Some changes

Makefile

@@ -36,7 +36,7 @@ endif
 
 OBJ=gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o imagenet.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o layer.o compare.o classifier.o local_layer.o
 ifeq ($(GPU), 1) 
-OBJ+=convolutional_kernels.o deconvolutional_kernels.o activation_kernels.o im2col_kernels.o col2im_kernels.o blas_kernels.o crop_layer_kernels.o dropout_layer_kernels.o maxpool_layer_kernels.o softmax_layer_kernels.o network_kernels.o avgpool_layer_kernels.o yolo_kernels.o
+OBJ+=convolutional_kernels.o deconvolutional_kernels.o activation_kernels.o im2col_kernels.o col2im_kernels.o blas_kernels.o crop_layer_kernels.o dropout_layer_kernels.o maxpool_layer_kernels.o softmax_layer_kernels.o network_kernels.o avgpool_layer_kernels.o yolo_kernels.o coco_kernels.o
 endif
 
 OBJS = $(addprefix $(OBJDIR), $(OBJ))

cfg/yolo-coco.cfg

@@ -0,0 +1,240 @@
+[net]
+batch=64
+subdivisions=4
+height=448
+width=448
+channels=3
+momentum=0.9
+decay=0.0005
+
+learning_rate=0.0001
+policy=steps
+steps=100,200,300,100000,150000
+scales=2.5,2,2,.1,.1
+max_batches = 300000
+
+[crop]
+crop_width=448
+crop_height=448
+flip=0
+angle=0
+saturation = 1.5
+exposure = 1.5
+
+[convolutional]
+filters=64
+size=7
+stride=2
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+filters=192
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+
+#################################
+
+
+[convolutional]
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=3
+stride=2
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[local]
+size=3
+stride=1
+pad=1
+filters=192
+activation=leaky
+
+[dropout]
+probability=.5
+
+[connected]
+output= 4410
+activation=linear
+
+[detection]
+classes=80
+coords=4
+rescore=1
+side=7
+num=2
+softmax=0
+sqrt=1
+jitter=.2
+
+object_scale=1
+noobject_scale=.5
+class_scale=1
+coord_scale=5
+

src/activation_kernels.cu

@@ -10,6 +10,7 @@ extern "C" {
 __device__ float linear_activate_kernel(float x){return x;}
 __device__ float logistic_activate_kernel(float x){return 1./(1. + exp(-x));}
 __device__ float relu_activate_kernel(float x){return x*(x>0);}
+__device__ float elu_activate_kernel(float x){return (x >= 0)*x + (x < 0)*(exp(x)-1);}
 __device__ float relie_activate_kernel(float x){return x*(x>0);}
 __device__ float ramp_activate_kernel(float x){return x*(x>0)+.1*x;}
 __device__ float leaky_activate_kernel(float x){return (x>0) ? x : .1*x;}
@@ -24,6 +25,7 @@ __device__ float plse_activate_kernel(float x)
 __device__ float linear_gradient_kernel(float x){return 1;}
 __device__ float logistic_gradient_kernel(float x){return (1-x)*x;}
 __device__ float relu_gradient_kernel(float x){return (x>0);}
+__device__ float elu_gradient_kernel(float x){return (x >= 0) + (x < 0)*(x + 1);}
 __device__ float relie_gradient_kernel(float x){return (x>0) ? 1 : .01;}
 __device__ float ramp_gradient_kernel(float x){return (x>0)+.1;}
 __device__ float leaky_gradient_kernel(float x){return (x>0) ? 1 : .1;}
@@ -39,6 +41,8 @@ __device__ float activate_kernel(float x, ACTIVATION a)
             return logistic_activate_kernel(x);
         case RELU:
             return relu_activate_kernel(x);
+        case ELU:
+            return elu_activate_kernel(x);
         case RELIE:
             return relie_activate_kernel(x);
         case RAMP:
@@ -62,6 +66,8 @@ __device__ float gradient_kernel(float x, ACTIVATION a)
             return logistic_gradient_kernel(x);
         case RELU:
             return relu_gradient_kernel(x);
+        case ELU:
+            return elu_gradient_kernel(x);
         case RELIE:
             return relie_gradient_kernel(x);
         case RAMP:

