void WadImageCache::cache_image(WadImageDescriptor& desc, int width, int height, SDL_Surface *image)
{
std::string name = retrieve_name(desc, width, height, true);
if (!name.empty())
{
autosave_cache();
return;
}
SDL_Surface *resized_image = NULL;
if (image)
{
resized_image = resize_image(image, width, height);
}
else
{
image = image_from_desc(desc);
if (image)
{
resized_image = resize_image(image, width, height);
SDL_FreeSurface(image);
}
}
if (!resized_image)
return;
name = add_to_cache(cache_key_t(desc, width, height), resized_image);
SDL_FreeSurface(resized_image);
}
void draw_label(image a, int r, int c, image label, image prob_label, const float *rgb)
{
float ratio = (float) label.w / label.h;
int h = label.h;
int w = ratio * h;
image rl = resize_image(label, w, h);
if (r - h >= 0) r = r - h;
float ratiop = (float) prob_label.w / prob_label.h;
int hp = prob_label.h;
int wp = ratiop * hp;
image rpl = resize_image(prob_label, wp, hp);
int i, j, k;
for(j = 0; j < h && j + r < a.h; ++j){
for(i = 0; i < w && i + c < a.w; ++i){
for(k = 0; k < label.c; ++k){
float val = get_pixel(rl, i, j, k);
set_pixel(a, i+c+50, j+r, k, rgb[k] * val);
}
}
}
for(j = 0; j < hp && j + r < a.h; ++j){
for(i = 0; i < wp && i + c < a.w; ++i){
for(k = 0; k < prob_label.c; ++k){
float val = get_pixel(rpl, i, j, k);
set_pixel(a, i+c, j+r, k, rgb[k] * val);
}
}
}
free_image(rl);
free_image(rpl);
}
SDL_Surface *WadImageCache::get_image(WadImageDescriptor& desc, int width, int height, SDL_Surface *image)
{
SDL_Surface *surface = retrieve_image(desc, width, height);
if (surface)
return surface;
if (image)
{
surface = resize_image(image, width, height);
}
else
{
image = image_from_desc(desc);
if (image)
{
surface = resize_image(image, width, height);
SDL_FreeSurface(image);
}
}
if (surface)
{
add_to_cache(cache_key_t(desc, width, height), surface);
}
return surface;
}
static bool create_ios_launch_images(const char *dir, export_config *conf) {
size_t len;
stbi_uc *img_data;
int width, height;
if (conf->launch_image == NULL) {
width = 1024;
height = 1024;
len = width * height * 4;
img_data = (stbi_uc*)malloc(len);
memset(img_data, 255, len);
} else {
void *data = am_read_file(conf->launch_image, &len);
int components = 4;
stbi_set_flip_vertically_on_load(0);
img_data =
stbi_load_from_memory((stbi_uc const *)data, len, &width, &height, &components, 4);
free(data);
if (img_data == NULL) return false;
}
if (!resize_image(img_data, width, height, dir, "Default.png", 320, 480)
|| !resize_image(img_data, width, height, dir, "*****@*****.**", 640, 960)
|| !resize_image(img_data, width, height, dir, "*****@*****.**", 640, 1136)
|| !resize_image(img_data, width, height, dir, "*****@*****.**", 750, 1334)
|| !resize_image(img_data, width, height, dir, "*****@*****.**", 1242, 2208)
|| !resize_image(img_data, width, height, dir, "Default-Landscape@2x~ipad.png", 2048, 1536)
|| !resize_image(img_data, width, height, dir, "Default-Landscape~ipad.png", 1024, 768)
|| !resize_image(img_data, width, height, dir, "Default-Portrait@2x~ipad.png", 1536, 2048)
|| !resize_image(img_data, width, height, dir, "Default-Portrait~ipad.png", 768, 1024)
) return false;
free(img_data);
return true;
}
/*
* do prediction
*@param[in]: yoloctx, context
*@param[in]: filename, input picture
*@param[in]: thresh, threshold for probability x confidence level
*@param[out]: predictions, store detected objects
*/
void yoloPredict(context_param_yolo_t *yoloctx, char *filename, float thresh, yoloPredictions *predictions)
{
printf("YOLO predict\n");
int nwidth = yoloctx->_nwidth;
int nheight = yoloctx->_nheight;
int side = yoloctx->_grid.grids;
int classes = yoloctx->_grid.classes;
int bbs = yoloctx->_grid.bbs;
int sqrt = yoloctx->_sqrt;
float nms = yoloctx->_nms;
image im = load_image_color(filename, 0, 0);
image sized = resize_image(im, nwidth, nheight);
