github
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Added scale_x_y to [Gaussian_yolo]. Fixed blur=10;

Browse Source
pull/4269/head
AlexeyAB 6 years ago
parent fa7687e6b5
commit f8c72acd42
4 changed files with 48 additions and 33 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 8
      src/data.c
  2. 67
      src/gaussian_yolo_layer.c
  3. 5
      src/image_opencv.cpp
  4. 1
      src/parser.c

8
src/data.c
Unescape View File

@ -875,7 +875,11 @@ data load_data_detection(int n, char **paths, int m, int w, int h, int c, int bo
dexp = rand_scale(exposure); dexp = rand_scale(exposure);
flip = use_flip ? random_gen() % 2 : 0; flip = use_flip ? random_gen() % 2 : 0;
blur = rand_int(0, 1) ? (use_blur) : 0;
//blur = rand_int(0, 1) ? (use_blur) : 0;
int tmp_blur = rand_int(0, 2); // 0 - disable, 1 - blur background, 2 - blur the whole image
if (tmp_blur == 2) blur = use_blur;
else blur = tmp_blur;
} }
int pleft = rand_precalc_random(-dw, dw, r1); int pleft = rand_precalc_random(-dw, dw, r1);
@ -922,7 +926,7 @@ data load_data_detection(int n, char **paths, int m, int w, int h, int c, int bo
int min_w_h = fill_truth_detection(filename, boxes, truth, classes, flip, dx, dy, 1. / sx, 1. / sy, w, h); int min_w_h = fill_truth_detection(filename, boxes, truth, classes, flip, dx, dy, 1. / sx, 1. / sy, w, h);
if (min_w_h/4 < blur) blur = min_w_h / 4; // disable blur if one of the objects is too small if (min_w_h/4 < blur && blur > 1) blur = min_w_h / 4; // disable blur if one of the objects is too small
image ai = image_data_augmentation(src, w, h, pleft, ptop, swidth, sheight, flip, dhue, dsat, dexp, image ai = image_data_augmentation(src, w, h, pleft, ptop, swidth, sheight, flip, dhue, dsat, dexp,
blur, boxes, d.y.vals[i]); blur, boxes, d.y.vals[i]);