src/activations.c

@@ -12,6 +12,8 @@ char *get_activation_string(ACTIVATION a)
             return "logistic";
         case RELU:
             return "relu";
+        case ELU:
+            return "elu";
         case RELIE:
             return "relie";
         case RAMP:
@@ -34,6 +36,7 @@ ACTIVATION get_activation(char *s)
 {
     if (strcmp(s, "logistic")==0) return LOGISTIC;
     if (strcmp(s, "relu")==0) return RELU;
+    if (strcmp(s, "elu")==0) return ELU;
     if (strcmp(s, "relie")==0) return RELIE;
     if (strcmp(s, "plse")==0) return PLSE;
     if (strcmp(s, "linear")==0) return LINEAR;
@@ -53,6 +56,8 @@ float activate(float x, ACTIVATION a)
             return logistic_activate(x);
         case RELU:
             return relu_activate(x);
+        case ELU:
+            return elu_activate(x);
         case RELIE:
             return relie_activate(x);
         case RAMP:
@@ -84,6 +89,8 @@ float gradient(float x, ACTIVATION a)
             return logistic_gradient(x);
         case RELU:
             return relu_gradient(x);
+        case ELU:
+            return elu_gradient(x);
         case RELIE:
             return relie_gradient(x);
         case RAMP:

src/activations.h

@@ -4,7 +4,7 @@
 #include "math.h"
 
 typedef enum{
-    LOGISTIC, RELU, RELIE, LINEAR, RAMP, TANH, PLSE, LEAKY
+    LOGISTIC, RELU, RELIE, LINEAR, RAMP, TANH, PLSE, LEAKY, ELU
 }ACTIVATION;
 
 ACTIVATION get_activation(char *s);
@@ -22,6 +22,7 @@ void gradient_array_ongpu(float *x, int n, ACTIVATION a, float *delta);
 static inline float linear_activate(float x){return x;}
 static inline float logistic_activate(float x){return 1./(1. + exp(-x));}
 static inline float relu_activate(float x){return x*(x>0);}
+static inline float elu_activate(float x){return (x >= 0)*x + (x < 0)*(exp(x)-1);}
 static inline float relie_activate(float x){return x*(x>0);}
 static inline float ramp_activate(float x){return x*(x>0)+.1*x;}
 static inline float leaky_activate(float x){return (x>0) ? x : .1*x;}
@@ -36,6 +37,7 @@ static inline float plse_activate(float x)
 static inline float linear_gradient(float x){return 1;}
 static inline float logistic_gradient(float x){return (1-x)*x;}
 static inline float relu_gradient(float x){return (x>0);}
+static inline float elu_gradient(float x){return (x >= 0) + (x < 0)*(x + 1);}
 static inline float relie_gradient(float x){return (x>0) ? 1 : .01;}
 static inline float ramp_gradient(float x){return (x>0)+.1;}
 static inline float leaky_gradient(float x){return (x>0) ? 1 : .1;}

src/coco.c

@@ -15,30 +15,7 @@ char *coco_classes[] = {"person","bicycle","car","motorcycle","airplane","bus","
 
 int coco_ids[] = {1,2,3,4,5,6,7,8,9,10,11,13,14,15,16,17,18,19,20,21,22,23,24,25,27,28,31,32,33,34,35,36,37,38,39,40,41,42,43,44,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,67,70,72,73,74,75,76,77,78,79,80,81,82,84,85,86,87,88,89,90};
 
