diff --git a/cfg/tiny-yolo.cfg b/cfg/tiny-yolo.cfg
index 5580098b..9a4a184f 100644
--- a/cfg/tiny-yolo.cfg
+++ b/cfg/tiny-yolo.cfg
@@ -1,6 +1,10 @@
 [net]
-batch=64
-subdivisions=8
+# Training
+# batch=64
+# subdivisions=2
+# Testing
+batch=1
+subdivisions=1
 width=416
 height=416
 channels=3
@@ -12,10 +16,11 @@ exposure = 1.5
 hue=.1
 
 learning_rate=0.001
-max_batches = 120000
+burn_in=1000
+max_batches = 500200
 policy=steps
-steps=-1,100,80000,100000
-scales=.1,10,.1,.1
+steps=400000,450000
+scales=.1,.1
 
 [convolutional]
 batch_normalize=1
@@ -104,7 +109,7 @@ batch_normalize=1
 size=3
 stride=1
 pad=1
-filters=1024
+filters=512
 activation=leaky
 
 [convolutional]
@@ -115,14 +120,14 @@ filters=425
 activation=linear
 
 [region]
-anchors = 0.738768,0.874946,  2.42204,2.65704,  4.30971,7.04493,  10.246,4.59428,  12.6868,11.8741
+anchors =  0.57273, 0.677385, 1.87446, 2.06253, 3.33843, 5.47434, 7.88282, 3.52778, 9.77052, 9.16828
 bias_match=1
 classes=80
 coords=4
 num=5
 softmax=1
 jitter=.2
-rescore=1
+rescore=0
 
 object_scale=5
 noobject_scale=1
diff --git a/include/darknet.h b/include/darknet.h
index 4f6bd6d6..cdf3cc66 100644
--- a/include/darknet.h
+++ b/include/darknet.h
@@ -699,6 +699,9 @@ float *network_predict_p(network *net, float *input);
 int network_width(network *net);
 int network_height(network *net);
 float *network_predict_image(network *net, image im);
+void network_detect(network *net, image im, float thresh, float hier_thresh, float nms, box *boxes, float **probs);
+int num_boxes(network *net);
+box *make_boxes(network *net);
 
 void reset_network_state(network net, int b);
 void reset_network_state(network net, int b);
diff --git a/python/darknet.py b/python/darknet.py
index 7dff2f06..b2750aea 100644
--- a/python/darknet.py
+++ b/python/darknet.py
@@ -15,6 +15,12 @@ def sample(probs):
 def c_array(ctype, values):
     return (ctype * len(values))(*values)
 
+class BOX(Structure):
+    _fields_ = [("x", c_float),
+                ("y", c_float),
+                ("w", c_float),
+                ("h", c_float)]
+
 class IMAGE(Structure):
     _fields_ = [("w", c_int),
                 ("h", c_int),
@@ -36,6 +42,24 @@ predict = lib.network_predict_p
 predict.argtypes = [c_void_p, POINTER(c_float)]
 predict.restype = POINTER(c_float)
 
+make_boxes = lib.make_boxes
+make_boxes.argtypes = [c_void_p]
+make_boxes.restype = POINTER(BOX)
+
+free_ptrs = lib.free_ptrs
+free_ptrs.argtypes = [POINTER(c_void_p), c_int]
+
+num_boxes = lib.num_boxes
+num_boxes.argtypes = [c_void_p]
+num_boxes.restype = c_int
+
+make_probs = lib.make_probs
+make_probs.argtypes = [c_void_p]
+make_probs.restype = POINTER(POINTER(c_float))
+
+detect = lib.network_predict_p
+detect.argtypes = [c_void_p, IMAGE, c_float, c_float, c_float, POINTER(BOX), POINTER(POINTER(c_float))]
+
 reset_rnn = lib.reset_rnn
 reset_rnn.argtypes = [c_void_p]
 
