void label_classifier(char *datacfg, char *filename, char *weightfile)
{
int i;
network *net = load_network(filename, weightfile, 0);
set_batch_network(net, 1);
srand(time(0));
list *options = read_data_cfg(datacfg);
char *label_list = option_find_str(options, "names", "data/labels.list");
char *test_list = option_find_str(options, "test", "data/train.list");
int classes = option_find_int(options, "classes", 2);
char **labels = get_labels(label_list);
list *plist = get_paths(test_list);
char **paths = (char **)list_to_array(plist);
int m = plist->size;
free_list(plist);
for(i = 0; i < m; ++i){
image im = load_image_color(paths[i], 0, 0);
image resized = resize_min(im, net->w);
image crop = crop_image(resized, (resized.w - net->w)/2, (resized.h - net->h)/2, net->w, net->h);
float *pred = network_predict(net, crop.data);
if(resized.data != im.data) free_image(resized);
free_image(im);
free_image(crop);
int ind = max_index(pred, classes);
printf("%s\n", labels[ind]);
}
}
void PixelsMovement::getDraggedImageCopy(base::UniquePtr<Image>& outputImage,
base::UniquePtr<Mask>& outputMask)
{
gfx::Rect bounds = m_currentData.transformedBounds();
base::UniquePtr<Image> image(Image::create(m_sprite->pixelFormat(), bounds.w, bounds.h));
drawImage(image, bounds.origin(), false);
// Draw mask without shrinking it, so the mask size is equal to the
// "image" render.
base::UniquePtr<Mask> mask(new Mask);
drawMask(mask, false);
// Now we can shrink and crop the image.
gfx::Rect oldMaskBounds = mask->bounds();
mask->shrink();
gfx::Rect newMaskBounds = mask->bounds();
if (newMaskBounds != oldMaskBounds) {
newMaskBounds.x -= oldMaskBounds.x;
newMaskBounds.y -= oldMaskBounds.y;
image.reset(crop_image(image,
newMaskBounds.x,
newMaskBounds.y,
newMaskBounds.w,
newMaskBounds.h, 0));
}
outputImage.reset(image.release());
outputMask.reset(mask.release());
}
ImageRef ExpandCelCanvas::trimDstImage(const gfx::Rect& bounds) const
{
return ImageRef(
crop_image(m_dstImage.get(),
bounds.x, bounds.y,
bounds.w, bounds.h,
m_dstImage->maskColor()));
}
void validate_classifier_single(char *datacfg, char *filename, char *weightfile)
{
int i, j;
network *net = load_network(filename, weightfile, 0);
set_batch_network(net, 1);
srand(time(0));
list *options = read_data_cfg(datacfg);
char *label_list = option_find_str(options, "labels", "data/labels.list");
char *leaf_list = option_find_str(options, "leaves", 0);
if(leaf_list) change_leaves(net->hierarchy, leaf_list);
char *valid_list = option_find_str(options, "valid", "data/train.list");
int classes = option_find_int(options, "classes", 2);
int topk = option_find_int(options, "top", 1);
char **labels = get_labels(label_list);
list *plist = get_paths(valid_list);
char **paths = (char **)list_to_array(plist);
int m = plist->size;
free_list(plist);
float avg_acc = 0;
float avg_topk = 0;
int *indexes = calloc(topk, sizeof(int));
for(i = 0; i < m; ++i){
int class = -1;
char *path = paths[i];
for(j = 0; j < classes; ++j){
if(strstr(path, labels[j])){
class = j;
break;
}
}
image im = load_image_color(paths[i], 0, 0);
image resized = resize_min(im, net->w);
image crop = crop_image(resized, (resized.w - net->w)/2, (resized.h - net->h)/2, net->w, net->h);
//show_image(im, "orig");
//show_image(crop, "cropped");
//cvWaitKey(0);
float *pred = network_predict(net, crop.data);
if(net->hierarchy) hierarchy_predictions(pred, net->outputs, net->hierarchy, 1, 1);
if(resized.data != im.data) free_image(resized);
free_image(im);
free_image(crop);
top_k(pred, classes, topk, indexes);
if(indexes[0] == class) avg_acc += 1;
for(j = 0; j < topk; ++j){
if(indexes[j] == class) avg_topk += 1;
}
printf("%d: top 1: %f, top %d: %f\n", i, avg_acc/(i+1), topk, avg_topk/(i+1));
}
}
void test_lsd(char *cfgfile, char *weightfile, char *filename)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
char buff[256];
char *input = buff;
int i, imlayer = 0;
for (i = 0; i < net.n; ++i) {
if (net.layers[i].out_c == 3) {
imlayer = i;
printf("%d\n", i);
break;
}
}
while(1){
if(filename){
strncpy(input, filename, 256);
}else{
printf("Enter Image Path: ");
fflush(stdout);
input = fgets(input, 256, stdin);
if(!input) return;
strtok(input, "\n");
}
image im = load_image_color(input, 0, 0);
image resized = resize_min(im, net.w);
image crop = crop_image(resized, (resized.w - net.w)/2, (resized.h - net.h)/2, net.w, net.h);
//grayscale_image_3c(crop);
float *X = crop.data;
time=clock();
network_predict(net, X);
image out = get_network_image_layer(net, imlayer);
//yuv_to_rgb(out);
constrain_image(out);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
show_image(out, "out");
show_image(crop, "crop");
save_image(out, "out");
#ifdef OPENCV
cvWaitKey(0);
#endif
free_image(im);
free_image(resized);
free_image(crop);
if (filename) break;
}
}
static void save_image(img_t *img, char *output_dir) {
char filename[1024];
// create the needed output directory if not present
snprintf(filename, 1024, "%s/13/", output_dir);
