[i1];
flip[i1] = flip[i2];
flip[i2] = swap;
if (z == 0) {
flip[i1] = -flip[i1];
flip[i2] = -flip[i2];
}
}
}
}
}
for (i = 0; i < l.outputs; ++i) {
l.output[i] = (l.output[i] + flip[i]) / 2.;
}
}
for (i = 0; i < l.w*l.h; ++i) {
int row = i / l.w;
int col = i % l.w;
for (n = 0; n < l.n; ++n) {
int index = n*l.w*l.h + i;
for (j = 0; j < l.classes; ++j) {
dets[index].prob[j] = 0;
}
int obj_index = entry_index(l, 0, n*l.w*l.h + i, l.coords);
int box_index = entry_index(l, 0, n*l.w*l.h + i, 0);
int mask_index = entry_index(l, 0, n*l.w*l.h + i, 4);
float scale = l.background ? 1 : predictions[obj_index];
dets[index].bbox = get_region_box(predictions, l.biases, n, box_index, col, row, l.w, l.h);// , l.w*l.h);
dets[index].objectness = scale > thresh ? scale : 0;
if (dets[index].mask) {
for (j = 0; j < l.coords - 4; ++j) {
dets[index].mask[j] = l.output[mask_index + j*l.w*l.h];
}
}
int class_index = entry_index(l, 0, n*l.w*l.h + i, l.coords + !l.background);
if (l.softmax_tree) {
hierarchy_predictions(predictions + class_index, l.classes, l.softmax_tree, 0);// , l.w*l.h);
if (map) {
for (j = 0; j < 200; ++j) {
int class_index = entry_index(l, 0, n*l.w*l.h + i, l.coords + 1 + map[j]);
float prob = scale*predictions[class_index];
dets[index].prob[j] = (prob > thresh) ? prob : 0;
}
}
else {
int j = hierarchy_top_prediction(predictions + class_index, l.softmax_tree, tree_thresh, l.w*l.h);
dets[index].prob[j] = (scale > thresh) ? scale : 0;
}
}
else {
if (dets[index].objectness) {
for (j = 0; j < l.classes; ++j) {
int class_index = entry_index(l, 0, n*l.w*l.h + i, l.coords + 1 + j);
float prob = scale*predictions[class_index];
dets[index].prob[j] = (prob > thresh) ? prob : 0;
}
}
}
}
}
correct_region_boxes(dets, l.w*l.h*l.n, w, h, netw, neth, relative);
}
void forward_region_layer(const region_layer l, network_state state)
{
int i,j,b,t,n;
int size = l.coords + l.classes + 1;
memcpy(l.output, state.input, l.outputs*l.batch*sizeof(float));
#ifndef GPU
flatten(l.output, l.w*l.h, size*l.n, l.batch, 1);
#endif
for (b = 0; b < l.batch; ++b){
for(i = 0; i < l.h*l.w*l.n; ++i){
int index = size*i + b*l.outputs;
l.output[index + 4] = logistic_activate(l.output[index + 4]);
}
}
#ifndef GPU
if (l.softmax_tree){
for (b = 0; b < l.batch; ++b){
for(i = 0; i < l.h*l.w*l.n; ++i){
int index = size*i + b*l.outputs;
softmax_tree(l.output + index + 5, 1, 0, 1, l.softmax_tree, l.output + index + 5);
}
}
} else if (l.softmax){
for (b = 0; b < l.batch; ++b){
for(i = 0; i < l.h*l.w*l.n; ++i){
int index = size*i + b*l.outputs;
softmax(l.output + index + 5, l.classes, 1, l.output + index + 5, 1);
}
}
}
#endif
if(!state.train) return;
memset(l.delta, 0, l.outputs * l.batch * sizeof(float));
float avg_iou = 0;
float recall = 0;
float avg_cat = 0;
float avg_obj = 0;
float avg_anyobj = 0;
int count = 0;
int class_count = 0;
*(l.cost) = 0;
for (b = 0; b < l.batch; ++b) {
if(l.softmax_tree){
int onlyclass_id = 0;
for(t = 0; t < l.max_boxes; ++t){
box truth = float_to_box(state.truth + t*5 + b*l.truths);
if(!truth.x) break; // continue;
int class_id = state.truth[t*5 + b*l.truths + 4];
float maxp = 0;
int maxi = 0;
if(truth.x > 100000 && truth.y > 100000){
for(n = 0; n < l.n*l.w*l.h; ++n){
int index = size*n + b*l.outputs + 5;
float scale = l.output[index-1];
float p = scale*get_hierarchy_probability(l.output + index, l.softmax_tree, class_id);
if(p > maxp){
maxp = p;
maxi = n;
}
}
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, l.focal_loss);
