MERRY CHRISTMAS I BROKE ALL YOUR DETECTION THINGS

Makefile

@@ -1,7 +1,7 @@
-GPU=0
-CUDNN=0
-OPENCV=0
-OPENMP=0
+GPU=1
+CUDNN=1
+OPENCV=1
+OPENMP=1
 DEBUG=0
 
 ARCH= -gencode arch=compute_30,code=sm_30 \
@@ -57,8 +57,8 @@ CFLAGS+= -DCUDNN
 LDFLAGS+= -lcudnn
 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 detection_layer.o route_layer.o box.o normalization_layer.o avgpool_layer.o layer.o local_layer.o shortcut_layer.o activation_layer.o rnn_layer.o gru_layer.o crnn_layer.o demo.o batchnorm_layer.o region_layer.o reorg_layer.o tree.o  lstm_layer.o
-EXECOBJA=captcha.o lsd.o super.o art.o tag.o cifar.o go.o rnn.o segmenter.o regressor.o classifier.o coco.o yolo.o detector.o nightmare.o attention.o darknet.o
+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 detection_layer.o route_layer.o upsample_layer.o box.o normalization_layer.o avgpool_layer.o layer.o local_layer.o shortcut_layer.o logistic_layer.o activation_layer.o rnn_layer.o gru_layer.o crnn_layer.o demo.o batchnorm_layer.o region_layer.o reorg_layer.o tree.o  lstm_layer.o
+EXECOBJA=captcha.o lsd.o super.o art.o tag.o cifar.o go.o rnn.o segmenter.o regressor.o classifier.o coco.o yolo.o detector.o nightmare.o darknet.o
 ifeq ($(GPU), 1) 
 LDFLAGS+= -lstdc++ 
 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 avgpool_layer_kernels.o

cfg/darknet.cfg

@@ -1,12 +1,12 @@
 [net]
 # Train
+# batch=128
+# subdivisions=1
+# Test
 batch=1
 subdivisions=1
-# Test
-# batch=1
-# subdivisions=1
-height=224
-width=224
+height=256
+width=256
 channels=3
 momentum=0.9
 decay=0.0005

cfg/tiny-yolo.cfg

@@ -120,7 +120,7 @@ filters=425
 activation=linear
 
 [region]
-anchors =  0.57273, 0.677385, 1.87446, 2.06253, 3.33843, 5.47434, 7.88282, 3.52778, 9.77052, 9.16828
+anchors =  18.3274,21.6763,  59.9827,66.001,  106.83,175.179,  252.25,112.889,  312.657,293.385
 bias_match=1
 classes=80
 coords=4

cfg/yolo.cfg

@@ -1,10 +1,10 @@
 [net]
 # Testing
-batch=1
-subdivisions=1
+# batch=1
+# subdivisions=1
 # Training
-# batch=64
-# subdivisions=8
+batch=64
+subdivisions=8
 width=608
 height=608
 channels=3
@@ -239,7 +239,7 @@ activation=linear
 
 
 [region]
-anchors =  0.57273, 0.677385, 1.87446, 2.06253, 3.33843, 5.47434, 7.88282, 3.52778, 9.77052, 9.16828
+anchors = 18.3274,21.6763, 59.9827,66.001, 106.83,175.179, 252.25,112.889, 312.657,293.385
 bias_match=1
 classes=80
 coords=4

examples/classifier.c

@@ -403,6 +403,7 @@ void validate_classifier_single(char *datacfg, char *filename, char *weightfile)
             if(indexes[j] == class) avg_topk += 1;
         }
 
+        printf("%s, %d, %f, %f, \n", paths[i], class, pred[0], pred[1]);
         printf("%d: top 1: %f, top %d: %f\n", i, avg_acc/(i+1), topk, avg_topk/(i+1));
     }
 }
@@ -704,6 +705,44 @@ void test_classifier(char *datacfg, char *cfgfile, char *weightfile, int target_
     }
 }
 