mkdir(filename, S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH);
snprintf(filename, 1024, "%s/13/%d/", output_dir, img->tileX);
mkdir(filename, S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH);
snprintf(filename, 1024, "%s/13/%d/%d.png", output_dir, img->tileX, img->tileY);
FILE *file = fopen(filename, "wb");
crop_image(img, 6, file);
fclose(file);
}
int main(int argc, char **argv)
{
char* input = argv[1];
int channels = 3;
list *plist = get_paths(input);
//int N = plist->size;
char **paths = (char **)list_to_array(plist);
int m = plist->size;
int count_label = 0;
char labelpath[256];
sprintf(labelpath, "../labels/01_5_1.txt");
int count = 0;
box_label *boxes = read_boxes(labelpath, &count);
for (int i = 0; i < m; i++)
{
if (!paths[i])
{
printf("load error!\n");
break;
}
image im = load_image(paths[i], 0, 0, channels);
printf("load %s", paths[i]);
float x, y, w, h;
count_label++;
x = boxes[i].x;
y = boxes[i].y;
w = boxes[i].w;
h = boxes[i].h;
box box = { x, y, w, h };
char *save_path1 = get_basename(paths[i]);
char save_path[256];
sprintf(save_path, "./images/%s", save_path1);
//show_image(im, save_path);
image crop_im = crop_image(im, x,y,w,h);
printf(" %f %f %f %f \n", x,y,w,h);
show_image(crop_im, save_path);
free_image(crop_im);
free_image(im);
}
}
// static
Image* Image::createCopy(const Image* image, const ImageBufferPtr& buffer)
{
ASSERT(image);
return crop_image(image, 0, 0, image->getWidth(), image->getHeight(),
image->getMaskColor(), buffer);
}
void copy_cel(ContextWriter& writer)
{
Document* document = writer.document();
Sprite* sprite = writer.sprite();
UndoTransaction undo(writer.context(), "Move Cel", undo::ModifyDocument);
Cel *src_cel, *dst_cel;
ASSERT(src_layer != NULL);
ASSERT(dst_layer != NULL);
ASSERT(src_frame >= 0 && src_frame < sprite->getTotalFrames());
ASSERT(dst_frame >= 0 && dst_frame < sprite->getTotalFrames());
src_cel = static_cast<LayerImage*>(src_layer)->getCel(src_frame);
dst_cel = static_cast<LayerImage*>(dst_layer)->getCel(dst_frame);
// Remove the 'dst_cel' (if it exists) because it must be replaced
// with 'src_cel'
if ((dst_cel != NULL) && (!dst_layer->isBackground() || src_cel != NULL))
remove_cel(sprite, undo, static_cast<LayerImage*>(dst_layer), dst_cel);
// Move the cel in the same layer.
if (src_cel != NULL) {
Image *src_image = sprite->getStock()->getImage(src_cel->getImage());
Image *dst_image;
int image_index;
int dst_cel_x;
int dst_cel_y;
int dst_cel_opacity;
// If we are moving a cel from a transparent layer to the
// background layer, we have to clear the background of the image.
if (!src_layer->isBackground() &&
dst_layer->isBackground()) {
dst_image = crop_image(src_image,
-src_cel->getX(),
-src_cel->getY(),
sprite->getWidth(),
sprite->getHeight(), 0);
clear_image(dst_image, app_get_color_to_clear_layer(dst_layer));
composite_image(dst_image, src_image, src_cel->getX(), src_cel->getY(), 255, BLEND_MODE_NORMAL);
dst_cel_x = 0;
dst_cel_y = 0;
dst_cel_opacity = 255;
}
else {
dst_image = Image::createCopy(src_image);
dst_cel_x = src_cel->getX();
dst_cel_y = src_cel->getY();
dst_cel_opacity = src_cel->getOpacity();
}
// Add the image in the stock
image_index = sprite->getStock()->addImage(dst_image);
if (undo.isEnabled())
undo.pushUndoer(new undoers::AddImage(undo.getObjects(),
sprite->getStock(), image_index));
// Create the new cel
dst_cel = new Cel(dst_frame, image_index);
dst_cel->setPosition(dst_cel_x, dst_cel_y);
dst_cel->setOpacity(dst_cel_opacity);
if (undo.isEnabled())
undo.pushUndoer(new undoers::AddCel(undo.getObjects(), dst_layer, dst_cel));
static_cast<LayerImage*>(dst_layer)->addCel(dst_cel);
}
undo.commit();
document->notifyCelCopied(src_layer, src_frame, dst_layer, dst_frame);
set_frame_to_handle(NULL, FrameNumber(0), NULL, FrameNumber(0));
}
int main(int argc, char **argv) {
int ret, tmp;
img_t img;
char *output_dir;
FILE *out_file;
if (argc < 5) {
printf("Usage:\npacked_tilegen <input> <output_dir> <tileX> <tileY> [cardinal direction N|E|S|W\n");
exit(1);
}
printf("Read file \"%s\"\n", argv[1]);
if (strstr(argv[1], ".png"))
ret = read_png(argv[1], &img);
else if (strstr(argv[1], ".ppm"))
ret = read_ppm(argv[1], &img);
else {
printf("Unknown format!\n");
exit(2);
}
output_dir = argv[2];
if (ret) {
printf("Could not read png input file! %d\n", ret);
exit(ret);
}
img.tileX = atoi(argv[3]);
img.tileY = atoi(argv[4]);
if (argc > 5) {
switch(argv[5][0]) {
case 'n':
case 'N':
// keep defaults
break;
case 'e':
case 'E':
tmp = img.tileX;
img.tileX = img.tileY;
img.tileY = (2<<12) - 1 - tmp;
break;
case 's':
case 'S':
img.tileX = (2<<12) - 1 - img.tileX;
img.tileY = (2<<12) - 1 - img.tileY;
break;
case 'w':
case 'W':
tmp = img.tileX;
img.tileX = (2<<12) - 1 - img.tileY;
img.tileY = tmp;
break;
default:
fprintf(stderr, "Unknown cardinal direction \"%s\". Default to north\n", argv[5]);
}
}
// create pack file for writing
out_file = open_packed_file(output_dir, img.tileX, img.tileY);
tmp = 0;
while (1) {
// crop image at given zoom level..