67
src/gaussian_yolo_layer.c
Unescape View File

@ -95,8 +95,8 @@ void resize_gaussian_yolo_layer(layer *l, int w, int h)
l->outputs = h*w*l->n*(l->classes + 8 + 1); l->outputs = h*w*l->n*(l->classes + 8 + 1);
l->inputs = l->outputs; l->inputs = l->outputs;
l->output = realloc(l->output, l->batch*l->outputs * sizeof(float)); l->output = (float *)realloc(l->output, l->batch*l->outputs * sizeof(float));
l->delta = realloc(l->delta, l->batch*l->outputs * sizeof(float)); l->delta = (float *)realloc(l->delta, l->batch*l->outputs * sizeof(float));
//if (!l->output_pinned) l->output = (float*)realloc(l->output, l->batch*l->outputs * sizeof(float)); //if (!l->output_pinned) l->output = (float*)realloc(l->output, l->batch*l->outputs * sizeof(float));
//if (!l->delta_pinned) l->delta = (float*)realloc(l->delta, l->batch*l->outputs * sizeof(float)); //if (!l->delta_pinned) l->delta = (float*)realloc(l->delta, l->batch*l->outputs * sizeof(float));
@ -187,17 +187,17 @@ float delta_gaussian_yolo_box(box truth, float *x, float *biases, int n, int ind
} }
void delta_gaussian_yolo_class(float *output, float *delta, int index, int class, int classes, int stride, float *avg_cat) void delta_gaussian_yolo_class(float *output, float *delta, int index, int class_id, int classes, int stride, float *avg_cat)
{ {
int n; int n;
if (delta[index]){ if (delta[index]){
delta[index + stride*class] = 1 - output[index + stride*class]; delta[index + stride*class_id] = 1 - output[index + stride*class_id];
if(avg_cat) *avg_cat += output[index + stride*class]; if(avg_cat) *avg_cat += output[index + stride*class_id];
return; return;
} }
for(n = 0; n < classes; ++n){ for(n = 0; n < classes; ++n){
delta[index + stride*n] = ((n == class)?1 : 0) - output[index + stride*n]; delta[index + stride*n] = ((n == class_id)?1 : 0) - output[index + stride*n];
if(n == class && avg_cat) *avg_cat += output[index + stride*n]; if(n == class_id && avg_cat) *avg_cat += output[index + stride*n];
} }
} }
@ -219,9 +219,11 @@ void forward_gaussian_yolo_layer(const layer l, network_state state)
// x : mu, sigma // x : mu, sigma
int index = entry_gaussian_index(l, b, n*l.w*l.h, 0); int index = entry_gaussian_index(l, b, n*l.w*l.h, 0);
activate_array(l.output + index, 2*l.w*l.h, LOGISTIC); activate_array(l.output + index, 2*l.w*l.h, LOGISTIC);
scal_add_cpu(l.w*l.h, l.scale_x_y, -0.5*(l.scale_x_y - 1), l.output + index, 1); // scale x
// y : mu, sigma // y : mu, sigma
index = entry_gaussian_index(l, b, n*l.w*l.h, 2); index = entry_gaussian_index(l, b, n*l.w*l.h, 2);
activate_array(l.output + index, 2*l.w*l.h, LOGISTIC); activate_array(l.output + index, 2*l.w*l.h, LOGISTIC);
scal_add_cpu(l.w*l.h, l.scale_x_y, -0.5*(l.scale_x_y - 1), l.output + index, 1); // scale y
// w : sigma // w : sigma
index = entry_gaussian_index(l, b, n*l.w*l.h, 5); index = entry_gaussian_index(l, b, n*l.w*l.h, 5);
activate_array(l.output + index, l.w*l.h, LOGISTIC); activate_array(l.output + index, l.w*l.h, LOGISTIC);
@ -272,10 +274,10 @@ void forward_gaussian_yolo_layer(const layer l, network_state state)
if (best_iou > l.truth_thresh) { if (best_iou > l.truth_thresh) {
l.delta[obj_index] = 1 - l.output[obj_index]; l.delta[obj_index] = 1 - l.output[obj_index];
int class = state.truth[best_t*(4 + 1) + b*l.truths + 4]; int class_id = state.truth[best_t*(4 + 1) + b*l.truths + 4];
if (l.map) class = l.map[class]; if (l.map) class_id = l.map[class_id];
int class_index = entry_gaussian_index(l, b, n*l.w*l.h + j*l.w + i, 9); int class_index = entry_gaussian_index(l, b, n*l.w*l.h + j*l.w + i, 9);
delta_gaussian_yolo_class(l.output, l.delta, class_index, class, l.classes, l.w*l.h, 0); delta_gaussian_yolo_class(l.output, l.delta, class_index, class_id, l.classes, l.w*l.h, 0);
box truth = float_to_box_stride(state.truth + best_t*(4 + 1) + b*l.truths, 1); box truth = float_to_box_stride(state.truth + best_t*(4 + 1) + b*l.truths, 1);
delta_gaussian_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); delta_gaussian_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);
} }
@ -312,10 +314,10 @@ void forward_gaussian_yolo_layer(const layer l, network_state state)
avg_obj += l.output[obj_index]; avg_obj += l.output[obj_index];
l.delta[obj_index] = 1 - l.output[obj_index]; l.delta[obj_index] = 1 - l.output[obj_index];
int class = state.truth[t*(4 + 1) + b*l.truths + 4]; int class_id = state.truth[t*(4 + 1) + b*l.truths + 4];
if (l.map) class = l.map[class]; if (l.map) class_id = l.map[class_id];
int class_index = entry_gaussian_index(l, b, mask_n*l.w*l.h + j*l.w + i, 9); int class_index = entry_gaussian_index(l, b, mask_n*l.w*l.h + j*l.w + i, 9);
delta_gaussian_yolo_class(l.output, l.delta, class_index, class, l.classes, l.w*l.h, &avg_cat); delta_gaussian_yolo_class(l.output, l.delta, class_index, class_id, l.classes, l.w*l.h, &avg_cat);
++count; ++count;
++class_count; ++class_count;
@ -433,24 +435,27 @@ int get_gaussian_yolo_detections(layer l, int w, int h, int netw, int neth, floa
for(n = 0; n < l.n; ++n){ for(n = 0; n < l.n; ++n){
int obj_index = entry_gaussian_index(l, 0, n*l.w*l.h + i, 8); int obj_index = entry_gaussian_index(l, 0, n*l.w*l.h + i, 8);
float objectness = predictions[obj_index]; float objectness = predictions[obj_index];
if(objectness <= thresh) continue; if (objectness <= thresh) continue; // incorrect behavior for Nan values
int box_index = entry_gaussian_index(l, 0, n*l.w*l.h + i, 0);
dets[count].bbox = get_gaussian_yolo_box(predictions, l.biases, l.mask[n], box_index, col, row, l.w, l.h, netw, neth, l.w*l.h); if (objectness > thresh) {
dets[count].objectness = objectness; int box_index = entry_gaussian_index(l, 0, n*l.w*l.h + i, 0);
dets[count].classes = l.classes; dets[count].bbox = get_gaussian_yolo_box(predictions, l.biases, l.mask[n], box_index, col, row, l.w, l.h, netw, neth, l.w*l.h);
dets[count].objectness = objectness;
dets[count].uc[0] = predictions[entry_gaussian_index(l, 0, n*l.w*l.h + i, 1)]; // tx uncertainty dets[count].classes = l.classes;
dets[count].uc[1] = predictions[entry_gaussian_index(l, 0, n*l.w*l.h + i, 3)]; // ty uncertainty
dets[count].uc[2] = predictions[entry_gaussian_index(l, 0, n*l.w*l.h + i, 5)]; // tw uncertainty dets[count].uc[0] = predictions[entry_gaussian_index(l, 0, n*l.w*l.h + i, 1)]; // tx uncertainty
dets[count].uc[3] = predictions[entry_gaussian_index(l, 0, n*l.w*l.h + i, 7)]; // th uncertainty dets[count].uc[1] = predictions[entry_gaussian_index(l, 0, n*l.w*l.h + i, 3)]; // ty uncertainty
dets[count].uc[2] = predictions[entry_gaussian_index(l, 0, n*l.w*l.h + i, 5)]; // tw uncertainty
for(j = 0; j < l.classes; ++j){ dets[count].uc[3] = predictions[entry_gaussian_index(l, 0, n*l.w*l.h + i, 7)]; // th uncertainty
int class_index = entry_gaussian_index(l, 0, n*l.w*l.h + i, 9 + j);
float uc_aver = (dets[count].uc[0] + dets[count].uc[1] + dets[count].uc[2] + dets[count].uc[3]) / 4.0; for (j = 0; j < l.classes; ++j) {
float prob = objectness*predictions[class_index]*(1.0-uc_aver); int class_index = entry_gaussian_index(l, 0, n*l.w*l.h + i, 9 + j);
dets[count].prob[j] = (prob > thresh) ? prob : 0; float uc_aver = (dets[count].uc[0] + dets[count].uc[1] + dets[count].uc[2] + dets[count].uc[3]) / 4.0;
float prob = objectness*predictions[class_index] * (1.0 - uc_aver);
dets[count].prob[j] = (prob > thresh) ? prob : 0;
}
++count;
} }
++count;
} }
} }
correct_gaussian_yolo_boxes(dets, count, w, h, netw, neth, relative, letter); correct_gaussian_yolo_boxes(dets, count, w, h, netw, neth, relative, letter);
@ -470,9 +475,11 @@ void forward_gaussian_yolo_layer_gpu(const layer l, network_state state)
// x : mu, sigma // x : mu, sigma
int index = entry_gaussian_index(l, b, n*l.w*l.h, 0); int index = entry_gaussian_index(l, b, n*l.w*l.h, 0);
activate_array_ongpu(l.output_gpu + index, 2*l.w*l.h, LOGISTIC); activate_array_ongpu(l.output_gpu + index, 2*l.w*l.h, LOGISTIC);
scal_add_ongpu(l.w*l.h, l.scale_x_y, -0.5*(l.scale_x_y - 1), l.output_gpu + index, 1); // scale x
// y : mu, sigma // y : mu, sigma
index = entry_gaussian_index(l, b, n*l.w*l.h, 2); index = entry_gaussian_index(l, b, n*l.w*l.h, 2);
activate_array_ongpu(l.output_gpu + index, 2*l.w*l.h, LOGISTIC); activate_array_ongpu(l.output_gpu + index, 2*l.w*l.h, LOGISTIC);
scal_add_ongpu(l.w*l.h, l.scale_x_y, -0.5*(l.scale_x_y - 1), l.output_gpu + index, 1); // scale y
// w : sigma // w : sigma
index = entry_gaussian_index(l, b, n*l.w*l.h, 5); index = entry_gaussian_index(l, b, n*l.w*l.h, 5);
activate_array_ongpu(l.output_gpu + index, l.w*l.h, LOGISTIC); activate_array_ongpu(l.output_gpu + index, l.w*l.h, LOGISTIC);