resetData(yoloctx);
float *x = sized.data;
float *fpredictions = network_predict(yoloctx->_net, x);
float **probs = yoloctx->_grid.probs;
box *boxes = yoloctx->_grid.boxes;
convertDetections(fpredictions, classes, bbs, sqrt, side, 1, 1, thresh, probs, boxes, 0);
if (nms) do_nms_sort(boxes, probs, side*side*bbs, classes, nms);
convertResults(im.w, im.h, side*side*bbs, thresh, boxes, probs, class_names, 20, predictions);
//free(predictions);
free_image(sized);
free_image(im);
}
void yolo_net_predict(network *pNet, char *imgfilename, char * resfile, float thresh){
detection_layer l = pNet->layers[pNet->n-1];
clock_t time;
char buff[256];
// char *input = buff;
int j;
float nms=.5;
box *boxes = calloc(l.side*l.side*l.n, sizeof(box));
float **probs = calloc(l.side*l.side*l.n, sizeof(float *));
for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float *));
image im = load_image_color(imgfilename,0,0);
image resized = resize_image(im, pNet->w, pNet->h);
float *X = resized.data;
time=clock();
float *predictions = network_predict(*pNet, X);
free_image(im);
printf("%s: Predicted in %f seconds.\n", imgfilename, sec(clock()-time));
FILE *ofp = fopen(resfile, "w");
if (ofp == NULL) {fprintf(stderr, "Can't open output file %s!\n",resfile); exit(1);}
//convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, demo_thresh, probs, boxes, 0);
convert_print_yolo_detections(ofp, predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
//if (nms) do_nms_sort(boxes, probs, l.side*l.side*l.n, l.classes, nms);
fclose(ofp);
}
void CAntimonyDlg::showImage(IplImage *image, UINT ID) // ID 是Picture Control控件的ID号
{
CvSize ImgSize;
IplImage *theimg;
ImgSize.width = picrect.Width();
ImgSize.height = picrect.Height();
theimg = cvCreateImage(ImgSize, IPL_DEPTH_8U, 3);
IplImage *image2 = image;
resize_image(image2, theimg);
CDC *pDC = GetDlgItem(ID)->GetDC();
HDC hDC = pDC->GetSafeHdc();
int rw = picrect.right - picrect.left;
int rh = picrect.bottom - picrect.top;
int iw = theimg->width;
int ih = theimg->height;
int tx = (int)(rw - iw) / 2;
int ty = (int)(rh - ih) / 2;
SetRect(picrect, tx, ty, tx + iw, ty + ih);
CvvImage cimg;
cimg.CopyOf(theimg); // 复制图片
cimg.DrawToHDC(hDC, &picrect); // 将图片绘制到显示控件的指定区域内
ReleaseDC(pDC);
}
void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh)
{
int show_flag = 1;
list *options = read_data_cfg(datacfg);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
image **alphabet = load_alphabet();
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 j;
float nms=.4;
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 sized = resize_image(im, net.w, net.h);
layer l = net.layers[net.n-1];
box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes + 1, sizeof(float *));
float *X = sized.data;
time=clock();
network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
get_region_boxes(l, 1, 1, thresh, probs, boxes, 0, 0, hier_thresh);
if (l.softmax_tree && nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
else if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms);
draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes, show_flag);
save_image(im, "predictions");
show_image(im, "predictions");
free_image(im);
free_image(sized);
free(boxes);
free_ptrs((void **)probs, l.w*l.h*l.n);
#ifdef OPENCV
cvWaitKey(0);
cvDestroyAllWindows();
#endif
if (filename) break;
}
}
void *fetch_in_thread(void *ptr)
{
in = get_image_from_stream(cap);
if(!in.data){
error("Stream closed.");
}
in_s = resize_image(in, net.w, net.h);
return 0;
}
float *network_predict_image(network *net, image im)
{
//image imr = letterbox_image(im, net->w, net->h);
image imr = resize_image(im, net->w, net->h);
set_batch_network(net, 1);
float *p = network_predict(*net, imr.data);
free_image(imr);
return p;
}
void test_yolo(char *cfgfile, char *weightfile, char *filename, float thresh)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