crop_image(&img, tmp++, out_file);
scale_image(&img);
if (img.sizeX == TILE_SIZE) {
save_image(&img, output_dir);
break;
}
}
close_packed_file(out_file);
return 0;
}
ExpandCelCanvas::ExpandCelCanvas(Context* context, TiledMode tiledMode, UndoTransaction& undo)
: m_cel(NULL)
, m_celImage(NULL)
, m_celCreated(false)
, m_closed(false)
, m_committed(false)
, m_undo(undo)
{
create_buffers();
DocumentLocation location = context->getActiveLocation();
m_document = location.document();
m_sprite = location.sprite();
m_layer = location.layer();
if (m_layer->isImage()) {
m_cel = static_cast<LayerImage*>(m_layer)->getCel(location.frame());
if (m_cel)
m_celImage = m_sprite->getStock()->getImage(m_cel->getImage());
}
// If there is no Cel
if (m_cel == NULL) {
// Create the image
m_celImage = Image::create(m_sprite->getPixelFormat(), m_sprite->getWidth(),
m_sprite->getHeight());
clear_image(m_celImage, m_sprite->getTransparentColor());
// Create the cel
m_cel = new Cel(location.frame(), 0);
static_cast<LayerImage*>(m_layer)->addCel(m_cel);
m_celCreated = true;
}
m_originalCelX = m_cel->getX();
m_originalCelY = m_cel->getY();
// Region to draw
int x1, y1, x2, y2;
if (tiledMode == TILED_NONE) { // Non-tiled
x1 = MIN(m_cel->getX(), 0);
y1 = MIN(m_cel->getY(), 0);
x2 = MAX(m_cel->getX()+m_celImage->getWidth(), m_sprite->getWidth());
y2 = MAX(m_cel->getY()+m_celImage->getHeight(), m_sprite->getHeight());
}
else { // Tiled
x1 = 0;
y1 = 0;
x2 = m_sprite->getWidth();
y2 = m_sprite->getHeight();
}
// create two copies of the image region which we'll modify with the tool
m_srcImage = crop_image(m_celImage,
x1-m_cel->getX(),
y1-m_cel->getY(), x2-x1, y2-y1,
m_sprite->getTransparentColor(),
src_buffer);
m_dstImage = Image::createCopy(m_srcImage, dst_buffer);
// We have to adjust the cel position to match the m_dstImage
// position (the new m_dstImage will be used in RenderEngine to
// draw this cel).
m_cel->setPosition(x1, y1);
}
void BackgroundBuilder::run(){
const QRect win_dim = QApplication::desktop()->screenGeometry();
std::cout << "Desktop is: " << win_dim.width() << "x" << win_dim.height() << "\n";
const float desktop_aspect = static_cast<float>(win_dim.width()) / win_dim.height();
const float image_aspect = static_cast<float>(original->width()) / original->height();
std::cout << "Desktop aspect = " << desktop_aspect << ", image = " << image_aspect << "\n";
auto pipeline_start = std::chrono::high_resolution_clock::now();
// If the image is has a higher aspect ratio than the desktop we'll want to scale y
// to fit and let x be croppped, otherwise we do the opposite
int scaled_w = 0;
int scaled_h = 0;
if (desktop_aspect < image_aspect){
scaled_h = win_dim.height() + 32;
scaled_w = scaled_h * image_aspect;
}
else {
scaled_w = win_dim.width() + 32;
scaled_h = scaled_w * (1.0 / image_aspect);
}
//std::cout << "scaling image to " << scaled_w << "x" << scaled_h << "\n";
QImage scaled_background{ scaled_w, scaled_h, QImage::Format_RGB32 };
auto start = std::chrono::high_resolution_clock::now();
resize_image(*blurred, scaled_background);
auto end = std::chrono::high_resolution_clock::now();
//std::cout << "resize took " << std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count()
// << "ms\n";
//scaled_background.save(QString("scaled_background.jpg"), "JPEG");
int crop_x = (scaled_w - win_dim.width()) / 2;
int start_x = crop_x;
int end_x = scaled_w - crop_x;
// Sometimes our crop may be off by a few pixels, so just drop the extra ones if we don't match
if (end_x - start_x != win_dim.width()){
//std::cout << "width mismatch of " << end_x - start_x - win_dim.width() << "pixels\n";
end_x -= end_x - start_x - win_dim.width();
}
int crop_y = (scaled_h - win_dim.height()) / 2;
int start_y = crop_y;
int end_y = scaled_h - crop_y;
if (end_y - start_y != win_dim.height()){
//std::cout << "height mismatch of " << end_y - start_y - win_dim.height() << "pixels\n";
end_y -= end_y - start_y - win_dim.height();
}
QSharedPointer<QImage> background(new QImage{win_dim.width(), win_dim.height(), QImage::Format_RGB32});
start = std::chrono::high_resolution_clock::now();
crop_image(scaled_background, *background, start_x, end_x, start_y, end_y);
end = std::chrono::high_resolution_clock::now();
//std::cout << "crop took " << std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count()