++class_count;
onlyclass_id = 1;
break;
}
}
if(onlyclass_id) continue;
}
for (j = 0; j < l.h; ++j) {
for (i = 0; i < l.w; ++i) {
for (n = 0; n < l.n; ++n) {
int index = size*(j*l.w*l.n + i*l.n + n) + b*l.outputs;
box pred = get_region_box(l.output, l.biases, n, index, i, j, l.w, l.h);
float best_iou = 0;
int best_class_id = -1;
for(t = 0; t < l.max_boxes; ++t){
box truth = float_to_box(state.truth + t*5 + b*l.truths);
int class_id = state.truth[t * 5 + 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; // continue;
float iou = box_iou(pred, truth);
if (iou > best_iou) {
best_class_id = state.truth[t*5 + b*l.truths + 4];
best_iou = iou;
}
}
avg_anyobj += l.output[index + 4];
l.delta[index + 4] = l.noobject_scale * ((0 - l.output[index + 4]) * logistic_gradient(l.output[index + 4]));
if(l.classfix == -1) l.delta[index + 4] = l.noobject_scale * ((best_iou - l.output[index + 4]) * logistic_gradient(l.output[index + 4]));
else{
if (best_iou > l.thresh) {
l.delta[index + 4] = 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, l.focal_loss);
++class_count;
}
}
}
if(*(state.net.seen) < 12800){
box truth = {0};
truth.x = (i + .5)/l.w;
truth.y = (j + .5)/l.h;
truth.w = l.biases[2*n];
truth.h = l.biases[2*n+1];
if(DOABS){
truth.w = l.biases[2*n]/l.w;
truth.h = l.biases[2*n+1]/l.h;
}
delta_region_box(truth, l.output, l.biases, n, index, i, j, l.w, l.h, l.delta, .01);
}
}
}
}
for(t = 0; t < l.max_boxes; ++t){
box truth = float_to_box(state.truth + t*5 + b*l.truths);
int class_id = state.truth[t * 5 + 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; // continue;
float best_iou = 0;
int best_index = 0;
int best_n = 0;
i = (truth.x * l.w);
j = (truth.y * l.h);
//printf("%d %f %d %f\n", i, truth.x*l.w, j, truth.y*l.h);
box truth_shift = truth;
truth_shift.x = 0;
truth_shift.y = 0;
//printf("index %d %d\n",i, j);
for(n = 0; n < l.n; ++n){
int index = size*(j*l.w*l.n + i*l.n + n) + b*l.outputs;
box pred = get_region_box(l.output, l.biases, n, index, i, j, l.w, l.h);
if(l.bias_match){
pred.w = l.biases[2*n];
pred.h = l.biases[2*n+1];
if(DOABS){
pred.w = l.biases[2*n]/l.w;
pred.h = l.biases[2*n+1]/l.h;
}
}
//printf("pred: (%f, %f) %f x %f\n", pred.x, pred.y, pred.w, pred.h);
pred.x = 0;
pred.y = 0;
float iou = box_iou(pred, truth_shift);
if (iou > best_iou){
best_index = index;
best_iou = iou;
best_n = n;
}
}
//printf("%d %f (%f, %f) %f x %f\n", best_n, best_iou, truth.x, truth.y, truth.w, truth.h);
float iou = delta_region_box(truth, l.output, l.biases, best_n, best_index, i, j, l.w, l.h, l.delta, l.coord_scale);
if(iou > .5) recall += 1;
avg_iou += iou;
//l.delta[best_index + 4] = iou - l.output[best_index + 4];
avg_obj += l.output[best_index + 4];
l.delta[best_index + 4] = l.object_scale * (1 - l.output[best_index + 4]) * logistic_gradient(l.output[best_index + 4]);
if (l.rescore) {
l.delta[best_index + 4] = l.object_scale * (iou - l.output[best_index + 4]) * logistic_gradient(l.output[best_index + 4]);
}
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, l.focal_loss);
++count;
++class_count;
}
}
//printf("\n");
#ifndef GPU
flatten(l.delta, l.w*l.h, size*l.n, l.batch, 0);
#endif
*(l.cost) = pow(mag_array(l.delta, l.outputs * l.batch), 2);
printf("Region Avg IOU: %f, Class: %f, Obj: %f, No Obj: %f, Avg Recall: %f, count: %d\n", avg_iou/count, avg_cat/class_count, avg_obj/count, avg_anyobj/(l.w*l.h*l.n*l.batch), recall/count, count);
}