-void draw_coco(image im, int num, float thresh, box *boxes, float **probs)
+image coco_labels[80];
-{
-    int classes = 80;
-    int i;
-
-    for(i = 0; i < num; ++i){
-        int class = max_index(probs[i], classes);
-        float prob = probs[i][class];
-        if(prob > thresh){
-            int width = sqrt(prob)*5 + 1;
-            printf("%f %s\n", prob, coco_classes[class]);
-            float red = get_color(0,class,classes);
-            float green = get_color(1,class,classes);
-            float blue = get_color(2,class,classes);
-            box b = boxes[i];
-
-            int left  = (b.x-b.w/2.)*im.w;
-            int right = (b.x+b.w/2.)*im.w;
-            int top   = (b.y-b.h/2.)*im.h;
-            int bot   = (b.y+b.h/2.)*im.h;
-            draw_box_width(im, left, top, right, bot, width, red, green, blue);
-        }
-    }
-}
 
 void train_coco(char *cfgfile, char *weightfile)
 {
@@ -368,6 +345,7 @@ void test_coco(char *cfgfile, char *weightfile, char *filename, float thresh)
     detection_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;
@@ -392,7 +370,8 @@ void test_coco(char *cfgfile, char *weightfile, char *filename, float thresh)
         float *predictions = network_predict(net, X);
         printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
         convert_coco_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
-        draw_coco(im, l.side*l.side*l.n, thresh, boxes, probs);
+        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, coco_classes, coco_labels, 80);
         show_image(im, "predictions");
 
         show_image(sized, "resized");
@@ -406,9 +385,23 @@ void test_coco(char *cfgfile, char *weightfile, char *filename, float thresh)
     }
 }
 
+#ifdef OPENCV
+#ifdef GPU
+void demo_coco(char *cfgfile, char *weightfile, float thresh, int cam_index);
+#endif
+#endif
+
 void run_coco(int argc, char **argv)
 {
+    int i;
+    for(i = 0; i < 80; ++i){
+        char buff[256];
+        sprintf(buff, "data/labels/%s.png", coco_classes[i]);
+        coco_labels[i] = load_image_color(buff, 0, 0);
+    }
     float thresh = find_float_arg(argc, argv, "-thresh", .2);
+    int cam_index = find_int_arg(argc, argv, "-c", 0);
+
     if(argc < 4){
         fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
         return;
@@ -421,4 +414,9 @@ 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);
+#ifdef OPENCV
+#ifdef GPU
+    else if(0==strcmp(argv[2], "demo")) demo_coco(cfg, weights, thresh, cam_index);
+#endif
+#endif
 }

src/coco_kernels.cu

@@ -10,6 +10,7 @@ extern "C" {
 #include "parser.h"
 #include "box.h"
 #include "image.h"
+#include <sys/time.h>
 }
 
 #ifdef OPENCV
@@ -17,7 +18,9 @@ extern "C" {
 #include "opencv2/imgproc/imgproc.hpp"
 extern "C" image ipl_to_image(IplImage* src);
 extern "C" void convert_coco_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness);
-extern "C" void draw_coco(image im, int num, float thresh, box *boxes, float **probs);
+
+extern "C" char *coco_classes[];
+extern "C" image *coco_labels;
 
 static float **probs;
 static box *boxes;
@@ -27,9 +30,10 @@ static image in_s ;
 static image det  ;
 static image det_s;
 static image disp ;
-static cv::VideoCapture cap(0);
+static cv::VideoCapture cap;
+static float fps = 0;
 
-void *fetch_in_thread(void *ptr)
+void *fetch_in_thread_coco(void *ptr)
 {
     cv::Mat frame_m;
     cap >> frame_m;
@@ -40,7 +44,7 @@ void *fetch_in_thread(void *ptr)
     return 0;
 }
 
