scripts and stuff

cfg/yolo-small.cfg

@@ -199,6 +199,6 @@ activation=logistic
 classes=20
 coords=4
 rescore=1
-joint=1
-objectness = 0
-background=0
+joint=0
+objectness=1
+

scripts/voc_label.py

@@ -0,0 +1,56 @@
+import xml.etree.ElementTree as ET
+import pickle
+import os
+from os import listdir, getcwd
+from os.path import join
+
+sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
+
+classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
+
+
+def convert(size, box):
+    dw = 1./size[0]
+    dh = 1./size[1]
+    x = (box[0] + box[1])/2.0
+    y = (box[2] + box[3])/2.0
+    w = box[1] - box[0]
+    h = box[3] - box[2]
+    x = x*dw
+    w = w*dw
+    y = y*dh
+    h = h*dh
+    return (x,y,w,h)
+
+def convert_annotation(year, image_id):
+    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
+    out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year, image_id), 'w')
+    tree=ET.parse(in_file)
+    root = tree.getroot()
+    size = root.find('size')
+    w = int(size.find('width').text)
+    h = int(size.find('height').text)
+
+    for obj in root.iter('object'):
+        difficult = obj.find('difficult').text
+        cls = obj.find('name').text
+        if cls not in classes or int(difficult) == 1:
+            continue
+        cls_id = classes.index(cls)
+        xmlbox = obj.find('bndbox')
+        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
+        bb = convert((w,h), b)
+        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
+
+wd = getcwd()
+
+for year, image_set in sets:
+    if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)):
+        os.makedirs('VOCdevkit/VOC%s/labels/'%(year))
+    image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
+    list_file = open('%s_%s.txt'%(year, image_set), 'w')
+    for image_id in image_ids:
+        list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n'%(wd, year, image_id))
+        convert_annotation(year, image_id)
+    list_file.close()
+

src/detection.c

@@ -51,6 +51,8 @@ void draw_detection(image im, float *box, int side, int objectness, char *label)
 
 void train_detection(char *cfgfile, char *weightfile)
 {
+    char *train_images = "/home/pjreddie/data/voc/test/train.txt";
+    char *backup_directory = "/home/pjreddie/backup/";
     srand(time(0));
     data_seed = time(0);
     char *base = basecfg(cfgfile);
@@ -71,7 +73,7 @@ void train_detection(char *cfgfile, char *weightfile)
     int side = sqrt(get_detection_layer_locations(layer));
 
     char **paths;
-    list *plist = get_paths("/home/pjreddie/data/voc/test/train.txt");
+    list *plist = get_paths(train_images);
     int N = plist->size;
 
     paths = (char **)list_to_array(plist);
@@ -96,26 +98,26 @@ void train_detection(char *cfgfile, char *weightfile)
             fprintf(stderr, "Starting second stage...\n");
             net.learning_rate *= 10;
             char buff[256];
-            sprintf(buff, "/home/pjreddie/imagenet_backup/%s_first_stage.weights", base);
+            sprintf(buff, "%s/%s_first_stage.weights", backup_directory, base);
             save_weights(net, buff);
         }
         if((i-1)*imgs <= 80*N && i*imgs > N*80){
             fprintf(stderr, "Second stage done.\n");
             net.learning_rate *= .1;
             char buff[256];
-            sprintf(buff, "/home/pjreddie/imagenet_backup/%s_second_stage.weights", base);
+            sprintf(buff, "%s/%s_second_stage.weights", backup_directory, base);
             save_weights(net, buff);
             return;
         }
         if(i%1000==0){
             char buff[256];
-            sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
+            sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
             save_weights(net, buff);
         }
         free_data(train);
     }
     char buff[256];
-    sprintf(buff, "/home/pjreddie/imagenet_backup/%s_final.weights",base);
+    sprintf(buff, "%s/%s_final.weights", backup_directory, base);
     save_weights(net, buff);
 }