detection_layer l = net.layers[net.n-1];
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
char buff[256];
char *input = buff;
int j;
float nms=.5;
box *boxes = calloc(l.side*l.side*l.n, sizeof(box));
float **probs = calloc(l.side*l.side*l.n, sizeof(float *));
for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float *));
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 sized = resize_image(im, net.w, net.h);
float *X = sized.data;
time=clock();
float *predictions = network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
if (nms) do_nms_sort(boxes, probs, l.side*l.side*l.n, l.classes, nms);
//draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, voc_labels, 20);
draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, 0, 20);
show_image(im, "predictions");
save_image(im, "predictions");
show_image(sized, "resized");
free_image(im);
free_image(sized);
#ifdef OPENCV
cvWaitKey(0);
cvDestroyAllWindows();
#endif
if (filename) break;
}
}
image load_image(char *filename, int w, int h, int c)
{
#ifdef OPENCV
image out = load_image_cv(filename, c);
#else
image out = load_image_stb(filename, c);
#endif
if((h && w) && (h != out.h || w != out.w)){
image resized = resize_image(out, w, h);
free_image(out);
out = resized;
}
return out;
}
void test_writing(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;
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);
resize_network(net, im.w, im.h);
printf("%d %d %d\n", im.h, im.w, im.c);
float *X = im.data;
time=clock();
network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
image pred = get_network_image(net);
image upsampled = resize_image(pred, im.w, im.h);
image thresh = threshold_image(upsampled, .5);
pred = thresh;
show_image(pred, "prediction");
show_image(im, "orig");
#ifdef OPENCV
cvWaitKey(0);
cvDestroyAllWindows();
#endif
free_image(upsampled);
free_image(thresh);
free_image(im);
if (filename) break;
}
}
void test_resize(char *filename)
{
image im = load_image(filename, 0,0, 3);
float mag = mag_array(im.data, im.w*im.h*im.c);
printf("L2 Norm: %f\n", mag);
image gray = grayscale_image(im);
image sat2 = copy_image(im);
saturate_image(sat2, 2);
image sat5 = copy_image(im);
saturate_image(sat5, .5);
image exp2 = copy_image(im);
exposure_image(exp2, 2);
image exp5 = copy_image(im);
exposure_image(exp5, .5);
#ifdef GPU
image r = resize_image(im, im.w, im.h);
image black = make_image(im.w*2 + 3, im.h*2 + 3, 9);
image black2 = make_image(im.w, im.h, 3);
float *r_gpu = cuda_make_array(r.data, r.w*r.h*r.c);
float *black_gpu = cuda_make_array(black.data, black.w*black.h*black.c);
float *black2_gpu = cuda_make_array(black2.data, black2.w*black2.h*black2.c);
shortcut_gpu(3, r.w, r.h, 1, r_gpu, black.w, black.h, 3, black_gpu);
//flip_image(r);
//shortcut_gpu(3, r.w, r.h, 1, r.data, black.w, black.h, 3, black.data);
shortcut_gpu(3, black.w, black.h, 3, black_gpu, black2.w, black2.h, 1, black2_gpu);
cuda_pull_array(black_gpu, black.data, black.w*black.h*black.c);
cuda_pull_array(black2_gpu, black2.data, black2.w*black2.h*black2.c);
show_image_layers(black, "Black");
show_image(black2, "Recreate");
#endif
show_image(im, "Original");
show_image(gray, "Gray");
show_image(sat2, "Saturation-2");
show_image(sat5, "Saturation-.5");
show_image(exp2, "Exposure-2");
show_image(exp5, "Exposure-.5");
#ifdef OPENCV
cvWaitKey(0);
#endif
}
float *get_image_dct( const IplImage *src, const int nSub, int &featLen ) {
IplImage *img = get_gray( src );
IplImage *subImage = resize_image( img, nSub );
IplImage *dctImage = cvCloneImage( subImage );
cvDCT( subImage, dctImage, CV_DXT_FORWARD );
// print_32f_image( dctImage );
// float *data = ( float * )( dctImage->imageData );
// qsort( data + 1, nSub * nSub - 1, sizeof( float ), cmp );
// print_32f_image( dctImage );
int subDct = 6;
featLen = subDct * subDct - 1;
