:charizard: fixed non-square aspect ratio thing :charizard:

cfg/yolo9000.cfg

@@ -1,10 +1,10 @@
 [net]
 # Testing
-# batch=1
-# subdivisions=1
+batch=1
+subdivisions=1
 # Training
-batch=64
-subdivisions=8
+# batch=64
+# subdivisions=8
 batch=1
 subdivisions=1
 height=544

src/coco.c

@@ -380,5 +380,5 @@ void run_coco(int argc, char **argv)
     else if(0==strcmp(argv[2], "train")) train_coco(cfg, weights);
     else if(0==strcmp(argv[2], "valid")) validate_coco(cfg, weights);
     else if(0==strcmp(argv[2], "recall")) validate_coco_recall(cfg, weights);
-    else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, filename, coco_classes, 80, frame_skip, prefix, .5);
+    else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, filename, coco_classes, 80, frame_skip, prefix, .5, 0,0,0,0);
 }

src/demo.c

@@ -68,7 +68,7 @@ void *detect_in_thread(void *ptr)
     if(l.type == DETECTION){
         get_detection_boxes(l, 1, 1, demo_thresh, probs, boxes, 0);
     } else if (l.type == REGION){
-        get_region_boxes(l, in.w, in.h, demo_thresh, probs, boxes, 0, 0, demo_hier_thresh, 1);
+        get_region_boxes(l, in.w, in.h, net.w, net.h, demo_thresh, probs, boxes, 0, 0, demo_hier_thresh, 1);
     } else {
         error("Last layer must produce detections\n");
     }
@@ -96,7 +96,7 @@ double get_wall_time()
     return (double)time.tv_sec + (double)time.tv_usec * .000001;
 }
 
-void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, int classes, int frame_skip, char *prefix, float hier_thresh)
+void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, int classes, int frame_skip, char *prefix, float hier_thresh, int w, int h, int fps, int fullscreen)
 {
     //skip = frame_skip;
     image **alphabet = load_alphabet();
@@ -120,10 +120,15 @@ void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const ch
         cap = cvCaptureFromFile(filename);
     }else{
         cap = cvCaptureFromCAM(cam_index);
-        if(DEMO){
-            cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_WIDTH, 1920);
-            cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_HEIGHT, 1080);
-            cvSetCaptureProperty(cap, CV_CAP_PROP_FPS, 60);
+
+        if(w){
+            cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_WIDTH, w);
+        }
+        if(h){
+            cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_HEIGHT, h);
+        }
+        if(fps){
+            cvSetCaptureProperty(cap, CV_CAP_PROP_FPS, fps);
         }
     }
 
@@ -164,8 +169,12 @@ void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const ch
     int count = 0;
     if(!prefix){
         cvNamedWindow("Demo", CV_WINDOW_NORMAL); 
-        cvMoveWindow("Demo", 0, 0);
-        cvResizeWindow("Demo", 1352, 1013);
+        if(fullscreen){
+            cvSetWindowProperty("Demo", CV_WND_PROP_FULLSCREEN, CV_WINDOW_FULLSCREEN);
+        } else {
+            cvMoveWindow("Demo", 0, 0);
+            cvResizeWindow("Demo", 1352, 1013);
+        }
     }
 
     double before = get_wall_time();
@@ -184,6 +193,12 @@ void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const ch
                     else if(frame_skip == 4) frame_skip = 0;
                     else if(frame_skip == 60) frame_skip = 4;   
                     else frame_skip = 0;
+                } else if (c == 27) {
+                    return;
+                } else if (c == 63232) {
+                    demo_thresh += .01;
+                } else if (c == 63233) {
+                    demo_thresh -= .01;
                 }
             }else{
                 char buff[256];
@@ -224,7 +239,7 @@ void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const ch
     }
 }
 #else
-void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, int classes, int frame_skip, char *prefix, float hier_thresh)
+void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, int classes, int frame_skip, char *prefix, float hier_thresh, int w, int h, int fps, int fullscreen)
 {
     fprintf(stderr, "Demo needs OpenCV for webcam images.\n");
 }

src/demo.h

@@ -2,6 +2,6 @@
 #define DEMO_H
 
 #include "image.h"
-void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, int classes, int frame_skip, char *prefix, float hier_thresh);
+void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, int classes, int frame_skip, char *prefix, float hier_thresh, int w, int h, int fps, int fullscreen);
 