-void *detect_in_thread(void *ptr)
+void *detect_in_thread_coco(void *ptr)
 {
     float nms = .4;
     float thresh = .2;
@@ -53,12 +57,13 @@ void *detect_in_thread(void *ptr)
     if (nms > 0) do_nms(boxes, probs, l.side*l.side*l.n, l.classes, nms);
     printf("\033[2J");
     printf("\033[1;1H");
-    printf("\nObjects:\n\n");
+    printf("\nFPS:%.0f\n",fps);
-    draw_coco(det, l.side*l.side*l.n, thresh, boxes, probs);
+    printf("Objects:\n\n");
+    draw_detections(det, l.side*l.side*l.n, thresh, boxes, probs, coco_classes, coco_labels, 80);
     return 0;
 }
 
-extern "C" void demo_coco(char *cfgfile, char *weightfile, float thresh)
+extern "C" void demo_coco(char *cfgfile, char *weightfile, float thresh, int cam_index)
 {
     printf("YOLO demo\n");
     net = parse_network_cfg(cfgfile);
@@ -69,6 +74,8 @@ extern "C" void demo_coco(char *cfgfile, char *weightfile, float thresh)
 
     srand(2222222);
 
+    cv::VideoCapture cam(cam_index);
+    cap = cam;
     if(!cap.isOpened()) error("Couldn't connect to webcam.\n");
 
     detection_layer l = net.layers[net.n-1];
@@ -81,19 +88,21 @@ extern "C" void demo_coco(char *cfgfile, char *weightfile, float thresh)
     pthread_t fetch_thread;
     pthread_t detect_thread;
 
-    fetch_in_thread(0);
+    fetch_in_thread_coco(0);
     det = in;
     det_s = in_s;
 
-    fetch_in_thread(0);
+    fetch_in_thread_coco(0);
-    detect_in_thread(0);
+    detect_in_thread_coco(0);
     disp = det;
     det = in;
     det_s = in_s;
 
     while(1){
-        if(pthread_create(&fetch_thread, 0, fetch_in_thread, 0)) error("Thread creation failed");
+        struct timeval tval_before, tval_after, tval_result;
-        if(pthread_create(&detect_thread, 0, detect_in_thread, 0)) error("Thread creation failed");
+        gettimeofday(&tval_before, NULL);
+        if(pthread_create(&fetch_thread, 0, fetch_in_thread_coco, 0)) error("Thread creation failed");
+        if(pthread_create(&detect_thread, 0, detect_in_thread_coco, 0)) error("Thread creation failed");
         show_image(disp, "YOLO");
         free_image(disp);
         cvWaitKey(1);
@@ -103,10 +112,15 @@ extern "C" void demo_coco(char *cfgfile, char *weightfile, float thresh)
         disp  = det;
         det   = in;
         det_s = in_s;
+
+        gettimeofday(&tval_after, NULL);
+        timersub(&tval_after, &tval_before, &tval_result);
+        float curr = 1000000.f/((long int)tval_result.tv_usec);
+        fps = .9*fps + .1*curr;
     }
 }
 #else
-extern "C" void demo_coco(char *cfgfile, char *weightfile, float thresh){
+extern "C" void demo_coco(char *cfgfile, char *weightfile, float thresh, int cam_index){
     fprintf(stderr, "YOLO-COCO demo needs OpenCV for webcam images.\n");
 }
 #endif

src/image.c

@@ -28,6 +28,26 @@ float get_color(int c, int x, int max)
     return r;
 }
 
+void draw_label(image a, int r, int c, image 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;
+
+    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, j+r, k, rgb[k] * val);
+            }
+        }
+    }
+    free_image(rl);
+}
+
 void draw_box(image a, int x1, int y1, int x2, int y2, float r, float g, float b)
 {
     //normalize_image(a);
@@ -42,25 +62,25 @@ void draw_box(image a, int x1, int y1, int x2, int y2, float r, float g, float b
     if(y2 < 0) y2 = 0;
     if(y2 >= a.h) y2 = a.h-1;
 
