diff --git a/build/darknet/x64/cfg/Gaussian_yolov3_BDD.cfg b/build/darknet/x64/cfg/Gaussian_yolov3_BDD.cfg
new file mode 100644
index 00000000000..2ca7ec600e3
--- /dev/null
+++ b/build/darknet/x64/cfg/Gaussian_yolov3_BDD.cfg
@@ -0,0 +1,807 @@
+[net]
+# Testing
+#batch=1
+#subdivisions=1
+# Training
+batch=64
+subdivisions=16
+width=512
+height=512
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.0001
+burn_in=1000
+max_batches = 500200
+policy=steps
+steps=400000,450000
+scales=.1,.1
+max_epochs = 300
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+######################
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=57
+activation=linear
+
+
+[Gaussian_yolo]
+mask = 6,7,8
+anchors = 7,10, 14,24, 27,43, 32,97, 57,64, 92,109, 73,175, 141,178, 144,291
+classes=10
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+iou_thresh=0.213
+uc_normalizer=1.0
+cls_normalizer=1.0
+iou_normalizer=0.5
+iou_loss=giou
+scale_x_y=1.0
+random=1
+
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 61
+
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=57
+activation=linear
+
+
+[Gaussian_yolo]
+mask = 3,4,5
+anchors = 7,10, 14,24, 27,43, 32,97, 57,64, 92,109, 73,175, 141,178, 144,291
+classes=10
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+iou_thresh=0.213
+uc_normalizer=1.0
+cls_normalizer=1.0
+iou_normalizer=0.5
+iou_loss=giou
+scale_x_y=1.0
+random=1
+
+
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 36
+
+
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=57
+activation=linear
+
+
+[Gaussian_yolo]
+mask = 0,1,2
+anchors = 7,10, 14,24, 27,43, 32,97, 57,64, 92,109, 73,175, 141,178, 144,291
+classes=10
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+iou_thresh=0.213
+uc_normalizer=1.0
+cls_normalizer=1.0
+iou_normalizer=0.5
+iou_loss=giou
+scale_x_y=1.0
+random=1
diff --git a/cfg/Gaussian_yolov3_BDD.cfg b/cfg/Gaussian_yolov3_BDD.cfg
new file mode 100644
index 00000000000..2ca7ec600e3
--- /dev/null
+++ b/cfg/Gaussian_yolov3_BDD.cfg
@@ -0,0 +1,807 @@
+[net]
+# Testing
+#batch=1
+#subdivisions=1
+# Training
+batch=64
+subdivisions=16
+width=512
+height=512
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.0001
+burn_in=1000
+max_batches = 500200
+policy=steps
+steps=400000,450000
+scales=.1,.1
+max_epochs = 300
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+######################
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=57
+activation=linear
+
+
+[Gaussian_yolo]
+mask = 6,7,8
+anchors = 7,10, 14,24, 27,43, 32,97, 57,64, 92,109, 73,175, 141,178, 144,291
+classes=10
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+iou_thresh=0.213
+uc_normalizer=1.0
+cls_normalizer=1.0
+iou_normalizer=0.5
+iou_loss=giou
+scale_x_y=1.0
+random=1
+
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 61
+
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=57
+activation=linear
+
+
+[Gaussian_yolo]
+mask = 3,4,5
+anchors = 7,10, 14,24, 27,43, 32,97, 57,64, 92,109, 73,175, 141,178, 144,291
+classes=10
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+iou_thresh=0.213
+uc_normalizer=1.0
+cls_normalizer=1.0
+iou_normalizer=0.5
+iou_loss=giou
+scale_x_y=1.0
+random=1
+
+
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 36
+
+
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=57
+activation=linear
+
+
+[Gaussian_yolo]
+mask = 0,1,2
+anchors = 7,10, 14,24, 27,43, 32,97, 57,64, 92,109, 73,175, 141,178, 144,291
+classes=10
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+iou_thresh=0.213
+uc_normalizer=1.0
+cls_normalizer=1.0
+iou_normalizer=0.5
+iou_loss=giou
+scale_x_y=1.0
+random=1
diff --git a/include/darknet.h b/include/darknet.h
index 2bd70d1cde3..7a906780c61 100644
--- a/include/darknet.h
+++ b/include/darknet.h
@@ -330,6 +330,7 @@ struct layer {
     float *weight_updates;
 
     float scale_x_y;
+    float uc_normalizer;
     float iou_normalizer;
     float cls_normalizer;
     IOU_LOSS iou_loss;
diff --git a/src/gaussian_yolo_layer.c b/src/gaussian_yolo_layer.c
index 7200fecd61b..16971437872 100644
--- a/src/gaussian_yolo_layer.c
+++ b/src/gaussian_yolo_layer.c
@@ -256,6 +256,26 @@ float delta_gaussian_yolo_box(box truth, float *x, float *biases, int n, int ind
     return iou;
 }
 