int index = 0;
float *feature = new float[ featLen ];
/*copy only 35 points of dcts*/
for ( int y = 0; y < subDct; y++ ) {
for ( int x = 0; x < subDct; x++ ) {
if ( x == 0 && y == 0 )
continue;
feature[ index++ ] = pixval32f( dctImage, x, y );
}
}
/*print the feature without sort*/
// print_dct_feature( feature, subDct );
qsort( feature, featLen, sizeof( float ), cmp );
//sort( feature, feature + featLen );
/*print the feature after sort*/
//print_dct_feature( feature, subDct );
for ( int i = 0; i < featLen; i++ ) {
printf( "%.3f\t", feature[ i ] );
}
std::cout << endl;
show_image( img, "gray" );
cvReleaseImage( &img );
cvReleaseImage( &subImage );
cvReleaseImage( &dctImage );
return feature;
}
void test_coco(char *cfgfile, char *weightfile, char *filename, float thresh)
{
image **alphabet = load_alphabet();
network *net = load_network(cfgfile, weightfile, 0);
layer l = net->layers[net->n-1];
set_batch_network(net, 1);
srand(2222222);
float nms = .4;
clock_t time;
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 im = load_image_color(input,0,0);
image sized = resize_image(im, net->w, net->h);
float *X = sized.data;
time=clock();
network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
int nboxes = 0;
detection *dets = get_network_boxes(net, 1, 1, thresh, 0, 0, 0, &nboxes);
if (nms) do_nms_sort(dets, l.side*l.side*l.n, l.classes, nms);
draw_detections(im, dets, l.side*l.side*l.n, thresh, coco_classes, alphabet, 80);
save_image(im, "prediction");
show_image(im, "predictions");
free_detections(dets, nboxes);
free_image(im);
free_image(sized);
#ifdef OPENCV
cvWaitKey(0);
cvDestroyAllWindows();
#endif
if (filename) break;
}
}
void demo_art(char *cfgfile, char *weightfile, int cam_index)
{
#ifdef OPENCV
network *net = load_network(cfgfile, weightfile, 0);
set_batch_network(net, 1);
srand(2222222);
void * cap = open_video_stream(0, cam_index, 0,0,0);
char *window = "ArtJudgementBot9000!!!";
if(!cap) error("Couldn't connect to webcam.\n");
int i;
int idx[] = {37, 401, 434};
int n = sizeof(idx)/sizeof(idx[0]);
while(1){
image in = get_image_from_stream(cap);
image in_s = resize_image(in, net->w, net->h);
float *p = network_predict(net, in_s.data);
printf("\033[2J");
printf("\033[1;1H");
float score = 0;
for(i = 0; i < n; ++i){
float s = p[idx[i]];
if (s > score) score = s;
}
score = score;
printf("I APPRECIATE THIS ARTWORK: %10.7f%%\n", score*100);
printf("[");
int upper = 30;
for(i = 0; i < upper; ++i){
printf("%c", ((i+.5) < score*upper) ? 219 : ' ');
}
printf("]\n");
show_image(in, window, 1);
free_image(in_s);
free_image(in);
}
#endif
}
void CAntimonyDlg::showVedio()
{
//VideoCapture capture("E:\\毕设\\锑粗选视频\\1\\20140608115045Sb.avi");
// for (int i = 0; i < 100; i++)
// {
// capture >> frame;
CvSize ImgSize;
IplImage *theimg;
ImgSize.width = picrect.Width();
ImgSize.height = picrect.Height();
theimg = cvCreateImage(ImgSize, IPL_DEPTH_8U, 3);
IplImage image = vedioframe;
resize_image(&image, theimg);
showImage(theimg, IDC_SHOWAVIS);
// waitKey(30);
// }
}
void show_images(image *ims, int n, char *window)
{
image m = collapse_images_vert(ims, n);
/*
int w = 448;
int h = ((float)m.h/m.w) * 448;
if(h > 896){
h = 896;
w = ((float)m.w/m.h) * 896;
}
image sized = resize_image(m, w, h);
*/
normalize_image(m);
image sized = resize_image(m, m.w, m.h);
save_image(sized, window);
show_image(sized, window);
free_image(sized);
free_image(m);
}
static uint8_t *frame_resize_image( mlt_frame frame, int owidth, int oheight, int bpp )
{
// Get properties
mlt_properties properties = MLT_FRAME_PROPERTIES( frame );
// Get the input image, width and height
uint8_t *input = mlt_properties_get_data( properties, "image", NULL );
uint8_t *alpha = mlt_frame_get_alpha( frame );
int alpha_size = 0;
mlt_properties_get_data( properties, "alpha", &alpha_size );
int iwidth = mlt_properties_get_int( properties, "width" );
