added face recognition with live stream through an IP camera in to the Attendance View.

AttendanceApp/camera.py

+from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
+from tensorflow.keras.preprocessing.image import img_to_array
+from tensorflow.keras.models import load_model
+from imutils.video import VideoStream
+import imutils
+import cv2,os,urllib.request
+import numpy as np
+from django.conf import settings
+face_detection_videocam = cv2.CascadeClassifier(os.path.join(
+			settings.BASE_DIR,'opencv_haarcascade_data/haarcascade_frontalface_default.xml'))
+face_detection_webcam = cv2.CascadeClassifier(os.path.join(
+			settings.BASE_DIR,'opencv_haarcascade_data/haarcascade_frontalface_default.xml'))
+# load our serialized face detector model from disk
+prototxtPath = os.path.sep.join([settings.BASE_DIR, "face_detector/deploy.prototxt"])
+weightsPath = os.path.sep.join([settings.BASE_DIR,"face_detector/res10_300x300_ssd_iter_140000.caffemodel"])
+faceNet = cv2.dnn.readNet(prototxtPath, weightsPath)
+maskNet = load_model(os.path.join(settings.BASE_DIR,'face_detector/mask_detector.model'))
+
+
+# class VideoCamera(object):
+# 	def __init__(self):
+# 		self.video = cv2.VideoCapture(0)
+#
+# 	def __del__(self):
+# 		self.video.release()
+#
+# 	def get_frame(self):
+# 		success, image = self.video.read()
+# 		# We are using Motion JPEG, but OpenCV defaults to capture raw images,
+# 		# so we must encode it into JPEG in order to correctly display the
+# 		# video stream.
+#
+# 		gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+# 		faces_detected = face_detection_videocam.detectMultiScale(gray, scaleFactor=1.3, minNeighbors=5)
+# 		for (x, y, w, h) in faces_detected:
+# 			cv2.rectangle(image, pt1=(x, y), pt2=(x + w, y + h), color=(255, 0, 0), thickness=2)
+# 		frame_flip = cv2.flip(image,1)
+# 		ret, jpeg = cv2.imencode('.jpg', frame_flip)
+# 		return jpeg.tobytes()
+
+
+class IPWebCam(object):
+	def __init__(self):
+		self.url = "http://192.168.8.100:8080/shot.jpg"
+
+	def __del__(self):
+		cv2.destroyAllWindows()
+
+	def get_frame(self):
+		imgResp = urllib.request.urlopen(self.url)
+		imgNp = np.array(bytearray(imgResp.read()),dtype=np.uint8)
+		img= cv2.imdecode(imgNp,-1)
+		# We are using Motion JPEG, but OpenCV defaults to capture raw images,
+		# so we must encode it into JPEG in order to correctly display the
+		# video stream
+		gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+		faces_detected = face_detection_webcam.detectMultiScale(gray, scaleFactor=1.3, minNeighbors=5)
+		for (x, y, w, h) in faces_detected:
+			cv2.rectangle(img, pt1=(x, y), pt2=(x + w, y + h), color=(255, 0, 0), thickness=2)
+		resize = cv2.resize(img, (640, 480), interpolation = cv2.INTER_LINEAR) 
+		frame_flip = cv2.flip(resize,1)
+		ret, jpeg = cv2.imencode('.jpg', frame_flip)
+		return jpeg.tobytes()
+
+
+class MaskDetect(object):
+	def __init__(self):
+		self.vs = VideoStream(src=0).start()
+
+	def __del__(self):
+		cv2.destroyAllWindows()
+
+	def detect_and_predict_mask(self,frame, faceNet, maskNet):
+		# grab the dimensions of the frame and then construct a blob
+		# from it
+		(h, w) = frame.shape[:2]
+		blob = cv2.dnn.blobFromImage(frame, 1.0, (300, 300),
+									 (104.0, 177.0, 123.0))
+
+		# pass the blob through the network and obtain the face detections
+		faceNet.setInput(blob)
+		detections = faceNet.forward()
+
+		# initialize our list of faces, their corresponding locations,
+		# and the list of predictions from our face mask network
+		faces = []
+		locs = []
+		preds = []
+
+		# loop over the detections
+		for i in range(0, detections.shape[2]):
+			# extract the confidence (i.e., probability) associated with
+			# the detection
+			confidence = detections[0, 0, i, 2]
+
+			# filter out weak detections by ensuring the confidence is
+			# greater than the minimum confidence
+			if confidence > 0.5:
+				# compute the (x, y)-coordinates of the bounding box for
+				# the object
+				box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
+				(startX, startY, endX, endY) = box.astype("int")
+
+				# ensure the bounding boxes fall within the dimensions of
+				# the frame
+				(startX, startY) = (max(0, startX), max(0, startY))
+				(endX, endY) = (min(w - 1, endX), min(h - 1, endY))
+
+				# extract the face ROI, convert it from BGR to RGB channel
+				# ordering, resize it to 224x224, and preprocess it
+				face = frame[startY:endY, startX:endX]
+				face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
+				face = cv2.resize(face, (224, 224))
+				face = img_to_array(face)
+				face = preprocess_input(face)
+
+				# add the face and bounding boxes to their respective
+				# lists
+				faces.append(face)
+				locs.append((startX, startY, endX, endY))
+
+		# only make a predictions if at least one face was detected
+		if len(faces) > 0:
+			# for faster inference we'll make batch predictions on *all*
+			# faces at the same time rather than one-by-one predictions
+			# in the above `for` loop
+			faces = np.array(faces, dtype="float32")
+			preds = maskNet.predict(faces, batch_size=32)
+
+		# return a 2-tuple of the face locations and their corresponding
+		# locations
+		return (locs, preds)
+
+	def get_frame(self):
+		frame = self.vs.read()
+		frame = imutils.resize(frame, width=650)
+		frame = cv2.flip(frame, 1)
+		# detect faces in the frame and determine if they are wearing a
+		# face mask or not
+		(locs, preds) = self.detect_and_predict_mask(frame, faceNet, maskNet)
+
+		# loop over the detected face locations and their corresponding
+		# locations
+		for (box, pred) in zip(locs, preds):
+			# unpack the bounding box and predictions
+			(startX, startY, endX, endY) = box
+			(mask, withoutMask) = pred
+
+			# determine the class label and color we'll use to draw
+			# the bounding box and text
+			label = "Mask" if mask > withoutMask else "No Mask"
+			color = (0, 255, 0) if label == "Mask" else (0, 0, 255)
+
+			# include the probability in the label
+			label = "{}: {:.2f}%".format(label, max(mask, withoutMask) * 100)
+
+			# display the label and bounding box rectangle on the output
+			# frame
+			cv2.putText(frame, label, (startX, startY - 10),
+						cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
+			cv2.rectangle(frame, (startX, startY), (endX, endY), color, 2)
+		ret, jpeg = cv2.imencode('.jpg', frame)
+		return jpeg.tobytes()
+		
+# class LiveWebCam(object):
+# 	def __init__(self):
+# 		self.url = cv2.VideoCapture("rtsp://admin:Mumbai@123@203.192.228.175:554/")
+#
+# 	def __del__(self):
+# 		cv2.destroyAllWindows()
+#
+# 	def get_frame(self):
+# 		success,imgNp = self.url.read()
+# 		resize = cv2.resize(imgNp, (640, 480), interpolation = cv2.INTER_LINEAR)
+# 		ret, jpeg = cv2.imencode('.jpg', resize)
+# 		return jpeg.tobytes()

