new font strategy

phwizard · Nov 5, 2016 · c7a700d · c7a700d
1 parent 352ae7e
commit c7a700d
Show file tree

Hide file tree

Showing 113 changed files with 331 additions and 210 deletions.
diff --git a/data/labels/100.png b/data/labels/100.png
diff --git a/data/labels/101.png b/data/labels/101.png
diff --git a/data/labels/102.png b/data/labels/102.png
diff --git a/data/labels/103.png b/data/labels/103.png
diff --git a/data/labels/104.png b/data/labels/104.png
diff --git a/data/labels/105.png b/data/labels/105.png
diff --git a/data/labels/106.png b/data/labels/106.png
diff --git a/data/labels/107.png b/data/labels/107.png
diff --git a/data/labels/108.png b/data/labels/108.png
diff --git a/data/labels/109.png b/data/labels/109.png
diff --git a/data/labels/110.png b/data/labels/110.png
diff --git a/data/labels/111.png b/data/labels/111.png
diff --git a/data/labels/112.png b/data/labels/112.png
diff --git a/data/labels/113.png b/data/labels/113.png
diff --git a/data/labels/114.png b/data/labels/114.png
diff --git a/data/labels/115.png b/data/labels/115.png
diff --git a/data/labels/116.png b/data/labels/116.png
diff --git a/data/labels/117.png b/data/labels/117.png
diff --git a/data/labels/118.png b/data/labels/118.png
diff --git a/data/labels/119.png b/data/labels/119.png
diff --git a/data/labels/120.png b/data/labels/120.png
diff --git a/data/labels/121.png b/data/labels/121.png
diff --git a/data/labels/122.png b/data/labels/122.png
diff --git a/data/labels/123.png b/data/labels/123.png
diff --git a/data/labels/124.png b/data/labels/124.png
diff --git a/data/labels/125.png b/data/labels/125.png
diff --git a/data/labels/126.png b/data/labels/126.png
diff --git a/data/labels/32.png b/data/labels/32.png
diff --git a/data/labels/33.png b/data/labels/33.png
diff --git a/data/labels/34.png b/data/labels/34.png
diff --git a/data/labels/35.png b/data/labels/35.png
diff --git a/data/labels/36.png b/data/labels/36.png
diff --git a/data/labels/37.png b/data/labels/37.png
diff --git a/data/labels/38.png b/data/labels/38.png
diff --git a/data/labels/39.png b/data/labels/39.png
diff --git a/data/labels/40.png b/data/labels/40.png
diff --git a/data/labels/41.png b/data/labels/41.png
diff --git a/data/labels/42.png b/data/labels/42.png
diff --git a/data/labels/43.png b/data/labels/43.png
diff --git a/data/labels/44.png b/data/labels/44.png
diff --git a/data/labels/45.png b/data/labels/45.png
diff --git a/data/labels/46.png b/data/labels/46.png
diff --git a/data/labels/47.png b/data/labels/47.png
diff --git a/data/labels/48.png b/data/labels/48.png
diff --git a/data/labels/49.png b/data/labels/49.png
diff --git a/data/labels/50.png b/data/labels/50.png
diff --git a/data/labels/51.png b/data/labels/51.png
diff --git a/data/labels/52.png b/data/labels/52.png
diff --git a/data/labels/53.png b/data/labels/53.png
diff --git a/data/labels/54.png b/data/labels/54.png
diff --git a/data/labels/55.png b/data/labels/55.png
diff --git a/data/labels/56.png b/data/labels/56.png
diff --git a/data/labels/57.png b/data/labels/57.png
diff --git a/data/labels/58.png b/data/labels/58.png
diff --git a/data/labels/59.png b/data/labels/59.png
diff --git a/data/labels/60.png b/data/labels/60.png
diff --git a/data/labels/61.png b/data/labels/61.png
diff --git a/data/labels/62.png b/data/labels/62.png
diff --git a/data/labels/63.png b/data/labels/63.png
diff --git a/data/labels/64.png b/data/labels/64.png
diff --git a/data/labels/65.png b/data/labels/65.png
diff --git a/data/labels/66.png b/data/labels/66.png
diff --git a/data/labels/67.png b/data/labels/67.png
diff --git a/data/labels/68.png b/data/labels/68.png
diff --git a/data/labels/69.png b/data/labels/69.png
diff --git a/data/labels/70.png b/data/labels/70.png
diff --git a/data/labels/71.png b/data/labels/71.png
diff --git a/data/labels/72.png b/data/labels/72.png
diff --git a/data/labels/73.png b/data/labels/73.png
diff --git a/data/labels/74.png b/data/labels/74.png
diff --git a/data/labels/75.png b/data/labels/75.png
diff --git a/data/labels/76.png b/data/labels/76.png
diff --git a/data/labels/77.png b/data/labels/77.png
diff --git a/data/labels/78.png b/data/labels/78.png
diff --git a/data/labels/79.png b/data/labels/79.png
diff --git a/data/labels/80.png b/data/labels/80.png
diff --git a/data/labels/81.png b/data/labels/81.png
diff --git a/data/labels/82.png b/data/labels/82.png
diff --git a/data/labels/83.png b/data/labels/83.png
diff --git a/data/labels/84.png b/data/labels/84.png
diff --git a/data/labels/85.png b/data/labels/85.png
diff --git a/data/labels/86.png b/data/labels/86.png
diff --git a/data/labels/87.png b/data/labels/87.png
diff --git a/data/labels/88.png b/data/labels/88.png
diff --git a/data/labels/89.png b/data/labels/89.png
diff --git a/data/labels/90.png b/data/labels/90.png
diff --git a/data/labels/91.png b/data/labels/91.png
diff --git a/data/labels/92.png b/data/labels/92.png
diff --git a/data/labels/93.png b/data/labels/93.png
diff --git a/data/labels/94.png b/data/labels/94.png
diff --git a/data/labels/95.png b/data/labels/95.png
diff --git a/data/labels/96.png b/data/labels/96.png
diff --git a/data/labels/97.png b/data/labels/97.png
diff --git a/data/labels/98.png b/data/labels/98.png
diff --git a/data/labels/99.png b/data/labels/99.png
diff --git a/data/labels/make_labels.py b/data/labels/make_labels.py
@@ -2,18 +2,22 @@
 import string
 import pipes
 