-    for(i = x1; i < x2; ++i){
+    for(i = x1; i <= x2; ++i){
-        a.data[i + y1*a.w + 0*a.w*a.h] = b;
+        a.data[i + y1*a.w + 0*a.w*a.h] = r;
-        a.data[i + y2*a.w + 0*a.w*a.h] = b;
+        a.data[i + y2*a.w + 0*a.w*a.h] = r;
 
         a.data[i + y1*a.w + 1*a.w*a.h] = g;
         a.data[i + y2*a.w + 1*a.w*a.h] = g;
 
-        a.data[i + y1*a.w + 2*a.w*a.h] = r;
+        a.data[i + y1*a.w + 2*a.w*a.h] = b;
-        a.data[i + y2*a.w + 2*a.w*a.h] = r;
+        a.data[i + y2*a.w + 2*a.w*a.h] = b;
     }
-    for(i = y1; i < y2; ++i){
+    for(i = y1; i <= y2; ++i){
-        a.data[x1 + i*a.w + 0*a.w*a.h] = b;
+        a.data[x1 + i*a.w + 0*a.w*a.h] = r;
-        a.data[x2 + i*a.w + 0*a.w*a.h] = b;
+        a.data[x2 + i*a.w + 0*a.w*a.h] = r;
 
         a.data[x1 + i*a.w + 1*a.w*a.h] = g;
         a.data[x2 + i*a.w + 1*a.w*a.h] = g;
 
-        a.data[x1 + i*a.w + 2*a.w*a.h] = r;
+        a.data[x1 + i*a.w + 2*a.w*a.h] = b;
-        a.data[x2 + i*a.w + 2*a.w*a.h] = r;
+        a.data[x2 + i*a.w + 2*a.w*a.h] = b;
     }
 }
 
@@ -85,6 +105,43 @@ void draw_bbox(image a, box bbox, int w, float r, float g, float b)
     }
 }
 
+void draw_detections(image im, int num, float thresh, box *boxes, float **probs, char **names, image *labels, int classes)
+{
+    int i;
+
+    for(i = 0; i < num; ++i){
+        int class = max_index(probs[i], classes);
+        float prob = probs[i][class];
+        if(prob > thresh){
+            int width = pow(prob, 1./2.)*10+1;
+            printf("%s: %.2f\n", names[class], prob);
+            int offset = class*17 % classes;
+            float red = get_color(0,offset,classes);
+            float green = get_color(1,offset,classes);
+            float blue = get_color(2,offset,classes);
+            float rgb[3];
+            rgb[0] = red;
+            rgb[1] = green;
+            rgb[2] = blue;
+            box b = boxes[i];
+
+            int left  = (b.x-b.w/2.)*im.w;
+            int right = (b.x+b.w/2.)*im.w;
+            int top   = (b.y-b.h/2.)*im.h;
+            int bot   = (b.y+b.h/2.)*im.h;
+
+            if(left < 0) left = 0;
+            if(right > im.w-1) right = im.w-1;
+            if(top < 0) top = 0;
+            if(bot > im.h-1) bot = im.h-1;
+
+            draw_box_width(im, left, top, right, bot, width, red, green, blue);
+            if (labels) draw_label(im, top + width, left, labels[class], rgb);
+        }
+    }
+}
+
+
 void flip_image(image a)
 {
     int i,j,k;

src/image.h

@@ -20,6 +20,8 @@ void flip_image(image a);
 void draw_box(image a, int x1, int y1, int x2, int y2, float r, float g, float b);
 void draw_box_width(image a, int x1, int y1, int x2, int y2, int w, float r, float g, float b);
 void draw_bbox(image a, box bbox, int w, float r, float g, float b);
+void draw_label(image a, int r, int c, image label, const float *rgb);
+void draw_detections(image im, int num, float thresh, box *boxes, float **probs, char **names, image *labels, int classes);
 image image_distance(image a, image b);
 void scale_image(image m, float s);
 image crop_image(image im, int dx, int dy, int w, int h);

src/layer.h

@@ -130,11 +130,12 @@ typedef struct {
     float * x_gpu;
     float * x_norm_gpu;
     float * weights_gpu;
-    float * biases_gpu;
-    float * scales_gpu;
-
     float * weight_updates_gpu;
+
+    float * biases_gpu;
     float * bias_updates_gpu;
+
+    float * scales_gpu;
     float * scale_updates_gpu;
 