int iheight = mlt_properties_get_int( properties, "height" );
// If width and height are correct, don't do anything
if ( iwidth < owidth || iheight < oheight )
{
uint8_t alpha_value = mlt_properties_get_int( properties, "resize_alpha" );
// Create the output image
uint8_t *output = mlt_pool_alloc( owidth * ( oheight + 1 ) * bpp );
// Call the generic resize
resize_image( output, owidth, oheight, input, iwidth, iheight, bpp );
// Now update the frame
mlt_frame_set_image( frame, output, owidth * ( oheight + 1 ) * bpp, mlt_pool_release );
// We should resize the alpha too
if ( alpha && alpha_size >= iwidth * iheight )
{
alpha = resize_alpha( alpha, owidth, oheight, iwidth, iheight, alpha_value );
if ( alpha )
mlt_frame_set_alpha( frame, alpha, owidth * oheight, mlt_pool_release );
}
// Return the output
return output;
}
// No change, return input
return input;
}
void test_coco(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;
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 sized = resize_image(im, net.w, net.h);
float *X = sized.data;
time=clock();
float *predictions = network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
draw_coco(im, predictions, 7, "predictions");
free_image(im);
free_image(sized);
#ifdef OPENCV
cvWaitKey(0);
cvDestroyAllWindows();
#endif
if (filename) break;
}
}
static void yolo_image2(const char *cfg, const char *weights, const char *filename, float thresh)
{
int i;
for (i = 0; i < 20; ++i){
char buff[256];
sprintf(buff, "/home/amenmd/myfs/source-codes/oss/darknet/data/labels/%s.png", voc_names[i]);
voc_labels[i] = load_image_color(buff, 0, 0);
}
network net = parse_network_cfg((char *)cfg);
load_weights(&net, (char *)weights);
detection_layer l = net.layers[net.n-1];
set_batch_network(&net, 1);
int j;
float nms=.5;
box *boxes = (box *)calloc(l.side*l.side*l.n, sizeof(box));
float **probs = (float **)calloc(l.side*l.side*l.n, sizeof(float *));
for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = (float *)calloc(l.classes, sizeof(float *));
image im = load_image_color((char *)filename, 0, 0);
image sized = resize_image(im, net.w, net.h);
float *X = sized.data;
float *predictions = network_predict(net, X);
convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
if (nms) do_nms_sort(boxes, probs, l.side*l.side*l.n, l.classes, nms);
//draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, voc_labels, 20);
draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, 0, 20);
show_image(im, "predictions");
save_image(im, "predictions");
show_image(sized, "resized");
free_image(im);
free_image(sized);
}
void test_writing(char *cfgfile, char *weightfile, char *outfile)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
char filename[256];
fgets(filename, 256, stdin);
strtok(filename, "\n");
image im = load_image_color(filename, 0, 0);
//image im = load_image_color("/home/pjreddie/darknet/data/figs/C02-1001-Figure-1.png", 0, 0);
image sized = resize_image(im, 256, 256);
printf("%d %d %d\n", im.h, im.w, im.c);
float *X = sized.data;
time=clock();
float *predictions = network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", filename, sec(clock()-time));
image pred = get_network_image(net);
if (outfile) {
printf("Save image as %s.png (shape: %d %d)\n", outfile, pred.w, pred.h);
save_image(pred, outfile);
} else {
show_image(pred, "prediction");
#ifdef OPENCV
cvWaitKey(0);
#endif
}
free_image(im);
free_image(sized);
}
void validate_coco_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 *base = "results/comp4_det_test_";
list *plist = get_paths("/home/pjreddie/data/voc/test/2007_test.txt");
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
int square = l.sqrt;
int side = l.side;
int j, k;
FILE **fps = calloc(classes, sizeof(FILE *));
for(j = 0; j < classes; ++j){
char buff[1024];
_snprintf(buff, 1024, "%s%s.txt", base, coco_classes[j]);