-#l = ["person","bicycle","car","motorcycle","airplane","bus","train","truck","boat","traffic light","fire hydrant","stop sign","parking meter","bench","bird","cat","dog","horse","sheep","cow","elephant","bear","zebra","giraffe","backpack","umbrella","handbag","tie","suitcase","frisbee","skis","snowboard","sports ball","kite","baseball bat","baseball glove","skateboard","surfboard","tennis racket","bottle","wine glass","cup","fork","knife","spoon","bowl","banana","apple","sandwich","orange","broccoli","carrot","hot dog","pizza","donut","cake","chair","couch","potted plant","bed","dining table","toilet","tv","laptop","mouse","remote","keyboard","cell phone","microwave","oven","toaster","sink","refrigerator","book","clock","vase","scissors","teddy bear","hair drier","toothbrush", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
+font = 'futura-normal'
 
-l = string.printable
+def make_labels(s):
+    l = string.printable
+    for word in l:
+        if word == ' ':
+            os.system('convert -fill black -background white -bordercolor white -font %s -pointsize %d label:"\ " 32_%d.png'%(font,s,s/12-1))
+        if word == '@':
+            os.system('convert -fill black -background white -bordercolor white -font %s -pointsize %d label:"\@" 64_%d.png'%(font,s,s/12-1))
+        elif word == '\\':
+            os.system('convert -fill black -background white -bordercolor white -font %s -pointsize %d label:"\\\\\\\\" 92_%d.png'%(font,s,s/12-1))
+        elif ord(word) in [9,10,11,12,13,14]:
+            pass
+        else:
+            os.system("convert -fill black -background white -bordercolor white -font %s -pointsize %d label:%s \"%d_%d.png\""%(font,s,pipes.quote(word), ord(word),s/12-1))
 