// << "ms\n";
//background->save(QString("cropped_background.jpg"), "JPEG");
//std::cout << "compositing original image with blurred background\n";
int centered_w = 0;
int centered_h = 0;
float border_percent = 0.04f;
if (desktop_aspect > image_aspect) {
centered_h = win_dim.height() - border_percent * win_dim.height();
centered_w = centered_h * image_aspect;
//std::cout << "border size of " << border_percent * win_dim.height() << " along x\n";
}
else {
centered_w = win_dim.width() - border_percent * win_dim.width();
centered_h = centered_w * (1.0 / image_aspect);
//std::cout << "border size of " << border_percent * win_dim.width() << " along y\n";
}
//std::cout << "Centered image will be scaled to " << centered_w << "x" << centered_h << "\n";
QImage centered_image{centered_w, centered_h, QImage::Format_RGB32};
start = std::chrono::high_resolution_clock::now();
resize_image(*original, centered_image);
end = std::chrono::high_resolution_clock::now();
//std::cout << "scaling centered image took "
// << std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count() << "ms\n";
//centered_image.save(QString("centered_image.jpg"), "JPEG");
start = std::chrono::high_resolution_clock::now();
composite_background(centered_image, *background, *background);
end = std::chrono::high_resolution_clock::now();
//std::cout << "compositing took "
// << std::chrono::duration_cast<std::chrono::milliseconds>(end - start).count() << "ms\n";
auto pipeline_end = std::chrono::high_resolution_clock::now();
std::cout << "Entire pipeline to build background took "
<< std::chrono::duration_cast<std::chrono::milliseconds>(pipeline_end - pipeline_start).count() << "ms\n";
std::cout << "done making background, Saving background to background.png\n";
// Note: in the future we'll only save to the temp dir if we need to (on Windows we must pass a filename)
background->save(QString::fromStdString("background.png"), "PNG");
background->save(QDir::tempPath() + QString::fromStdString("/background.png"), "PNG");
std::cout << "background saved\n";
emit finished(background);
}
void run_nightmare(int argc, char **argv)
{
srand(0);
if(argc < 4){
fprintf(stderr, "usage: %s %s [cfg] [weights] [image] [layer] [options! (optional)]\n", argv[0], argv[1]);
return;
}
char *cfg = argv[2];
char *weights = argv[3];
char *input = argv[4];
int max_layer = atoi(argv[5]);
int range = find_int_arg(argc, argv, "-range", 1);
int rounds = find_int_arg(argc, argv, "-rounds", 1);
int iters = find_int_arg(argc, argv, "-iters", 10);
int octaves = find_int_arg(argc, argv, "-octaves", 4);
float zoom = find_float_arg(argc, argv, "-zoom", 1.);
float rate = find_float_arg(argc, argv, "-rate", .04);
float thresh = find_float_arg(argc, argv, "-thresh", 1.);
float rotate = find_float_arg(argc, argv, "-rotate", 0);
char *prefix = find_char_arg(argc, argv, "-prefix", 0);
network net = parse_network_cfg(cfg);
load_weights(&net, weights);
char *cfgbase = basecfg(cfg);
char *imbase = basecfg(input);
set_batch_network(&net, 1);
image im = load_image_color(input, 0, 0);
if(0){
float scale = 1;
if(im.w > 512 || im.h > 512){
if(im.w > im.h) scale = 512.0/im.w;
else scale = 512.0/im.h;
}
image resized = resize_image(im, scale*im.w, scale*im.h);
free_image(im);
im = resized;
}
int e;
int n;
for(e = 0; e < rounds; ++e){
fprintf(stderr, "Iteration: ");
fflush(stderr);
for(n = 0; n < iters; ++n){
fprintf(stderr, "%d, ", n);
fflush(stderr);
int layer = max_layer + rand()%range - range/2;
int octave = rand()%octaves;
optimize_picture(&net, im, layer, 1/pow(1.33333333, octave), rate, thresh);
}
fprintf(stderr, "done\n");
if(0){
image g = grayscale_image(im);
free_image(im);
im = g;
}
char buff[256];
if (prefix){
sprintf(buff, "%s/%s_%s_%d_%06d",prefix, imbase, cfgbase, max_layer, e);
}else{
sprintf(buff, "%s_%s_%d_%06d",imbase, cfgbase, max_layer, e);
}
printf("%d %s\n", e, buff);
save_image(im, buff);
//show_image(im, buff);
//cvWaitKey(0);
if(rotate){
image rot = rotate_image(im, rotate);
free_image(im);
im = rot;
}
image crop = crop_image(im, im.w * (1. - zoom)/2., im.h * (1.-zoom)/2., im.w*zoom, im.h*zoom);
image resized = resize_image(crop, im.w, im.h);
free_image(im);
free_image(crop);
im = resized;
}
}
/*
* BEE::Sprite::crop_image_height() - Crop the image to the given height