 #endif

src/detector.c

@@ -346,7 +346,7 @@ void validate_detector_flip(char *datacfg, char *cfgfile, char *weightfile, char
             network_predict(net, input.data);
             int w = val[t].w;
             int h = val[t].h;
-            get_region_boxes(l, w, h, thresh, probs, boxes, 0, map, .5, 0);
+            get_region_boxes(l, w, h, net.w, net.h, thresh, probs, boxes, 0, map, .5, 0);
             if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, nms);
             if (coco){
                 print_cocos(fp, path, boxes, probs, l.w*l.h*l.n, classes, w, h);
@@ -477,7 +477,7 @@ void validate_detector(char *datacfg, char *cfgfile, char *weightfile, char *out
             network_predict(net, X);
             int w = val[t].w;
             int h = val[t].h;
-            get_region_boxes(l, w, h, thresh, probs, boxes, 0, map, .5, 0);
+            get_region_boxes(l, w, h, net.w, net.h, thresh, probs, boxes, 0, map, .5, 0);
             if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, nms);
             if (coco){
                 print_cocos(fp, path, boxes, probs, l.w*l.h*l.n, classes, w, h);
@@ -541,7 +541,7 @@ void validate_detector_recall(char *cfgfile, char *weightfile)
         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, 0);
+        get_region_boxes(l, sized.w, sized.h, net.w, net.h, thresh, probs, boxes, 1, 0, .5, 1);
         if (nms) do_nms(boxes, probs, l.w*l.h*l.n, 1, nms);
 
         char labelpath[4096];
@@ -624,16 +624,16 @@ void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filenam
         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, 0);
+        get_region_boxes(l, im.w, im.h, net.w, net.h, thresh, probs, boxes, 0, 0, hier_thresh, 1);
         if (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(sized, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes);
+        draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes);
         if(outfile){
-            save_image(sized, outfile);
+            save_image(im, outfile);
         }
         else{
-            save_image(sized, "predictions");
-            show_image(sized, "predictions");
+            save_image(im, "predictions");
+            show_image(im, "predictions");
 #ifdef OPENCV
             cvWaitKey(0);
             cvDestroyAllWindows();
@@ -684,6 +684,10 @@ void run_detector(int argc, char **argv)
     }
 
     int clear = find_arg(argc, argv, "-clear");
+    int fullscreen = find_arg(argc, argv, "-fullscreen");
+    int height = find_int_arg(argc, argv, "-h", 0);
+    int width = find_int_arg(argc, argv, "-w", 0);
+    int fps = find_int_arg(argc, argv, "-fps", 0);
 
     char *datacfg = argv[3];
     char *cfg = argv[4];
@@ -699,6 +703,6 @@ void run_detector(int argc, char **argv)
         int classes = option_find_int(options, "classes", 20);
         char *name_list = option_find_str(options, "names", "data/names.list");
         char **names = get_labels(name_list);
-        demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, hier_thresh);
+        demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, hier_thresh, width, height, fps, fullscreen);
     }
 }

src/lsd.c

@@ -548,7 +548,7 @@ void train_dcgan(char *cfg, char *weight, char *acfg, char *aweight, int clear,
             printf("%f\n", genaloss);
 
             scal_ongpu(imlayer.outputs*imlayer.batch, 1, imerror, 1);
-            scal_ongpu(imlayer.outputs*imlayer.batch, .00, gnet.layers[gnet.n-1].delta_gpu, 1);
+            scal_ongpu(imlayer.outputs*imlayer.batch, .1, gnet.layers[gnet.n-1].delta_gpu, 1);
 
             printf("realness %f\n", cuda_mag_array(imerror, imlayer.outputs*imlayer.batch));
             printf("features %f\n", cuda_mag_array(gnet.layers[gnet.n-1].delta_gpu, imlayer.outputs*imlayer.batch));

src/region_layer.c

@@ -315,7 +315,35 @@ void backward_region_layer(const layer l, network net)
      */
 }
 