-for word in l:
-    #os.system("convert -fill black -background white -bordercolor white -border 4 -font futura-normal -pointsize 18 label:\"%s\" \"%s.png\""%(word, word))
-    if word == ' ':
-        os.system('convert -fill black -background white -bordercolor white -font futura-normal -pointsize 64 label:"\ " 32.png')
-    elif word == '\\':
-        os.system('convert -fill black -background white -bordercolor white -font futura-normal -pointsize 64 label:"\\\\\\\\" 92.png')
-    elif ord(word) in [9,10,11,12,13,14]:
-        pass
-    else:
-        os.system("convert -fill black -background white -bordercolor white -font futura-normal -pointsize 64 label:%s \"%d.png\""%(pipes.quote(word), ord(word)))
+for i in [12,24,36,48,60,72,84,96]:
+    make_labels(i)
 
diff --git a/src/classifier.c b/src/classifier.c
@@ -13,50 +13,6 @@
 image get_image_from_stream(CvCapture *cap);
 #endif
 
-list *read_data_cfg(char *filename)
-{
-    FILE *file = fopen(filename, "r");
-    if(file == 0) file_error(filename);
-    char *line;
-    int nu = 0;
-    list *options = make_list();
-    while((line=fgetl(file)) != 0){
-        ++ nu;
-        strip(line);
-        switch(line[0]){
-            case '\0':
-            case '#':
-            case ';':
-                free(line);
-                break;
-            default:
-                if(!read_option(line, options)){
-                    fprintf(stderr, "Config file error line %d, could parse: %s\n", nu, line);
-                    free(line);
-                }
-                break;
-        }
-    }
-    fclose(file);
-    return options;
-}
-
-void hierarchy_predictions(float *predictions, int n, tree *hier, int only_leaves)
-{
-    int j;
-    for(j = 0; j < n; ++j){
-        int parent = hier->parent[j];
-        if(parent >= 0){
-            predictions[j] *= predictions[parent]; 
-        }
-    }
-    if(only_leaves){
-        for(j = 0; j < n; ++j){
-            if(!hier->leaf[j]) predictions[j] = 0;
-        }
-    }
-}
-
 float *get_regression_values(char **labels, int n)
 {
     float *v = calloc(n, sizeof(float));
@@ -488,26 +444,6 @@ void validate_classifier_full(char *datacfg, char *filename, char *weightfile)
     }
 }
 
-void change_leaves(tree *t, char *leaf_list)
-{
-    list *llist = get_paths(leaf_list);
-    char **leaves = (char **)list_to_array(llist);
-    int n = llist->size;
-    int i,j;
-    int found = 0;
-    for(i = 0; i < t->n; ++i){
-        t->leaf[i] = 0;
-        for(j = 0; j < n; ++j){
-            if (0==strcmp(t->name[i], leaves[j])){
-                t->leaf[i] = 1;
-                ++found;
-                break;
-            }
-        }
-    }
-    fprintf(stderr, "Found %d leaves.\n", found);
-}
-
 
 void validate_classifier_single(char *datacfg, char *filename, char *weightfile)
 {

diff --git a/src/coco.c b/src/coco.c
@@ -318,7 +318,7 @@ void validate_coco_recall(char *cfgfile, char *weightfile)
 
 void test_coco(char *cfgfile, char *weightfile, char *filename, float thresh)
 {
-    image *alphabet = load_alphabet();
+    image **alphabet = load_alphabet();
     network net = parse_network_cfg(cfgfile);
     if(weightfile){
         load_weights(&net, weightfile);