AttendanceApp/templates/AttendanceApp/Initiate_Lecture.html

@@ -31,18 +31,18 @@
 </script>
 
 
-<script type="text/javascript">
-
-    $(document).ready(function() {
-        $('#initiate_btn').click(function() {
-
-            fetch('http://127.0.0.1:8000/attendance/process-initiate-lecture')
-            .then((res) => res.json())
-            .then((out) => alert(out.response))
-            .catch((err) => alert('error: ' + err))
-        });
-    })
-
+<script>
+function toggleLectureLive() {
+  var x = document.getElementById("liveStreamLecture");
+  var y = document.getElementById("liveStreamLectureStartButton");
+  if (x.style.display === "none") {
+    x.style.display = "block";
+    y.style.display = "block";
+  } else {
+    x.style.display = "none";
+    y.style.display = "none";
+  }
+}
 </script>
 
 {% endblock %}
@@ -55,11 +55,19 @@
             <div class="text-center">
                 <div class="card">
                     <div class="card-header">
-                        <h4 class="card-title">Starting the lecture....</h4>
+                        <h4 class="card-title">Lecture Live</h4>
                     </div>
 
                     <div class="card-body">
-                        <button type="button" class="btn btn-success" id="initiate_btn">Initiate Lecture</button>
+                        <button type="button" class="btn btn-success" id="initiate_btn" onclick="toggleLectureLive()">Show Live Stream</button>
+                    </div>
+                    <div style="vertical-align: middle; border-style: none; background-color: #055270; height: 500px; width: 100%">
+                        <div class="row justify-content-center">
+                            <img id="liveStreamLecture" style="display: none; height: inherit; margin-bottom: -25px;" src="{% url 'webcam_feed' %}">
+                        </div>
+                        <div class="row justify-content-center">
+                            <button style="display: none; width: 70px; height: 70px;" id="liveStreamLectureStartButton" class="btn btn-warning btn-circle"><i class="fas fa-video"></i></button>
+                        </div>
                     </div>
                 </div>
             </div>