5
src/image_opencv.cpp
Unescape View File

@ -1196,7 +1196,10 @@ image image_data_augmentation(mat_cv* mat, int w, int h,
if (blur) { if (blur) {
cv::Mat dst(sized.size(), sized.type()); cv::Mat dst(sized.size(), sized.type());
if(blur == 1) cv::GaussianBlur(sized, dst, cv::Size(31, 31), 0); if (blur == 1) {
//cv::GaussianBlur(sized, dst, cv::Size(31, 31), 0);
cv::bilateralFilter(sized, dst, 31, 75, 75);
}
else { else {
int ksize = (blur / 2) * 2 + 1; int ksize = (blur / 2) * 2 + 1;
cv::Size kernel_size = cv::Size(ksize, ksize); cv::Size kernel_size = cv::Size(ksize, ksize);

1
src/parser.c
Unescape View File

@ -433,6 +433,7 @@ layer parse_gaussian_yolo(list *options, size_params params) // Gaussian_YOLOv3
layer l = make_gaussian_yolo_layer(params.batch, params.w, params.h, num, total, mask, classes, max_boxes); layer l = make_gaussian_yolo_layer(params.batch, params.w, params.h, num, total, mask, classes, max_boxes);
assert(l.outputs == params.inputs); assert(l.outputs == params.inputs);
l.scale_x_y = option_find_float_quiet(options, "scale_x_y", 1);
l.max_boxes = option_find_int_quiet(options, "max", 90); l.max_boxes = option_find_int_quiet(options, "max", 90);
l.jitter = option_find_float(options, "jitter", .2); l.jitter = option_find_float(options, "jitter", .2);

Write Preview
Loading…
Cancel
Save