* @new_crop_height: the new height to crop the image to
*/
int BEE::Sprite::crop_image_height(int new_crop_height) {
crop.h = new_crop_height; // Set the height
return crop_image(crop); // Return the status of the cropping
}
void run_nightmare(int argc, char **argv)
{
srand(0);
if(argc < 4){
fprintf(stderr, "usage: %s %s [cfg] [weights] [image] [layer] [options! (optional)]\n", argv[0], argv[1]);
return;
}
char *cfg = argv[2];
char *weights = argv[3];
char *input = argv[4];
int max_layer = atoi(argv[5]);
int range = find_int_arg(argc, argv, "-range", 1);
int norm = find_int_arg(argc, argv, "-norm", 1);
int rounds = find_int_arg(argc, argv, "-rounds", 1);
int iters = find_int_arg(argc, argv, "-iters", 10);
int octaves = find_int_arg(argc, argv, "-octaves", 4);
float zoom = find_float_arg(argc, argv, "-zoom", 1.);
float rate = find_float_arg(argc, argv, "-rate", .04);
float thresh = find_float_arg(argc, argv, "-thresh", 1.);
float rotate = find_float_arg(argc, argv, "-rotate", 0);
float momentum = find_float_arg(argc, argv, "-momentum", .9);
float lambda = find_float_arg(argc, argv, "-lambda", .01);
char *prefix = find_char_arg(argc, argv, "-prefix", 0);
int reconstruct = find_arg(argc, argv, "-reconstruct");
int smooth_size = find_int_arg(argc, argv, "-smooth", 1);
network net = parse_network_cfg(cfg);
load_weights(&net, weights);
char *cfgbase = basecfg(cfg);
char *imbase = basecfg(input);
set_batch_network(&net, 1);
image im = load_image_color(input, 0, 0);
if(0){
float scale = 1;
if(im.w > 512 || im.h > 512){
if(im.w > im.h) scale = 512.0/im.w;
else scale = 512.0/im.h;
}
image resized = resize_image(im, scale*im.w, scale*im.h);
free_image(im);
im = resized;
}
float *features = 0;
image update;
if (reconstruct){
resize_network(&net, im.w, im.h);
int zz = 0;
network_predict(net, im.data);
image out_im = get_network_image(net);
image crop = crop_image(out_im, zz, zz, out_im.w-2*zz, out_im.h-2*zz);
//flip_image(crop);
image f_im = resize_image(crop, out_im.w, out_im.h);
free_image(crop);
printf("%d features\n", out_im.w*out_im.h*out_im.c);
im = resize_image(im, im.w, im.h);
f_im = resize_image(f_im, f_im.w, f_im.h);
features = f_im.data;
int i;
for(i = 0; i < 14*14*512; ++i){
features[i] += rand_uniform(-.19, .19);
}
free_image(im);
im = make_random_image(im.w, im.h, im.c);
update = make_image(im.w, im.h, im.c);
}
int e;
int n;
for(e = 0; e < rounds; ++e){
fprintf(stderr, "Iteration: ");
fflush(stderr);
for(n = 0; n < iters; ++n){
fprintf(stderr, "%d, ", n);
fflush(stderr);
if(reconstruct){
reconstruct_picture(net, features, im, update, rate, momentum, lambda, smooth_size, 1);
//if ((n+1)%30 == 0) rate *= .5;
show_image(im, "reconstruction");
#ifdef OPENCV
cvWaitKey(10);
#endif
}else{
int layer = max_layer + rand()%range - range/2;
int octave = rand()%octaves;
optimize_picture(&net, im, layer, 1/pow(1.33333333, octave), rate, thresh, norm);
}
}
fprintf(stderr, "done\n");
if(0){
image g = grayscale_image(im);
free_image(im);
im = g;
}
char buff[256];
if (prefix){
sprintf(buff, "%s/%s_%s_%d_%06d",prefix, imbase, cfgbase, max_layer, e);
}else{
sprintf(buff, "%s_%s_%d_%06d",imbase, cfgbase, max_layer, e);
}
printf("%d %s\n", e, buff);
save_image(im, buff);
//show_image(im, buff);
//cvWaitKey(0);
if(rotate){
image rot = rotate_image(im, rotate);
free_image(im);
im = rot;
}
image crop = crop_image(im, im.w * (1. - zoom)/2., im.h * (1.-zoom)/2., im.w*zoom, im.h*zoom);
image resized = resize_image(crop, im.w, im.h);
free_image(im);
free_image(crop);
im = resized;
}
}
void move_cel(ContextWriter& writer)
{
Document* document = writer.document();
Sprite* sprite = writer.sprite();
Cel *src_cel, *dst_cel;
ASSERT(src_layer != NULL);
ASSERT(dst_layer != NULL);
ASSERT(src_frame >= 0 && src_frame < sprite->getTotalFrames());
ASSERT(dst_frame >= 0 && dst_frame < sprite->getTotalFrames());
if (src_layer->isBackground()) {
copy_cel(writer);
return;
}
src_cel = static_cast<LayerImage*>(src_layer)->getCel(src_frame);
dst_cel = static_cast<LayerImage*>(dst_layer)->getCel(dst_frame);
UndoTransaction undo(writer.context(), "Move Cel", undo::ModifyDocument);
/* remove the 'dst_cel' (if it exists) because it must be
replaced with 'src_cel' */
if ((dst_cel != NULL) && (!dst_layer->isBackground() || src_cel != NULL))
remove_cel(sprite, undo, static_cast<LayerImage*>(dst_layer), dst_cel);