diff --git a/src/convolutional_kernels.cu b/src/convolutional_kernels.cu
@@ -215,6 +215,10 @@ void pull_convolutional_layer(convolutional_layer layer)
         cuda_pull_array(layer.rolling_mean_gpu, layer.rolling_mean, layer.n);
         cuda_pull_array(layer.rolling_variance_gpu, layer.rolling_variance, layer.n);
     }
+    if (layer.adam){
+        cuda_pull_array(layer.m_gpu, layer.m, layer.c*layer.n*layer.size*layer.size);
+        cuda_pull_array(layer.v_gpu, layer.v, layer.c*layer.n*layer.size*layer.size);
+    }
 }
 
 void push_convolutional_layer(convolutional_layer layer)
@@ -228,6 +232,10 @@ void push_convolutional_layer(convolutional_layer layer)
         cuda_push_array(layer.rolling_mean_gpu, layer.rolling_mean, layer.n);
         cuda_push_array(layer.rolling_variance_gpu, layer.rolling_variance, layer.n);
     }
+    if (layer.adam){
+        cuda_push_array(layer.m_gpu, layer.m, layer.c*layer.n*layer.size*layer.size);
+        cuda_push_array(layer.v_gpu, layer.v, layer.c*layer.n*layer.size*layer.size);
+    }
 }
 
 void update_convolutional_layer_gpu(convolutional_layer layer, int batch, float learning_rate, float momentum, float decay)

diff --git a/src/convolutional_layer.c b/src/convolutional_layer.c
@@ -235,6 +235,11 @@ convolutional_layer make_convolutional_layer(int batch, int h, int w, int c, int
         l.rolling_mean = calloc(n, sizeof(float));
         l.rolling_variance = calloc(n, sizeof(float));
     }
+    if(adam){
+        l.adam = 1;
+        l.m = calloc(c*n*size*size, sizeof(float));
+        l.v = calloc(c*n*size*size, sizeof(float));
+    }
 
 #ifdef GPU
     l.forward_gpu = forward_convolutional_layer_gpu;
@@ -243,9 +248,8 @@ convolutional_layer make_convolutional_layer(int batch, int h, int w, int c, int
 
     if(gpu_index >= 0){
         if (adam) {
-            l.adam = 1;
-            l.m_gpu = cuda_make_array(l.weight_updates, c*n*size*size);
-            l.v_gpu = cuda_make_array(l.weight_updates, c*n*size*size);
+            l.m_gpu = cuda_make_array(l.m, c*n*size*size);
+            l.v_gpu = cuda_make_array(l.v, c*n*size*size);
         }
 
         l.weights_gpu = cuda_make_array(l.weights, c*n*size*size);

diff --git a/src/demo.c b/src/demo.c
@@ -17,7 +17,7 @@
 image get_image_from_stream(CvCapture *cap);
 
 static char **demo_names;
-static image *demo_alphabet;
+static image **demo_alphabet;
 static int demo_classes;
 
 static float **probs;
@@ -94,7 +94,7 @@ double get_wall_time()
 void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, int classes, int frame_skip, char *prefix)
 {
     //skip = frame_skip;
-    image *alphabet = load_alphabet();
+    image **alphabet = load_alphabet();
     int delay = frame_skip;
     demo_names = names;
     demo_alphabet = alphabet;

diff --git a/src/detector.c b/src/detector.c
@@ -5,17 +5,18 @@
 #include "parser.h"
 #include "box.h"
 #include "demo.h"
+#include "option_list.h"
 