+void file_output_classifier(char *datacfg, char *filename, char *weightfile, char *listfile)
+{
+    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, "names", "data/labels.list");
+    int classes = option_find_int(options, "classes", 2);
+
+    list *plist = get_paths(listfile);
+
+    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(net->hierarchy) hierarchy_predictions(pred, net->outputs, net->hierarchy, 0, 1);
+
+        if(resized.data != im.data) free_image(resized);
+        free_image(im);
+        free_image(crop);
+
+        printf("%s", paths[i]);
+        for(j = 0; j < classes; ++j){
+            printf("\t%g", pred[j]);
+        }
+        printf("\n");
+    }
+}
+
 
 void threat_classifier(char *datacfg, char *cfgfile, char *weightfile, int cam_index, const char *filename)
 {
@@ -922,15 +961,26 @@ void demo_classifier(char *datacfg, char *cfgfile, char *weightfile, int cam_ind
     srand(2222222);
     CvCapture * cap;
 
+    int w = 1280;
+    int h = 720;
+
     if(filename){
         cap = cvCaptureFromFile(filename);
     }else{
         cap = cvCaptureFromCAM(cam_index);
     }
 
+    if(w){
+        cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_WIDTH, w);
+    }
+    if(h){
+        cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_HEIGHT, h);
+    }
+
     int top = option_find_int(options, "top", 1);
 
-    char *name_list = option_find_str(options, "names", 0);
+    char *label_list = option_find_str(options, "labels", 0);
+    char *name_list = option_find_str(options, "names", label_list);
     char **names = get_labels(name_list);
 
     int *indexes = calloc(top, sizeof(int));
@@ -998,6 +1048,7 @@ void run_classifier(int argc, char **argv)
     char *layer_s = (argc > 7) ? argv[7]: 0;
     int layer = layer_s ? atoi(layer_s) : -1;
     if(0==strcmp(argv[2], "predict")) predict_classifier(data, cfg, weights, filename, top);
+    else if(0==strcmp(argv[2], "fout")) file_output_classifier(data, cfg, weights, filename);
     else if(0==strcmp(argv[2], "try")) try_classifier(data, cfg, weights, filename, atoi(layer_s));
     else if(0==strcmp(argv[2], "train")) train_classifier(data, cfg, weights, gpus, ngpus, clear);
     else if(0==strcmp(argv[2], "demo")) demo_classifier(data, cfg, weights, cam_index, filename);

examples/coco.c

@@ -94,14 +94,14 @@ void train_coco(char *cfgfile, char *weightfile)
     save_weights(net, buff);
 }
 
-void print_cocos(FILE *fp, int image_id, box *boxes, float **probs, int num_boxes, int classes, int w, int h)
+static void print_cocos(FILE *fp, int image_id, detection *dets, int num_boxes, int classes, int w, int h)
 {
     int i, j;
     for(i = 0; i < num_boxes; ++i){
-        float xmin = boxes[i].x - boxes[i].w/2.;
-        float xmax = boxes[i].x + boxes[i].w/2.;
-        float ymin = boxes[i].y - boxes[i].h/2.;
-        float ymax = boxes[i].y + boxes[i].h/2.;
+        float xmin = dets[i].bbox.x - dets[i].bbox.w/2.;
+        float xmax = dets[i].bbox.x + dets[i].bbox.w/2.;
+        float ymin = dets[i].bbox.y - dets[i].bbox.h/2.;
+        float ymax = dets[i].bbox.y + dets[i].bbox.h/2.;
 
         if (xmin < 0) xmin = 0;
         if (ymin < 0) ymin = 0;
@@ -114,7 +114,7 @@ void print_cocos(FILE *fp, int image_id, box *boxes, float **probs, int num_boxe
         float bh = ymax - ymin;
 
         for(j = 0; j < classes; ++j){
-            if (probs[i][j]) fprintf(fp, "{\"image_id\":%d, \"category_id\":%d, \"bbox\":[%f, %f, %f, %f], \"score\":%f},\n", image_id, coco_ids[j], bx, by, bw, bh, probs[i][j]);
+            if (dets[i].prob[j]) fprintf(fp, "{\"image_id\":%d, \"category_id\":%d, \"bbox\":[%f, %f, %f, %f], \"score\":%f},\n", image_id, coco_ids[j], bx, by, bw, bh, dets[i].prob[j]);
         }
     }
 }
@@ -140,17 +140,13 @@ void validate_coco(char *cfg, char *weights)
 
     layer l = net->layers[net->n-1];
     int classes = l.classes;
-    int side = l.side;
 