/* move the cel in the same layer */
if (src_cel != NULL) {
if (src_layer == dst_layer) {
if (undo.isEnabled())
undo.pushUndoer(new undoers::SetCelFrame(undo.getObjects(), src_cel));
src_cel->setFrame(dst_frame);
}
/* move the cel in different layers */
else {
if (undo.isEnabled())
undo.pushUndoer(new undoers::RemoveCel(undo.getObjects(), src_layer, src_cel));
static_cast<LayerImage*>(src_layer)->removeCel(src_cel);
src_cel->setFrame(dst_frame);
/* if we are moving a cel from a transparent layer to the
background layer, we have to clear the background of the
image */
if (!src_layer->isBackground() &&
dst_layer->isBackground()) {
Image* src_image = sprite->getStock()->getImage(src_cel->getImage());
Image* dst_image = crop_image(src_image,
-src_cel->getX(),
-src_cel->getY(),
sprite->getWidth(),
sprite->getHeight(), 0);
if (undo.isEnabled()) {
undo.pushUndoer(new undoers::ReplaceImage(undo.getObjects(),
sprite->getStock(), src_cel->getImage()));
undo.pushUndoer(new undoers::SetCelPosition(undo.getObjects(), src_cel));
undo.pushUndoer(new undoers::SetCelOpacity(undo.getObjects(), src_cel));
}
clear_image(dst_image, app_get_color_to_clear_layer(dst_layer));
composite_image(dst_image, src_image, src_cel->getX(), src_cel->getY(), 255, BLEND_MODE_NORMAL);
src_cel->setPosition(0, 0);
src_cel->setOpacity(255);
sprite->getStock()->replaceImage(src_cel->getImage(), dst_image);
delete src_image;
}
if (undo.isEnabled())
undo.pushUndoer(new undoers::AddCel(undo.getObjects(), dst_layer, src_cel));
static_cast<LayerImage*>(dst_layer)->addCel(src_cel);
}
}
undo.commit();
document->notifyCelMoved(src_layer, src_frame, dst_layer, dst_frame);
set_frame_to_handle(NULL, FrameNumber(0), NULL, FrameNumber(0));
}
void validate_classifier_10(char *datacfg, char *filename, char *weightfile)
{
int i, j;
network *net = load_network(filename, weightfile, 0);
set_batch_network(net, 1);
srand(time(0));
list *options = read_data_cfg(datacfg);
char *label_list = option_find_str(options, "labels", "data/labels.list");
char *valid_list = option_find_str(options, "valid", "data/train.list");
int classes = option_find_int(options, "classes", 2);
int topk = option_find_int(options, "top", 1);
char **labels = get_labels(label_list);
list *plist = get_paths(valid_list);
char **paths = (char **)list_to_array(plist);
int m = plist->size;
free_list(plist);
float avg_acc = 0;
float avg_topk = 0;
int *indexes = calloc(topk, sizeof(int));
for(i = 0; i < m; ++i){
int class = -1;
char *path = paths[i];
for(j = 0; j < classes; ++j){
if(strstr(path, labels[j])){
class = j;
break;
}
}
int w = net->w;
int h = net->h;
int shift = 32;
image im = load_image_color(paths[i], w+shift, h+shift);
image images[10];
images[0] = crop_image(im, -shift, -shift, w, h);
images[1] = crop_image(im, shift, -shift, w, h);
images[2] = crop_image(im, 0, 0, w, h);
images[3] = crop_image(im, -shift, shift, w, h);
images[4] = crop_image(im, shift, shift, w, h);
flip_image(im);
images[5] = crop_image(im, -shift, -shift, w, h);
images[6] = crop_image(im, shift, -shift, w, h);
images[7] = crop_image(im, 0, 0, w, h);
images[8] = crop_image(im, -shift, shift, w, h);
images[9] = crop_image(im, shift, shift, w, h);
float *pred = calloc(classes, sizeof(float));
for(j = 0; j < 10; ++j){
float *p = network_predict(net, images[j].data);
if(net->hierarchy) hierarchy_predictions(p, net->outputs, net->hierarchy, 1, 1);
axpy_cpu(classes, 1, p, 1, pred, 1);
free_image(images[j]);
}
free_image(im);
top_k(pred, classes, topk, indexes);
free(pred);
if(indexes[0] == class) avg_acc += 1;
for(j = 0; j < topk; ++j){
if(indexes[j] == class) avg_topk += 1;
}
printf("%d: top 1: %f, top %d: %f\n", i, avg_acc/(i+1), topk, avg_topk/(i+1));
}
}
void try_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename, int layer_num)
{
network *net = load_network(cfgfile, weightfile, 0);
set_batch_network(net, 1);
srand(2222222);
list *options = read_data_cfg(datacfg);
char *name_list = option_find_str(options, "names", 0);
if(!name_list) name_list = option_find_str(options, "labels", "data/labels.list");
int top = option_find_int(options, "top", 1);
int i = 0;
char **names = get_labels(name_list);
clock_t time;
int *indexes = calloc(top, sizeof(int));
char buff[256];
char *input = buff;
while(1){
if(filename){
strncpy(input, filename, 256);
