void forward_yolo_layer(const layer l, network_state state)
{
int i, j, b, t, n;
memcpy(l.output, state.input, l.outputs*l.batch * sizeof(float));
#ifndef GPU
for (b = 0; b < l.batch; ++b) {
for (n = 0; n < l.n; ++n) {
int index = entry_index(l, b, n*l.w*l.h, 0);
activate_array(l.output + index, 2 * l.w*l.h, LOGISTIC);
scal_add_cpu(2 * l.w*l.h, l.scale_x_y, -0.5*(l.scale_x_y - 1), l.output + index, 1);
index = entry_index(l, b, n*l.w*l.h, 4);
activate_array(l.output + index, (1 + l.classes)*l.w*l.h, LOGISTIC);
}
}
#endif
memset(l.delta, 0, l.outputs * l.batch * sizeof(float));
if (!state.train) return;
float tot_iou = 0;
float tot_giou = 0;
float tot_diou = 0;
float tot_ciou = 0;
float tot_iou_loss = 0;
float tot_giou_loss = 0;
float tot_diou_loss = 0;
float tot_ciou_loss = 0;
float recall = 0;
float recall75 = 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) {
for (j = 0; j < l.h; ++j) {
for (i = 0; i < l.w; ++i) {
for (n = 0; n < l.n; ++n) {
int box_index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 0);
box pred = get_yolo_box(l.output, l.biases, l.mask[n], box_index, i, j, l.w, l.h, state.net.w, state.net.h, l.w*l.h);
float best_match_iou = 0;
int best_match_t = 0;
float best_iou = 0;
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 || class_id < 0) {
printf("\n 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);
printf("\n truth.x = %f, truth.y = %f, truth.w = %f, truth.h = %f, class_id = %d \n", truth.x, truth.y, truth.w, truth.h, class_id);
if (check_mistakes) getchar();
continue;
}
if (!truth.x) break;
int class_index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 4 + 1);
int obj_index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 4);
float objectness = l.output[obj_index];
if (isnan(objectness) || isinf(objectness)) l.output[obj_index] = 0;
int class_id_match = compare_yolo_class(l.output, l.classes, class_index, l.w*l.h, objectness, class_id, 0.25f);
float iou = box_iou(pred, truth);
if (iou > best_match_iou && class_id_match == 1) {
best_match_iou = iou;
best_match_t = t;
}
if (iou > best_iou) {
best_iou = iou;
best_t = t;
}
}
int obj_index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 4);
avg_anyobj += l.output[obj_index];
l.delta[obj_index] = l.cls_normalizer * (0 - l.output[obj_index]);
if (best_match_iou > l.ignore_thresh) {
l.delta[obj_index] = 0;
}
else if (state.net.adversarial) {
int class_index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 4 + 1);
int stride = l.w*l.h;
float scale = pred.w * pred.h;
if (scale > 0) scale = sqrt(scale);
l.delta[obj_index] = scale * l.cls_normalizer * (0 - l.output[obj_index]);
int cl_id;
for (cl_id = 0; cl_id < l.classes; ++cl_id) {
if(l.output[class_index + stride*cl_id] * l.output[obj_index] > 0.25)
l.delta[class_index + stride*cl_id] = scale * (0 - l.output[class_index + stride*cl_id]);
}
}
if (best_iou > l.truth_thresh) {
l.delta[obj_index] = l.cls_normalizer * (1 - l.output[obj_index]);
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_id, l.classes, l.w*l.h, 0, l.focal_loss, l.label_smooth_eps, l.classes_multipliers);
box truth = float_to_box_stride(state.truth + best_t*(4 + 1) + b*l.truths, 1);
const float class_multiplier = (l.classes_multipliers) ? l.classes_multipliers[class_id] : 1.0f;
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, l.iou_normalizer * class_multiplier, l.iou_loss, 1, l.max_delta);
}
}
}
}
for (t = 0; t < l.max_boxes; ++t) {
box truth = float_to_box_stride(state.truth + t*(4 + 1) + b*l.truths, 1);
if (truth.x < 0 || truth.y < 0 || truth.x > 1 || truth.y > 1 || truth.w < 0 || truth.h < 0) {
char buff[256];
printf(" Wrong label: truth.x = %f, truth.y = %f, truth.w = %f, truth.h = %f \n", truth.x, truth.y, truth.w, truth.h);
sprintf(buff, "echo \"Wrong label: truth.x = %f, truth.y = %f, truth.w = %f, truth.h = %f\" >> bad_label.list",
truth.x, truth.y, truth.w, truth.h);
system(buff);
}
int class_id = state.truth[t*(4 + 1) + b*l.truths + 4];
if (class_id >= l.classes || class_id < 0) continue;
if (!truth.x) break;
float best_iou = 0;
int best_n = 0;
i = (truth.x * l.w);
j = (truth.y * l.h);
box truth_shift = truth;
truth_shift.x = truth_shift.y = 0;
for (n = 0; n < l.total; ++n) {
box pred = { 0 };
pred.w = l.biases[2 * n] / state.net.w;
pred.h = l.biases[2 * n + 1] / state.net.h;
float iou = box_iou(pred, truth_shift);
if (iou > best_iou) {
best_iou = iou;
best_n = n;
}
}
int mask_n = int_index(l.mask, best_n, l.n);
if (mask_n >= 0) {
int class_id = state.truth[t*(4 + 1) + b*l.truths + 4];
if (l.map) class_id = l.map[class_id];