+void averages_gaussian_yolo_deltas(int class_index, int box_index, int stride, int classes, float *delta)
+{
+
+    int classes_in_one_box = 0;
+    int c;
+    for (c = 0; c < classes; ++c) {
+        if (delta[class_index + stride*c] > 0) classes_in_one_box++;
+    }
+
+    if (classes_in_one_box > 0) {
+        delta[box_index + 0 * stride] /= classes_in_one_box;
+        delta[box_index + 1 * stride] /= classes_in_one_box;
+        delta[box_index + 2 * stride] /= classes_in_one_box;
+        delta[box_index + 3 * stride] /= classes_in_one_box;
+        delta[box_index + 4 * stride] /= classes_in_one_box;
+        delta[box_index + 5 * stride] /= classes_in_one_box;
+        delta[box_index + 6 * stride] /= classes_in_one_box;
+        delta[box_index + 7 * stride] /= classes_in_one_box;
+    }
+}
 
 void delta_gaussian_yolo_class(float *output, float *delta, int index, int class_id, int classes, int stride, float *avg_cat)
 {
@@ -469,25 +489,73 @@ void forward_gaussian_yolo_layer(const layer l, network_state state)
                     int class_index = entry_gaussian_index(l, b, n*l.w*l.h + j*l.w + i, 9);
                     const int stride = l.w*l.h;
 
-                    int classes_in_one_box = 0;
-                    for (n = 0; n < l.classes; ++n) {
-                        if (l.delta[class_index + stride*n] > 0) classes_in_one_box++;
-                    }
+                    averages_gaussian_yolo_deltas(class_index, box_index, stride, l.classes, l.delta);
+                }
+            }
+        }
+    }
+
+
+    // calculate: Classification-loss, IoU-loss and Uncertainty-loss
+    const int stride = l.w*l.h;
+    float* classification_lost = (float *)calloc(l.batch * l.outputs, sizeof(float));
+    memcpy(classification_lost, l.delta, l.batch * l.outputs * sizeof(float));
+
 
-                    l.delta[box_index + 0 * stride] /= classes_in_one_box;
-                    l.delta[box_index + 1 * stride] /= classes_in_one_box;
-                    l.delta[box_index + 2 * stride] /= classes_in_one_box;
-                    l.delta[box_index + 3 * stride] /= classes_in_one_box;
-                    l.delta[box_index + 4 * stride] /= classes_in_one_box;
-                    l.delta[box_index + 5 * stride] /= classes_in_one_box;
-                    l.delta[box_index + 6 * stride] /= classes_in_one_box;
-                    l.delta[box_index + 7 * stride] /= classes_in_one_box;
+    for (b = 0; b < l.batch; ++b) {
+        for (j = 0; j < l.h; ++j) {
+            for (i = 0; i < l.w; ++i) {
+                for (n = 0; n < l.n; ++n) {
+                    int box_index = entry_gaussian_index(l, b, n*l.w*l.h + j*l.w + i, 0);
+
+                    classification_lost[box_index + 0 * stride] = 0;
+                    classification_lost[box_index + 1 * stride] = 0;
+                    classification_lost[box_index + 2 * stride] = 0;
+                    classification_lost[box_index + 3 * stride] = 0;
+                    classification_lost[box_index + 4 * stride] = 0;
+                    classification_lost[box_index + 5 * stride] = 0;
+                    classification_lost[box_index + 6 * stride] = 0;
+                    classification_lost[box_index + 7 * stride] = 0;
                 }
             }
         }
     }
+    float class_loss = pow(mag_array(classification_lost, l.outputs * l.batch), 2);
+    free(classification_lost);
+
+
+    float* except_uncertainty_lost = (float *)calloc(l.batch * l.outputs, sizeof(float));
+    memcpy(except_uncertainty_lost, l.delta, l.batch * l.outputs * sizeof(float));
+    for (b = 0; b < l.batch; ++b) {
+        for (j = 0; j < l.h; ++j) {
+            for (i = 0; i < l.w; ++i) {
+                for (n = 0; n < l.n; ++n) {
+                    int box_index = entry_gaussian_index(l, b, n*l.w*l.h + j*l.w + i, 0);
+                    except_uncertainty_lost[box_index + 4 * stride] = 0;
+                    except_uncertainty_lost[box_index + 5 * stride] = 0;
+                    except_uncertainty_lost[box_index + 6 * stride] = 0;
+                    except_uncertainty_lost[box_index + 7 * stride] = 0;
+                }
+            }
+        }
+    }
+    float except_uc_loss = pow(mag_array(except_uncertainty_lost, l.outputs * l.batch), 2);
+    free(except_uncertainty_lost);
+
     *(l.cost) = pow(mag_array(l.delta, l.outputs * l.batch), 2);
-    printf("Region %d Avg IOU: %f, Class: %f, Obj: %f, No Obj: %f, .5R: %f, .75R: %f,  count: %d\n", state.index, avg_iou/count, avg_cat/class_count, avg_obj/count, avg_anyobj/(l.w*l.h*l.n*l.batch), recall/count, recall75/count, count);
+
+    float loss = pow(mag_array(l.delta, l.outputs * l.batch), 2);
+    float uc_loss = loss - except_uc_loss;
+    float iou_loss = except_uc_loss - class_loss;
+
+    loss /= l.batch;
+    class_loss /= l.batch;
+    uc_loss /= l.batch;
+    iou_loss /= l.batch;
+
+    printf("Region %d Avg IOU: %f, Class: %f, Obj: %f, No Obj: %f, .5R: %f, .75R: %f,  count: %d, loss = %.2f, class_loss = %.2f, iou_loss = %.2f, uc_loss = %.2f \n",
+        state.index, avg_iou/count, avg_cat/class_count, avg_obj/count, avg_anyobj/(l.w*l.h*l.n*l.batch), recall/count, recall75/count, count,
+        loss, class_loss, iou_loss, uc_loss);
 }
 