-void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *boxes, int only_objectness, int *map, float tree_thresh, int nomult)
+void correct_region_boxes(box *boxes, int n, int w, int h, int netw, int neth, int relative)
+{
+    int i;
+    int new_w=0;
+    int new_h=0;
+    if (((float)netw/w) < ((float)neth/h)) {
+        new_w = netw;
+        new_h = (h * netw)/w;
+    } else {
+        new_h = neth;
+        new_w = (w * neth)/h;
+    }
+    for (i = 0; i < n; ++i){
+        box b = boxes[i];
+        b.x =  (b.x - (netw - new_w)/2./netw) / ((float)new_w/netw); 
+        b.y =  (b.y - (neth - new_h)/2./neth) / ((float)new_h/neth); 
+        b.w *= (float)netw/new_w;
+        b.h *= (float)neth/new_h;
+        if(!relative){
+            b.x *= w;
+            b.w *= w;
+            b.y *= h;
+            b.h *= h;
+        }
+        boxes[i] = b;
+    }
+}
+
+void get_region_boxes(layer l, int w, int h, int netw, int neth, float thresh, float **probs, box *boxes, int only_objectness, int *map, float tree_thresh, int relative)
 {
     int i,j,n,z;
     float *predictions = l.output;
@@ -354,19 +382,6 @@ void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *b
             int box_index = entry_index(l, 0, n*l.w*l.h + i, 0);
             float scale = predictions[obj_index];
             boxes[index] = get_region_box(predictions, l.biases, n, box_index, col, row, l.w, l.h, l.w*l.h);
-            if(1){
-                int max = w > h ? w : h;
-                boxes[index].x =  (boxes[index].x - (max - w)/2./max) / ((float)w/max); 
-                boxes[index].y =  (boxes[index].y - (max - h)/2./max) / ((float)h/max); 
-                boxes[index].w *= (float)max/w;
-                boxes[index].h *= (float)max/h;
-            }
-            if(!nomult){
-                boxes[index].x *= w;
-                boxes[index].y *= h;
-                boxes[index].w *= w;
-                boxes[index].h *= h;
-            }
 
             int class_index = entry_index(l, 0, n*l.w*l.h + i, 5);
             if(l.softmax_tree){
@@ -393,12 +408,12 @@ void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *b
                     // TODO REMOVE
                     // if (j != 15 && j != 16) probs[index][j] = 0; 
                     /*
-                     if (j != 0) probs[index][j] = 0; 
-                     int blacklist[] = {121, 497, 482, 504, 122, 518,481, 418, 542, 491, 914, 478, 120, 510,500};
-                     int bb;
-                     for (bb = 0; bb < sizeof(blacklist)/sizeof(int); ++bb){
-                        if(index == blacklist[bb]) probs[index][j] = 0;
-                     }
+                       if (j != 0) probs[index][j] = 0; 
+                       int blacklist[] = {121, 497, 482, 504, 122, 518,481, 418, 542, 491, 914, 478, 120, 510,500};
+                       int bb;
+                       for (bb = 0; bb < sizeof(blacklist)/sizeof(int); ++bb){
+                       if(index == blacklist[bb]) probs[index][j] = 0;
+                       }
                      */
                 }
                 probs[index][l.classes] = max;
@@ -408,6 +423,7 @@ void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *b
             }
         }
     }
+    correct_region_boxes(boxes, l.w*l.h*l.n, w, h, netw, neth, relative);
 }
 
 #ifdef GPU

src/region_layer.h

@@ -7,7 +7,7 @@
 layer make_region_layer(int batch, int h, int w, int n, int classes, int coords);
 void forward_region_layer(const layer l, network net);
 void backward_region_layer(const layer l, network net);
-void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *boxes, int only_objectness, int *map, float tree_thresh, int nomult);
+void get_region_boxes(layer l, int w, int h, int netw, int neth, float thresh, float **probs, box *boxes, int only_objectness, int *map, float tree_thresh, int relative);
 void resize_region_layer(layer *l, int w, int h);
 void zero_objectness(layer l);
 

src/yolo.c

@@ -347,5 +347,5 @@ void run_yolo(int argc, char **argv)
     else if(0==strcmp(argv[2], "train")) train_yolo(cfg, weights);
     else if(0==strcmp(argv[2], "valid")) validate_yolo(cfg, weights);
     else if(0==strcmp(argv[2], "recall")) validate_yolo_recall(cfg, weights);
-    else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, filename, voc_names, 20, frame_skip, prefix, .5);
+    else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, filename, voc_names, 20, frame_skip, prefix, .5, 0,0,0,0);
 }