 #ifdef OPENCV
 #include "opencv2/highgui/highgui_c.h"
 #endif
 
-static char *voc_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
-
-void train_detector(char *cfgfile, char *weightfile)
+void train_detector(char *datacfg, char *cfgfile, char *weightfile, int clear)
 {
-    char *train_images = "/data/voc/train.txt";
-    char *backup_directory = "/home/pjreddie/backup/";
+    list *options = read_data_cfg(datacfg);
+    char *train_images = option_find_str(options, "train", "data/train.list");
+    char *backup_directory = option_find_str(options, "backup", "/backup/");
+
     srand(time(0));
     char *base = basecfg(cfgfile);
     printf("%s\n", base);
@@ -24,6 +25,7 @@ void train_detector(char *cfgfile, char *weightfile)
     if(weightfile){
         load_weights(&net, weightfile);
     }
+    if(clear) *net.seen = 0;
     printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
     int imgs = net.batch*net.subdivisions;
     int i = *net.seen/imgs;
@@ -124,8 +126,13 @@ void print_detector_detections(FILE **fps, char *id, box *boxes, float **probs,
     }
 }
 
-void validate_detector(char *cfgfile, char *weightfile)
+void validate_detector(char *datacfg, char *cfgfile, char *weightfile)
 {
+    list *options = read_data_cfg(datacfg);
+    char *valid_images = option_find_str(options, "valid", "data/train.list");
+    char *name_list = option_find_str(options, "names", "data/names.list");
+    char **names = get_labels(name_list);
+
     network net = parse_network_cfg(cfgfile);
     if(weightfile){
         load_weights(&net, weightfile);
@@ -135,9 +142,7 @@ void validate_detector(char *cfgfile, char *weightfile)
     srand(time(0));
 
     char *base = "results/comp4_det_test_";
-    //list *plist = get_paths("data/voc.2007.test");
-    list *plist = get_paths("/home/pjreddie/data/voc/2007_test.txt");
-    //list *plist = get_paths("data/voc.2012.test");
+    list *plist = get_paths(valid_images);
     char **paths = (char **)list_to_array(plist);
 
     layer l = net.layers[net.n-1];
@@ -147,7 +152,7 @@ void validate_detector(char *cfgfile, char *weightfile)
     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]);
+        snprintf(buff, 1024, "%s%s.txt", base, names[j]);
         fps[j] = fopen(buff, "w");
     }
     box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
@@ -224,20 +229,13 @@ void validate_detector_recall(char *cfgfile, char *weightfile)
     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 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(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 *));
@@ -299,9 +297,13 @@ void validate_detector_recall(char *cfgfile, char *weightfile)
     }
 }
 
-void test_detector(char *cfgfile, char *weightfile, char *filename, float thresh)
+void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh)
 {
-    image *alphabet = load_alphabet();
+    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);
@@ -335,8 +337,7 @@ void test_detector(char *cfgfile, char *weightfile, char *filename, float thresh
         printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
         get_region_boxes(l, 1, 1, thresh, probs, boxes, 0);
         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, voc_names, voc_labels, 20);
-        draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, voc_names, alphabet, 20);
+        draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes);
         save_image(im, "predictions");
         show_image(im, "predictions");
 
@@ -360,13 +361,21 @@ void run_detector(int argc, char **argv)
         fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
         return;
     }
-
-    char *cfg = argv[3];
-    char *weights = (argc > 4) ? argv[4] : 0;
-    char *filename = (argc > 5) ? argv[5]: 0;
-    if(0==strcmp(argv[2], "test")) test_detector(cfg, weights, filename, thresh);
-    else if(0==strcmp(argv[2], "train")) train_detector(cfg, weights);
-    else if(0==strcmp(argv[2], "valid")) validate_detector(cfg, weights);
+    int clear = find_arg(argc, argv, "-clear");
+
+    char *datacfg = argv[3];
+    char *cfg = argv[4];
+    char *weights = (argc > 5) ? argv[5] : 0;
+    char *filename = (argc > 6) ? argv[6]: 0;
+    if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh);
+    else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, clear);
+    else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights);
     else if(0==strcmp(argv[2], "recall")) validate_detector_recall(cfg, weights);
-    else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, filename, voc_names, 20, frame_skip, prefix);
+    else if(0==strcmp(argv[2], "demo")) {
+        list *options = read_data_cfg(datacfg);
+        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);
+    }
 }