 void backward_gaussian_yolo_layer(const layer l, network_state state)
diff --git a/src/yolo_layer.c b/src/yolo_layer.c
index b663b73da74..34185937459 100644
--- a/src/yolo_layer.c
+++ b/src/yolo_layer.c
@@ -192,6 +192,23 @@ ious delta_yolo_box(box truth, float *x, float *biases, int n, int index, int i,
     return all_ious;
 }
 
+void averages_yolo_deltas(int class_index, int box_index, int stride, int classes, float *delta)
+{
+
+    int classes_in_one_box = 0;
+    int c;
+    for (c = 0; c < classes; ++c) {
+        if (delta[class_index + stride*c] > 0) classes_in_one_box++;
+    }
+
+    if (classes_in_one_box > 0) {
+        delta[box_index + 0 * stride] /= classes_in_one_box;
+        delta[box_index + 1 * stride] /= classes_in_one_box;
+        delta[box_index + 2 * stride] /= classes_in_one_box;
+        delta[box_index + 3 * stride] /= classes_in_one_box;
+    }
+}
+
 void delta_yolo_class(float *output, float *delta, int index, int class_id, int classes, int stride, float *avg_cat, int focal_loss)
 {
     int n;
@@ -436,19 +453,12 @@ void forward_yolo_layer(const layer l, network_state state)
                     int class_index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 4 + 1);
                     const int stride = l.w*l.h;
 
-                    int classes_in_one_box = 0;
-                    for (n = 0; n < l.classes; ++n) {
-                        if (l.delta[class_index + stride*n] > 0) classes_in_one_box++;
-                    }
-
-                    l.delta[box_index + 0 * stride] /= classes_in_one_box;
-                    l.delta[box_index + 1 * stride] /= classes_in_one_box;
-                    l.delta[box_index + 2 * stride] /= classes_in_one_box;
-                    l.delta[box_index + 3 * stride] /= classes_in_one_box;
+                    averages_yolo_deltas(class_index, box_index, stride, l.classes, l.delta);
                 }
             }
         }
     }
+
     //*(l.cost) = pow(mag_array(l.delta, l.outputs * l.batch), 2);
     //printf("Region %d Avg IOU: %f, Class: %f, Obj: %f, No Obj: %f, .5R: %f, .75R: %f,  count: %d\n", state.index, avg_iou / count, avg_cat / class_count, avg_obj / count, avg_anyobj / (l.w*l.h*l.n*l.batch), recall / count, recall75 / count, count);