}else{
printf("Enter Image Path: ");
fflush(stdout);
input = fgets(input, 256, stdin);
if(!input) return;
strtok(input, "\n");
}
image orig = load_image_color(input, 0, 0);
image r = resize_min(orig, 256);
image im = crop_image(r, (r.w - 224 - 1)/2 + 1, (r.h - 224 - 1)/2 + 1, 224, 224);
float mean[] = {0.48263312050943, 0.45230225481413, 0.40099074308742};
float std[] = {0.22590347483426, 0.22120921437787, 0.22103996251583};
float var[3];
var[0] = std[0]*std[0];
var[1] = std[1]*std[1];
var[2] = std[2]*std[2];
normalize_cpu(im.data, mean, var, 1, 3, im.w*im.h);
float *X = im.data;
time=clock();
float *predictions = network_predict(net, X);
layer l = net->layers[layer_num];
for(i = 0; i < l.c; ++i){
if(l.rolling_mean) printf("%f %f %f\n", l.rolling_mean[i], l.rolling_variance[i], l.scales[i]);
}
#ifdef GPU
cuda_pull_array(l.output_gpu, l.output, l.outputs);
#endif
for(i = 0; i < l.outputs; ++i){
printf("%f\n", l.output[i]);
}
/*
printf("\n\nWeights\n");
for(i = 0; i < l.n*l.size*l.size*l.c; ++i){
printf("%f\n", l.filters[i]);
}
printf("\n\nBiases\n");
for(i = 0; i < l.n; ++i){
printf("%f\n", l.biases[i]);
}
*/
top_predictions(net, top, indexes);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
for(i = 0; i < top; ++i){
int index = indexes[i];
printf("%s: %f\n", names[index], predictions[index]);
}
free_image(im);
if (filename) break;
}
}
void validate_recall(char *cfgfile, char *weightfile)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
srand(time(0));
char *val_images = "/home/pjreddie/data/voc/test/2007_test.txt";
list *plist = get_paths(val_images);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n - 1];
int num_boxes = l.side;
int num = l.n;
int classes = l.classes;
int j;
box *boxes = calloc(num_boxes*num_boxes*num, sizeof(box));
float **probs = calloc(num_boxes*num_boxes*num, sizeof(float *));
for(j = 0; j < num_boxes*num_boxes*num; ++j) probs[j] = calloc(classes+1, sizeof(float *));
int N = plist->size;
int i=0;
int k;
float iou_thresh = .5;
float thresh = .1;
int total = 0;
int correct = 0;
float avg_iou = 0;
int nms = 1;
int proposals = 0;
int save = 1;
for (i = 0; i < N; ++i) {
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image resized = resize_image(orig, net.w, net.h);
float *X = resized.data;
float *predictions = network_predict(net, X);
get_boxes(predictions+1+classes, num, num_boxes, 5+classes, boxes);
get_probs(predictions, num*num_boxes*num_boxes, classes, 5+classes, probs);
if (nms) do_nms(boxes, probs, num*num_boxes*num_boxes, (classes>0) ? classes : 1, iou_thresh);
char *labelpath = find_replace(path, "images", "labels");
labelpath = find_replace(labelpath, "JPEGImages", "labels");
labelpath = find_replace(labelpath, ".jpg", ".txt");
labelpath = find_replace(labelpath, ".JPEG", ".txt");
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < num_boxes*num_boxes*num; ++k){
if(probs[k][0] > thresh){
++proposals;
if(save){
char buff[256];
sprintf(buff, "/data/extracted/nms_preds/%d", proposals);
int dx = (boxes[k].x - boxes[k].w/2) * orig.w;
int dy = (boxes[k].y - boxes[k].h/2) * orig.h;
int w = boxes[k].w * orig.w;
int h = boxes[k].h * orig.h;
image cropped = crop_image(orig, dx, dy, w, h);
image sized = resize_image(cropped, 224, 224);
#ifdef OPENCV
save_image_jpg(sized, buff);
#endif
free_image(sized);
free_image(cropped);
sprintf(buff, "/data/extracted/nms_pred_boxes/%d.txt", proposals);
char *im_id = basecfg(path);
FILE *fp = fopen(buff, "w");
fprintf(fp, "%s %d %d %d %d\n", im_id, dx, dy, dx+w, dy+h);
fclose(fp);
free(im_id);
}
}
}
for (j = 0; j < num_labels; ++j) {
++total;
box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
float best_iou = 0;
for(k = 0; k < num_boxes*num_boxes*num; ++k){
float iou = box_iou(boxes[k], t);
if(probs[k][0] > thresh && iou > best_iou){
best_iou = iou;
}
}
avg_iou += best_iou;
if(best_iou > iou_thresh){
++correct;
}
}
free(truth);
free_image(orig);
free_image(resized);
fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total);
}
}
void extract_boxes(char *cfgfile, char *weightfile)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
srand(time(0));
char *val_images = "/home/pjreddie/data/voc/test/train.txt";
list *plist = get_paths(val_images);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n - 1];
int num_boxes = l.side;
int num = l.n;
