Add video

README.md

@@ -8,11 +8,37 @@
 
 3. [SSD](https://github.com/eric612/MobileNet-SSD-windows)
 
-### YoloV2 Model download
 
-download [here](https://drive.google.com/open?id=1pfGqD00STsauvBAnj6UyzNlgSJugm89q)
 
-### YoloV2 Result 
+### Customize YOLOv2 
+
+1. Better performance on small vehicle detection , but will add false object more
+2. light weight (30M , 27% size of full yolov2)
+3. 1.5x faster of full yolov2 (CPU forward)
+4. Only has conv,max pooling and region loss layer
+
+#### Result
+
+[![1](https://img.youtube.com/vi/9pS3Ov_b-Qg/0.jpg)](https://www.youtube.com/watch?v=9pS3Ov_b-Qg)
+
+[![1](https://img.youtube.com/vi/EU51rO3M6yo/0.jpg)](https://www.youtube.com/watch?v=EU51rO3M6yo)
+
+#### Training
+
+weights download [here](https://drive.google.com/open?id=1Ul8yRlvzcr8nsn5yfm9G_pdxqHVYsryY)
+
+train command
+```
+darknet detector train data/voc.data yolo-voc-custom.cfg car.conv.14
+```
+
+### Original YOLOv2 
+
+#### Model download
+
+weights download [here](https://drive.google.com/open?id=1pfGqD00STsauvBAnj6UyzNlgSJugm89q)
+
+#### Result
 
 [![1](https://img.youtube.com/vi/kuKnOTDIbq4/0.jpg)](https://www.youtube.com/watch?v=kuKnOTDIbq4)
 
@@ -32,6 +58,16 @@ download [here](https://drive.google.com/open?id=1pfGqD00STsauvBAnj6UyzNlgSJugm8
 
 ### FasterRCNN Result 
 
+####VGG19
+
+[![IMAGE ALT TEXT HERE](https://img.youtube.com/vi/NhID_pNwgac/0.jpg)](https://www.youtube.com/watch?v=NhID_pNwgac)
+
+[![IMAGE ALT TEXT HERE](https://img.youtube.com/vi/AjnaTelt0KM/0.jpg)](https://www.youtube.com/watch?v=AjnaTelt0KM)
+
+[![IMAGE ALT TEXT HERE](https://img.youtube.com/vi/vxk77dicGAQ/0.jpg)](https://www.youtube.com/watch?v=vxk77dicGAQ)
+
+####VGG16
+
 [![IMAGE ALT TEXT HERE](https://img.youtube.com/vi/xjIB9t1tLOg/0.jpg)](https://www.youtube.com/watch?v=xjIB9t1tLOg)
 
 ### SSD Model

YOLO/Customize Model/yolo-voc-custom.cfg

@@ -0,0 +1,163 @@
+[net]
+# Testing
+batch=16
+subdivisions=4
+# Training
+# batch=64
+# subdivisions=8
+height=416
+width=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.0001
+max_batches = 45000
+policy=steps
+steps=100,25000,35000
+scales=10,.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+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
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+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
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+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
+
+
+#######
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=50
+activation=linear
+
+[region]
+anchors = 1.08,1.19,  3.42,4.41,  6.63,11.38,  9.42,5.11,  16.62,10.52
+bias_match=1
+classes=5
+coords=4
+num=5
+softmax=1
+jitter=.2
+rescore=1
+
+object_scale=5
+noobject_scale=1
+class_scale=1
+coord_scale=1
+
+absolute=1
+thresh = .6
+random=0