fps[j] = fopen(buff, "w");
}
box *boxes = calloc(side*side*l.n, sizeof(box));
float **probs = calloc(side*side*l.n, sizeof(float *));
for(j = 0; j < side*side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
float thresh = .001;
int nms = 0;
float iou_thresh = .5;
float nms_thresh = .5;
int total = 0;
int correct = 0;
int proposals = 0;
float avg_iou = 0;
for(i = 0; i < m; ++i){
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
float *predictions = network_predict(net, sized.data);
convert_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 1);
if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms_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 < side*side*l.n; ++k){
if(probs[k][0] > thresh){
++proposals;
}
}
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 < side*side*l.n; ++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;
}
}
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);
free(id);
free_image(orig);
free_image(sized);
}
}
void validate_detector_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));
list *plist = get_paths("data/voc.2007.test");
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
int j, k;
box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
float thresh = .001;
float iou_thresh = .5;
float nms = .4;
int total = 0;
int correct = 0;
int proposals = 0;
float avg_iou = 0;
for(i = 0; i < m; ++i){
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
network_predict(net, sized.data);
get_region_boxes(l, 1, 1, thresh, probs, boxes, 1, 0, .5);
if (nms) do_nms(boxes, probs, l.w*l.h*l.n, 1, nms);
char labelpath[4096];
find_replace(path, "images", "labels", labelpath);
find_replace(labelpath, "JPEGImages", "labels", labelpath);
find_replace(labelpath, ".jpg", ".txt", labelpath);
find_replace(labelpath, ".JPEG", ".txt", labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < l.w*l.h*l.n; ++k){
if(probs[k][0] > thresh){
++proposals;
}
}
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 < l.w*l.h*l.n; ++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;
}
}
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);
free(id);
free_image(orig);
free_image(sized);
}
}
void *fetch_in_thread(void *ptr)
{
in = get_image_from_stream(cap);
in_s = resize_image(in, net.w, net.h);
return 0;
}
void validate_yolo_classify(char *datacfg, char *cfgfile, char *weightfile)
{
list *options = read_data_cfg(datacfg);
//char *train_list = option_find_str(options, "train", "data/train_list.txt");
//char *test_list = option_find_str(options, "test", "data/test_list.txt");
char *valid_list = option_find_str(options, "valid", "data/valid_list.txt");
//char *backup_directory = option_find_str(options, "backup", "/backup/");
//char *label_list = option_find_str(options, "labels", "data/labels_list.txt");
//int classes = option_find_int(options, "classes", 2);
//char **labels = get_labels(label_list);
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 *base = "results/comp4_det_test_";
//list *plist = get_paths("data/voc.2007.test");
list *plist = get_paths(valid_list);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
int square = l.sqrt;
int side = l.side;
int j, k;
FILE **fps = calloc(classes, sizeof(FILE *));
for(j = 0; j < classes; ++j){
char buff[1024];
snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]);
fps[j] = fopen(buff, "w");
}
box *boxes = calloc(side*side*l.n, sizeof(box));
float **probs = calloc(side*side*l.n, sizeof(float *));
for(j = 0; j < side*side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
//float thresh = .001;
float thresh = .2;
float iou_thresh = .5;
//float nms = 0;
float nms = 0.5;
int total = 0;
int correct = 0;
int class_correct = 0;
int proposals = 0;
float avg_iou = 0;
for(i = 0; i < m; ++i){
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
float *predictions = network_predict(net, sized.data);