@@ -43,6 +67,9 @@ load_net = lib.load_network_p
 load_net.argtypes = [c_char_p, c_char_p, c_int]
 load_net.restype = c_void_p
 
+free_image = lib.free_image
+free_image.argtypes = [IMAGE]
+
 letterbox_image = lib.letterbox_image
 letterbox_image.argtypes = [IMAGE, c_int, c_int]
 letterbox_image.restype = IMAGE
@@ -59,6 +86,9 @@ predict_image = lib.network_predict_image
 predict_image.argtypes = [c_void_p, IMAGE]
 predict_image.restype = POINTER(c_float)
 
+network_detect = lib.network_detect
+network_detect.argtypes = [c_void_p, IMAGE, c_float, c_float, c_float, POINTER(BOX), POINTER(POINTER(c_float))]
+
 def classify(net, meta, im):
     out = predict_image(net, im)
     res = []
@@ -67,20 +97,31 @@ def classify(net, meta, im):
     res = sorted(res, key=lambda x: -x[1])
     return res
 
-def detect(net, meta, im):
-    out = predict_image(net, im)
+def detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45):
+    im = load_image(image, 0, 0)
+    boxes = make_boxes(net)
+    probs = make_probs(net)
+    num =   num_boxes(net)
+    network_detect(net, im, thresh, hier_thresh, nms, boxes, probs)
     res = []
-    for i in range(meta.classes):
-        res.append((meta.names[i], out[i]))
+    for j in range(num):
+        for i in range(meta.classes):
+            if probs[j][i] > 0:
+                res.append((meta.names[i], probs[j][i], (boxes[j].x, boxes[j].y, boxes[j].w, boxes[j].h)))
     res = sorted(res, key=lambda x: -x[1])
+    free_image(im)
+    free_ptrs(cast(probs, POINTER(c_void_p)), num)
     return res
     
-
 if __name__ == "__main__":
-    net = load_net("cfg/densenet201.cfg", "/home/pjreddie/trained/densenet201.weights", 0)
-    im = load_image("data/wolf.jpg", 0, 0)
-    meta = load_meta("cfg/imagenet1k.data")
-    r = classify(net, meta, im)
-    print r[:10]
+    #net = load_net("cfg/densenet201.cfg", "/home/pjreddie/trained/densenet201.weights", 0)
+    #im = load_image("data/wolf.jpg", 0, 0)
+    #meta = load_meta("cfg/imagenet1k.data")
+    #r = classify(net, meta, im)
+    #print r[:10]
+    net = load_net("cfg/tiny-yolo.cfg", "tiny-yolo.backup", 0)
+    meta = load_meta("cfg/coco.data")
+    r = detect(net, meta, "data/dog.jpg")
+    print r
     
 
diff --git a/src/network.c b/src/network.c
index 38d5229e..89e18238 100644
--- a/src/network.c
+++ b/src/network.c
@@ -494,6 +494,38 @@ float *network_predict(network net, float *input)
     return net.output;
 }
 
+int num_boxes(network *net)
+{
+    layer l = net->layers[net->n-1];
+    return l.w*l.h*l.n;
+}
+
+box *make_boxes(network *net)
+{
+    layer l = net->layers[net->n-1];
+    box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
+    return boxes;
+}
+
+float **make_probs(network *net)
+{
+    int j;
+    layer l = net->layers[net->n-1];
+    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(l.classes + 1, sizeof(float *));
+    return probs;
+}
+
+void network_detect(network *net, image im, float thresh, float hier_thresh, float nms, box *boxes, float **probs)
+{
+    network_predict_image(net, im);
+    layer l = net->layers[net->n-1];
+    if(l.type == REGION){
+        get_region_boxes(l, im.w, im.h, net->w, net->h, thresh, probs, boxes, 0, 0, 0, hier_thresh, 0);
+        if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms);
+    }
+}
+
 float *network_predict_p(network *net, float *input)
 {
     return network_predict(*net, input);