-    int j;
     char buff[1024];
     snprintf(buff, 1024, "%s/coco_results.json", base);
     FILE *fp = fopen(buff, "w");
     fprintf(fp, "[\n");
 
-    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 *));
+    detection *dets = make_network_boxes(net);
 
     int m = plist->size;
     int i=0;
@@ -199,9 +195,9 @@ void validate_coco(char *cfg, char *weights)
             network_predict(net, X);
             int w = val[t].w;
             int h = val[t].h;
-            get_detection_boxes(l, w, h, thresh, probs, boxes, 0);
-            if (nms) do_nms_sort(boxes, probs, side*side*l.n, classes, iou_thresh);
-            print_cocos(fp, image_id, boxes, probs, side*side*l.n, classes, w, h);
+            fill_network_boxes(net, w, h, thresh, 0, 0, 0, dets);
+            if (nms) do_nms_sort(dets, l.side*l.side*l.n, classes, iou_thresh);
+            print_cocos(fp, image_id, dets, l.side*l.side*l.n, classes, w, h);
             free_image(val[t]);
             free_image(val_resized[t]);
         }
@@ -235,17 +231,14 @@ void validate_coco_recall(char *cfgfile, char *weightfile)
         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 *));
+    detection *dets = make_network_boxes(net);
 
     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;
@@ -258,8 +251,9 @@ void validate_coco_recall(char *cfgfile, char *weightfile)
         image sized = resize_image(orig, net->w, net->h);
         char *id = basecfg(path);
         network_predict(net, sized.data);
-        get_detection_boxes(l, 1, 1, thresh, probs, boxes, 1);
-        if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms_thresh);
+
+        fill_network_boxes(net, orig.w, orig.h, thresh, 0, 0, 1, dets);
+        if (nms) do_nms_obj(dets, side*side*l.n, 1, nms);
 
         char labelpath[4096];
         find_replace(path, "images", "labels", labelpath);
@@ -270,7 +264,7 @@ void validate_coco_recall(char *cfgfile, char *weightfile)
         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){
+            if(dets[k].objectness > thresh){
                 ++proposals;
             }
         }
@@ -279,8 +273,8 @@ void validate_coco_recall(char *cfgfile, char *weightfile)
             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){
+                float iou = box_iou(dets[k].bbox, t);
+                if(dets[k].objectness > thresh && iou > best_iou){
                     best_iou = iou;
                 }
             }
@@ -308,10 +302,7 @@ void test_coco(char *cfgfile, char *weightfile, char *filename, float thresh)
     clock_t time;
     char buff[256];
     char *input = buff;
-    int j;
-    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 *));
+    detection *dets = make_network_boxes(net);
     while(1){
         if(filename){
             strncpy(input, filename, 256);
@@ -328,9 +319,11 @@ void test_coco(char *cfgfile, char *weightfile, char *filename, float thresh)
         time=clock();
         network_predict(net, X);
         printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
-        get_detection_boxes(l, 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, 0, coco_classes, alphabet, 80);
+
+        fill_network_boxes(net, 1, 1, thresh, 0, 0, 0, dets);
+        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_image(im);

examples/darknet.c

@@ -12,7 +12,6 @@ extern void run_coco(int argc, char **argv);
 extern void run_captcha(int argc, char **argv);
 extern void run_nightmare(int argc, char **argv);
 extern void run_classifier(int argc, char **argv);
-extern void run_attention(int argc, char **argv);
 extern void run_regressor(int argc, char **argv);
 extern void run_segmenter(int argc, char **argv);
 extern void run_char_rnn(int argc, char **argv);
@@ -432,8 +431,6 @@ int main(int argc, char **argv)
         predict_classifier("cfg/imagenet1k.data", argv[2], argv[3], argv[4], 5);
     } else if (0 == strcmp(argv[1], "classifier")){
         run_classifier(argc, argv);
-    } else if (0 == strcmp(argv[1], "attention")){
-        run_attention(argc, argv);
     } else if (0 == strcmp(argv[1], "regressor")){
         run_regressor(argc, argv);
     } else if (0 == strcmp(argv[1], "segmenter")){