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); }
void forward_detection_layer(const detection_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, 1, l.output + index + offset); } } } 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; } } if(l.random && *(state.net.seen) < 64000){ best_index = rand()%l.n; } 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(0){ float *costs = calloc(l.batch*locations*l.n, sizeof(float)); for (b = 0; b < l.batch; ++b) { int index = b*l.inputs; for (i = 0; i < locations; ++i) { for (j = 0; j < l.n; ++j) { int p_index = index + locations*l.classes + i*l.n + j; costs[b*locations*l.n + i*l.n + j] = l.delta[p_index]*l.delta[p_index]; } } } int indexes[100]; top_k(costs, l.batch*locations*l.n, 100, indexes); float cutoff = costs[indexes[99]]; for (b = 0; b < l.batch; ++b) { int index = b*l.inputs; for (i = 0; i < locations; ++i) { for (j = 0; j < l.n; ++j) { int p_index = index + locations*l.classes + i*l.n + j; if (l.delta[p_index]*l.delta[p_index] < cutoff) l.delta[p_index] = 0; } } } free(costs); } *(l.cost) = pow(mag_array(l.delta, l.outputs * l.batch), 2); if ( l.b_debug ) { printf("Detection 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); } } }