AttendanceApp/urls.py

@@ -17,7 +17,7 @@ urlpatterns = [
     path('student/', StudentAPIView.as_view()),
     path('student/<str:pk>', StudentDetails.as_view()),
     url(r'^upload/$', FileView.as_view(), name='file-upload'),
-
+    path('webcam_feed', views.webcam_feed, name='webcam_feed'),
     # this url will initiate the lecture
     url(r'^process-initiate-lecture/$', InitiateLecture.as_view())
 ]

AttendanceApp/views.py

 from django.shortcuts import render
+from django.http.response import StreamingHttpResponse
+from AttendanceApp.camera import IPWebCam
 
 
 def initiate_lecture(request):
 
-    return render(request, "AttendanceApp/Initiate_lecture.html")
\ No newline at end of file
+    return render(request, "AttendanceApp/Initiate_lecture.html")
+
+def gen(camera):
+	while True:
+		frame = camera.get_frame()
+		yield (b'--frame\r\n'
+				b'Content-Type: image/jpeg\r\n\r\n' + frame + b'\r\n\r\n')
+
+def webcam_feed(request):
+	return StreamingHttpResponse(gen(IPWebCam()),
+					content_type='multipart/x-mixed-replace; boundary=frame')
\ No newline at end of file

face_detector/deploy.prototxt

+input: "data"
+input_shape {
+  dim: 1
+  dim: 3
+  dim: 300
+  dim: 300
+}
+
+layer {
+  name: "data_bn"
+  type: "BatchNorm"
+  bottom: "data"
+  top: "data_bn"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "data_scale"
+  type: "Scale"
+  bottom: "data_bn"
+  top: "data_bn"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "conv1_h"
+  type: "Convolution"
+  bottom: "data_bn"
+  top: "conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 32
+    pad: 3
+    kernel_size: 7
+    stride: 2
+    weight_filler {
+      type: "msra"
+      variance_norm: FAN_OUT
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv1_bn_h"
+  type: "BatchNorm"
+  bottom: "conv1_h"
+  top: "conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "conv1_scale_h"
+  type: "Scale"
+  bottom: "conv1_h"
+  top: "conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "conv1_relu"
+  type: "ReLU"
+  bottom: "conv1_h"
+  top: "conv1_h"
+}
+layer {
+  name: "conv1_pool"
+  type: "Pooling"
+  bottom: "conv1_h"
+  top: "conv1_pool"
+  pooling_param {
+    kernel_size: 3
+    stride: 2
+  }
+}
+layer {
+  name: "layer_64_1_conv1_h"
+  type: "Convolution"
+  bottom: "conv1_pool"
+  top: "layer_64_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 32
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_64_1_bn2_h"
+  type: "BatchNorm"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_64_1_scale2_h"
+  type: "Scale"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_64_1_relu2"
+  type: "ReLU"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv1_h"
+}
+layer {
+  name: "layer_64_1_conv2_h"
+  type: "Convolution"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv2_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 32
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_64_1_sum"
+  type: "Eltwise"
+  bottom: "layer_64_1_conv2_h"
+  bottom: "conv1_pool"
+  top: "layer_64_1_sum"
+}
+layer {
+  name: "layer_128_1_bn1_h"
+  type: "BatchNorm"
+  bottom: "layer_64_1_sum"
+  top: "layer_128_1_bn1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_128_1_scale1_h"
+  type: "Scale"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_bn1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_128_1_relu1"
+  type: "ReLU"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_bn1_h"
+}
+layer {
+  name: "layer_128_1_conv1_h"
+  type: "Convolution"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_128_1_bn2"
+  type: "BatchNorm"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_128_1_scale2"
+  type: "Scale"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_128_1_relu2"
+  type: "ReLU"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv1_h"
+}
+layer {
+  name: "layer_128_1_conv2"
+  type: "Convolution"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_128_1_conv_expand_h"
+  type: "Convolution"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_conv_expand_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 0
+    kernel_size: 1
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_128_1_sum"
+  type: "Eltwise"
+  bottom: "layer_128_1_conv2"
+  bottom: "layer_128_1_conv_expand_h"
+  top: "layer_128_1_sum"
+}
+layer {
+  name: "layer_256_1_bn1"
+  type: "BatchNorm"
+  bottom: "layer_128_1_sum"
+  top: "layer_256_1_bn1"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_256_1_scale1"
+  type: "Scale"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_bn1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_256_1_relu1"
+  type: "ReLU"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_bn1"
+}
+layer {
+  name: "layer_256_1_conv1"