int box_index = entry_index(l, b, mask_n*l.w*l.h + j*l.w + i, 0);
const float class_multiplier = (l.classes_multipliers) ? l.classes_multipliers[class_id] : 1.0f;
ious all_ious = delta_yolo_box(truth, l.output, l.biases, best_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, l.iou_normalizer * class_multiplier, l.iou_loss, 1, l.max_delta);
tot_iou += all_ious.iou;
tot_iou_loss += 1 - all_ious.iou;
tot_giou += all_ious.giou;
tot_giou_loss += 1 - all_ious.giou;
tot_diou += all_ious.diou;
tot_diou_loss += 1 - all_ious.diou;
tot_ciou += all_ious.ciou;
tot_ciou_loss += 1 - all_ious.ciou;
int obj_index = entry_index(l, b, mask_n*l.w*l.h + j*l.w + i, 4);
avg_obj += l.output[obj_index];
l.delta[obj_index] = class_multiplier * l.cls_normalizer * (1 - l.output[obj_index]);
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_id, l.classes, l.w*l.h, &avg_cat, l.focal_loss, l.label_smooth_eps, l.classes_multipliers);
++count;
++class_count;
if (all_ious.iou > .5) recall += 1;
if (all_ious.iou > .75) recall75 += 1;
}
for (n = 0; n < l.total; ++n) {
int mask_n = int_index(l.mask, n, l.n);
if (mask_n >= 0 && n != best_n && l.iou_thresh < 1.0f) {
box pred = { 0 };
pred.w = l.biases[2 * n] / state.net.w;
pred.h = l.biases[2 * n + 1] / state.net.h;
float iou = box_iou_kind(pred, truth_shift, l.iou_thresh_kind);
if (iou > l.iou_thresh) {
int class_id = state.truth[t*(4 + 1) + b*l.truths + 4];
if (l.map) class_id = l.map[class_id];
int box_index = entry_index(l, b, mask_n*l.w*l.h + j*l.w + i, 0);
const float class_multiplier = (l.classes_multipliers) ? l.classes_multipliers[class_id] : 1.0f;
ious all_ious = delta_yolo_box(truth, l.output, l.biases, 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, l.iou_normalizer * class_multiplier, l.iou_loss, 1, l.max_delta);
tot_iou += all_ious.iou;
tot_iou_loss += 1 - all_ious.iou;
tot_giou += all_ious.giou;
tot_giou_loss += 1 - all_ious.giou;
tot_diou += all_ious.diou;
tot_diou_loss += 1 - all_ious.diou;
tot_ciou += all_ious.ciou;
tot_ciou_loss += 1 - all_ious.ciou;
int obj_index = entry_index(l, b, mask_n*l.w*l.h + j*l.w + i, 4);
avg_obj += l.output[obj_index];
l.delta[obj_index] = class_multiplier * l.cls_normalizer * (1 - l.output[obj_index]);
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_id, l.classes, l.w*l.h, &avg_cat, l.focal_loss, l.label_smooth_eps, l.classes_multipliers);
++count;
++class_count;
if (all_ious.iou > .5) recall += 1;
if (all_ious.iou > .75) recall75 += 1;
}
}
}
}
for (j = 0; j < l.h; ++j) {
for (i = 0; i < l.w; ++i) {
for (n = 0; n < l.n; ++n) {
int box_index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 0);
int class_index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 4 + 1);
const int stride = l.w*l.h;
averages_yolo_deltas(class_index, box_index, stride, l.classes, l.delta);
}
}
}
}
if (count == 0) count = 1;
if (class_count == 0) class_count = 1;
int stride = l.w*l.h;
float* no_iou_loss_delta = (float *)calloc(l.batch * l.outputs, sizeof(float));
memcpy(no_iou_loss_delta, l.delta, l.batch * l.outputs * sizeof(float));
for (b = 0; b < l.batch; ++b) {
for (j = 0; j < l.h; ++j) {
for (i = 0; i < l.w; ++i) {
for (n = 0; n < l.n; ++n) {
int index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 0);
no_iou_loss_delta[index + 0 * stride] = 0;
no_iou_loss_delta[index + 1 * stride] = 0;
no_iou_loss_delta[index + 2 * stride] = 0;
no_iou_loss_delta[index + 3 * stride] = 0;
}
}
}
}
float classification_loss = l.cls_normalizer * pow(mag_array(no_iou_loss_delta, l.outputs * l.batch), 2);
free(no_iou_loss_delta);
float loss = pow(mag_array(l.delta, l.outputs * l.batch), 2);
float iou_loss = loss - classification_loss;
float avg_iou_loss = 0;
if (l.iou_loss == MSE) {
*(l.cost) = pow(mag_array(l.delta, l.outputs * l.batch), 2);
}
else {
if (l.iou_loss == GIOU) {
avg_iou_loss = count > 0 ? l.iou_normalizer * (tot_giou_loss / count) : 0;
}
else {
avg_iou_loss = count > 0 ? l.iou_normalizer * (tot_iou_loss / count) : 0;
}
*(l.cost) = avg_iou_loss + classification_loss;
}
loss /= l.batch;
classification_loss /= l.batch;
iou_loss /= l.batch;
fprintf(stderr, "v3 (%s loss, Normalizer: (iou: %.2f, cls: %.2f) Region %d Avg (IOU: %f, GIOU: %f), Class: %f, Obj: %f, No Obj: %f, .5R: %f, .75R: %f, count: %d, class_loss = %f, iou_loss = %f, total_loss = %f \n",
(l.iou_loss == MSE ? "mse" : (l.iou_loss == GIOU ? "giou" : "iou")), l.iou_normalizer, l.cls_normalizer, state.index, tot_iou / count, tot_giou / count, avg_cat / class_count, avg_obj / count, avg_anyobj / (l.w*l.h*l.n*l.batch), recall / count, recall75 / count, count,
classification_loss, iou_loss, loss);
}