     float * output_gpu;

src/network.c

@@ -26,6 +26,17 @@ int get_current_batch(network net)
     return batch_num;
 }
 
+void reset_momentum(network net)
+{
+    if (net.momentum == 0) return;
+    net.learning_rate = 0;
+    net.momentum = 0;
+    net.decay = 0;
+    #ifdef GPU
+        if(gpu_index >= 0) update_network_gpu(net);
+    #endif
+}
+
 float get_current_rate(network net)
 {
     int batch_num = get_current_batch(net);
@@ -41,6 +52,7 @@ float get_current_rate(network net)
             for(i = 0; i < net.num_steps; ++i){
                 if(net.steps[i] > batch_num) return rate;
                 rate *= net.scales[i];
+                if(net.steps[i] > batch_num - 1) reset_momentum(net);
             }
             return rate;
         case EXP:

src/network.h

@@ -51,6 +51,7 @@ float * get_network_delta_gpu_layer(network net, int i);
 float *get_network_output_gpu(network net);
 void forward_network_gpu(network net, network_state state);
 void backward_network_gpu(network net, network_state state);
+void update_network_gpu(network net);
 #endif
 
 float get_current_rate(network net);

src/yolo.c

@@ -11,40 +11,6 @@
 
 char *voc_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
 
-void draw_yolo(image im, int num, float thresh, box *boxes, float **probs)
-{
-    int classes = 20;
-    int i;
-
-    for(i = 0; i < num; ++i){
-        int class = max_index(probs[i], classes);
-        float prob = probs[i][class];
-        if(prob > thresh){
-            int width = pow(prob, 1./2.)*10+1;
-            width = 8;
-            printf("%s: %.2f\n", voc_names[class], prob);
-            class = class * 7 % 20;
-            float red = get_color(0,class,classes);
-            float green = get_color(1,class,classes);
-            float blue = get_color(2,class,classes);
-            //red = green = blue = 0;
-            box b = boxes[i];
-
-            int left  = (b.x-b.w/2.)*im.w;
-            int right = (b.x+b.w/2.)*im.w;
-            int top   = (b.y-b.h/2.)*im.h;
-            int bot   = (b.y+b.h/2.)*im.h;
-
-            if(left < 0) left = 0;
-            if(right > im.w-1) right = im.w-1;
-            if(top < 0) top = 0;
-            if(bot > im.h-1) bot = im.h-1;
-
-            draw_box_width(im, left, top, right, bot, width, red, green, blue);
-        }
-    }
-}
-
 void train_yolo(char *cfgfile, char *weightfile)
 {
     char *train_images = "data/voc.0712.trainval";
@@ -377,7 +343,7 @@ void test_yolo(char *cfgfile, char *weightfile, char *filename, float thresh)
         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_yolo(im, l.side*l.side*l.n, thresh, boxes, probs);
+        draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, 0, 20);
         show_image(im, "predictions");
 
         show_image(sized, "resized");

src/yolo_kernels.cu

@@ -20,6 +20,8 @@ extern "C" image ipl_to_image(IplImage* src);
 extern "C" void convert_yolo_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness);
 extern "C" void draw_yolo(image im, int num, float thresh, box *boxes, float **probs);
 
+extern "C" char *voc_names[];
+
 static float **probs;
 static box *boxes;
 static network net;
@@ -57,7 +59,7 @@ void *detect_in_thread(void *ptr)
     printf("\033[1;1H");
     printf("\nFPS:%.0f\n",fps);
     printf("Objects:\n\n");
-    draw_yolo(det, l.side*l.side*l.n, thresh, boxes, probs);
+    draw_detections(det, l.side*l.side*l.n, thresh, boxes, probs, voc_names, 0, 20);
     return 0;
 }