convert_yolo_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 0);
//if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms);
if (nms) do_nms(boxes, probs, side*side*l.n, classes, nms);
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");
labelpath = find_replace(labelpath, ".bmp", ".txt");
labelpath = find_replace(labelpath, ".dib", ".txt");
labelpath = find_replace(labelpath, ".jpe", ".txt");
labelpath = find_replace(labelpath, ".jp2", ".txt");
labelpath = find_replace(labelpath, ".png", ".txt");
labelpath = find_replace(labelpath, ".pbm", ".txt");
labelpath = find_replace(labelpath, ".pgm", ".txt");
labelpath = find_replace(labelpath, ".ppm", ".txt");
labelpath = find_replace(labelpath, ".sr", ".txt");
labelpath = find_replace(labelpath, ".ras", ".txt");
labelpath = find_replace(labelpath, ".tiff", ".txt");
labelpath = find_replace(labelpath, ".tif", ".txt");
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < side*side*l.n; ++k){
int class = max_index(probs[k], classes);
float prob = probs[k][class];
//fprintf(stderr, "path=%s\t\tk=%d\tprob=%f\tclass=%d\n", path, k, prob, class);
if(prob > thresh){
++proposals;
}
}
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;
int pre_class = -1;
for(k = 0; k < side*side*l.n; ++k){
float iou = box_iou(boxes[k], t);
int class = max_index(probs[k], classes);
float prob = probs[k][class];
//fprintf(stderr, "path=%s\t\tk=%d\tprob=%f\tclass=%d\n", path, k, prob, class);
if(prob > thresh && iou > best_iou){
best_iou = iou;
pre_class = class;
}
}
avg_iou += best_iou;
if(best_iou > iou_thresh){
++correct;
}
if(pre_class == truth[j].id){
++class_correct;
}
//fprintf(stderr, "true_class=%d\tpre_class=%d\n", truth[j].id, pre_class);
}
fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\t\tClassify:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total, 100.*class_correct/total);
free(id);
free_image(orig);
free_image(sized);
}
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);
}
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 validate_yolo_recall(char *cfg, char *weights)
{
network *net = load_network(cfg, weights, 0);
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 *base = "results/comp4_det_test_";
list *plist = get_paths("data/voc.2007.test");
char **paths = (char **)list_to_array(plist);
layer l = net->layers[net->n-1];
int classes = l.classes;
int side = l.side;
int j, k;
FILE **fps = calloc(classes, sizeof(FILE *));
for(j = 0; j < classes; ++j){
char buff[1024];
snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]);
fps[j] = fopen(buff, "w");
}
int m = plist->size;
int i=0;
float thresh = .001;
float iou_thresh = .5;
float nms = 0;
int total = 0;
int correct = 0;
int proposals = 0;
float avg_iou = 0;
for(i = 0; i < m; ++i){
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image sized = resize_image(orig, net->w, net->h);
char *id = basecfg(path);
network_predict(net, sized.data);
int nboxes = 0;
detection *dets = get_network_boxes(net, orig.w, orig.h, thresh, 0, 0, 1, &nboxes);
if (nms) do_nms_obj(dets, side*side*l.n, 1, nms);
char labelpath[4096];
find_replace(path, "images", "labels", labelpath);
find_replace(labelpath, "JPEGImages", "labels", labelpath);
find_replace(labelpath, ".jpg", ".txt", labelpath);
find_replace(labelpath, ".JPEG", ".txt", labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < side*side*l.n; ++k){
if(dets[k].objectness > thresh){
++proposals;
}
}
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 < side*side*l.n; ++k){
float iou = box_iou(dets[k].bbox, t);
if(dets[k].objectness > thresh && iou > best_iou){
best_iou = iou;
}
}
avg_iou += best_iou;
if(best_iou > iou_thresh){
++correct;
}
}
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);
free_detections(dets, nboxes);
free(id);
free_image(orig);
free_image(sized);
}
free_network( net );
}