int classes = l.classes;
int j;
box *boxes = calloc(num_boxes*num_boxes*num, sizeof(box));
float **probs = calloc(num_boxes*num_boxes*num, sizeof(float *));
for(j = 0; j < num_boxes*num_boxes*num; ++j) probs[j] = calloc(classes+1, sizeof(float *));
int N = plist->size;
int i=0;
int k;
int count = 0;
float iou_thresh = .3;
for (i = 0; i < N; ++i) {
fprintf(stderr, "%5d %5d\n", i, count);
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image resized = resize_image(orig, net.w, net.h);
float *X = resized.data;
float *predictions = network_predict(net, X);
get_boxes(predictions+1+classes, num, num_boxes, 5+classes, boxes);
get_probs(predictions, num*num_boxes*num_boxes, classes, 5+classes, probs);
char *labelpath = find_replace(path, "images", "labels");
labelpath = find_replace(labelpath, "JPEGImages", "labels");
labelpath = find_replace(labelpath, ".jpg", ".txt");
labelpath = find_replace(labelpath, ".JPEG", ".txt");
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
FILE *label = stdin;
for(k = 0; k < num_boxes*num_boxes*num; ++k){
int overlaps = 0;
for (j = 0; j < num_labels; ++j) {
box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
float iou = box_iou(boxes[k], t);
if (iou > iou_thresh){
if (!overlaps) {
char buff[256];
sprintf(buff, "/data/extracted/labels/%d.txt", count);
label = fopen(buff, "w");
overlaps = 1;
}
fprintf(label, "%d %f\n", truth[j].id, iou);
}
}
if (overlaps) {
char buff[256];
sprintf(buff, "/data/extracted/imgs/%d", count++);
int dx = (boxes[k].x - boxes[k].w/2) * orig.w;
int dy = (boxes[k].y - boxes[k].h/2) * orig.h;
int w = boxes[k].w * orig.w;
int h = boxes[k].h * orig.h;
image cropped = crop_image(orig, dx, dy, w, h);
image sized = resize_image(cropped, 224, 224);
#ifdef OPENCV
save_image_jpg(sized, buff);
#endif
free_image(sized);
free_image(cropped);
fclose(label);
}
}
free(truth);
free_image(orig);
free_image(resized);
}
}
void optimize_picture(network *net, image orig, int max_layer, float scale, float rate, float thresh, int norm)
{
//scale_image(orig, 2);
//translate_image(orig, -1);
net->n = max_layer + 1;
int dx = rand()%16 - 8;
int dy = rand()%16 - 8;
int flip = rand()%2;
image crop = crop_image(orig, dx, dy, orig.w, orig.h);
image im = resize_image(crop, (int)(orig.w * scale), (int)(orig.h * scale));
if(flip) flip_image(im);
resize_network(net, im.w, im.h);
layer_t last = net->layers[net->n-1];
//net->layers[net->n - 1].activation = LINEAR;
image delta = make_image(im.w, im.h, im.c);
NETWORK_STATE(state);
#ifdef GPU
state.input = cuda_make_array(im.data, im.w*im.h*im.c);
state.delta = cuda_make_array(im.data, im.w*im.h*im.c);
forward_network_gpu(*net, state);
copy_ongpu(last.outputs, last.output_gpu, 1, last.delta_gpu, 1);
cuda_pull_array(last.delta_gpu, last.delta, last.outputs);
calculate_loss(last.delta, last.delta, last.outputs, thresh);
cuda_push_array(last.delta_gpu, last.delta, last.outputs);
backward_network_gpu(*net, state);
cuda_pull_array(state.delta, delta.data, im.w*im.h*im.c);
cuda_free(state.input);
cuda_free(state.delta);
#else
state.input = im.data;
state.delta = delta.data;
forward_network(*net, state);
fltcpy(last.delta, last.output, last.outputs);
calculate_loss(last.output, last.delta, last.outputs, thresh);
backward_network(*net, state);
#endif
if(flip) flip_image(delta);
//normalize_array(delta.data, delta.w*delta.h*delta.c);
image resized = resize_image(delta, orig.w, orig.h);
image out = crop_image(resized, -dx, -dy, orig.w, orig.h);
/*
image g = grayscale_image(out);
free_image(out);
out = g;
*/
//rate = rate / abs_mean(out.data, out.w*out.h*out.c);
if(norm) normalize_array(out.data, out.w*out.h*out.c);
fltaddmul(orig.data, out.data, orig.w * orig.h * orig.c, rate);
/*
normalize_array(orig.data, orig.w*orig.h*orig.c);
scale_image(orig, sqrt(var));
translate_image(orig, mean);
*/
//translate_image(orig, 1);
//scale_image(orig, .5);
//normalize_image(orig);
constrain_image(orig);
free_image(crop);
free_image(im);
free_image(delta);
free_image(resized);
free_image(out);
}
/*
* BEE::Sprite::crop_image_width() - Crop the image to the given width
* @new_crop_width: the new width to crop the image to
*/
int BEE::Sprite::crop_image_width(int new_crop_width) {
crop.w = new_crop_width; // Set the width
return crop_image(crop); // Return the status of the cropping
}