+  type: "Convolution"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_conv1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_256_1_bn2"
+  type: "BatchNorm"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv1"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_256_1_scale2"
+  type: "Scale"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_256_1_relu2"
+  type: "ReLU"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv1"
+}
+layer {
+  name: "layer_256_1_conv2"
+  type: "Convolution"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_256_1_conv_expand"
+  type: "Convolution"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_conv_expand"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 0
+    kernel_size: 1
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_256_1_sum"
+  type: "Eltwise"
+  bottom: "layer_256_1_conv2"
+  bottom: "layer_256_1_conv_expand"
+  top: "layer_256_1_sum"
+}
+layer {
+  name: "layer_512_1_bn1"
+  type: "BatchNorm"
+  bottom: "layer_256_1_sum"
+  top: "layer_512_1_bn1"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_512_1_scale1"
+  type: "Scale"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_bn1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_512_1_relu1"
+  type: "ReLU"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_bn1"
+}
+layer {
+  name: "layer_512_1_conv1_h"
+  type: "Convolution"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1 # 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_512_1_bn2_h"
+  type: "BatchNorm"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_512_1_scale2_h"
+  type: "Scale"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_512_1_relu2"
+  type: "ReLU"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv1_h"
+}
+layer {
+  name: "layer_512_1_conv2_h"
+  type: "Convolution"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv2_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 2 # 1
+    kernel_size: 3
+    stride: 1
+    dilation: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_512_1_conv_expand_h"
+  type: "Convolution"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_conv_expand_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 0
+    kernel_size: 1
+    stride: 1 # 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_512_1_sum"
+  type: "Eltwise"
+  bottom: "layer_512_1_conv2_h"
+  bottom: "layer_512_1_conv_expand_h"
+  top: "layer_512_1_sum"
+}
+layer {
+  name: "last_bn_h"
+  type: "BatchNorm"
+  bottom: "layer_512_1_sum"
+  top: "layer_512_1_sum"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "last_scale_h"
+  type: "Scale"
+  bottom: "layer_512_1_sum"
+  top: "layer_512_1_sum"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "last_relu"
+  type: "ReLU"
+  bottom: "layer_512_1_sum"
+  top: "fc7"
+}
+
+layer {
+  name: "conv6_1_h"
+  type: "Convolution"
+  bottom: "fc7"
+  top: "conv6_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_1_relu"
+  type: "ReLU"
+  bottom: "conv6_1_h"
+  top: "conv6_1_h"
+}
+layer {
+  name: "conv6_2_h"
+  type: "Convolution"
+  bottom: "conv6_1_h"
+  top: "conv6_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_2_relu"
+  type: "ReLU"
+  bottom: "conv6_2_h"
+  top: "conv6_2_h"
+}
+layer {
+  name: "conv7_1_h"
+  type: "Convolution"
+  bottom: "conv6_2_h"
+  top: "conv7_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 64
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_1_relu"
+  type: "ReLU"
+  bottom: "conv7_1_h"
+  top: "conv7_1_h"
+}
+layer {
+  name: "conv7_2_h"
+  type: "Convolution"
+  bottom: "conv7_1_h"
+  top: "conv7_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_2_relu"
+  type: "ReLU"
+  bottom: "conv7_2_h"
+  top: "conv7_2_h"
+}
+layer {
+  name: "conv8_1_h"
+  type: "Convolution"
+  bottom: "conv7_2_h"
+  top: "conv8_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 64
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_1_relu"
+  type: "ReLU"
+  bottom: "conv8_1_h"
+  top: "conv8_1_h"
+}
+layer {
+  name: "conv8_2_h"
+  type: "Convolution"
+  bottom: "conv8_1_h"
+  top: "conv8_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_2_relu"
+  type: "ReLU"
+  bottom: "conv8_2_h"
+  top: "conv8_2_h"
+}
+layer {
+  name: "conv9_1_h"
+  type: "Convolution"
+  bottom: "conv8_2_h"
+  top: "conv9_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 64
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_1_relu"
+  type: "ReLU"
+  bottom: "conv9_1_h"
+  top: "conv9_1_h"
+}
+layer {
+  name: "conv9_2_h"
+  type: "Convolution"
+  bottom: "conv9_1_h"
+  top: "conv9_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_2_relu"
+  type: "ReLU"
+  bottom: "conv9_2_h"
+  top: "conv9_2_h"
+}
+layer {
+  name: "conv4_3_norm"
+  type: "Normalize"
+  bottom: "layer_256_1_bn1"
+  top: "conv4_3_norm"
+  norm_param {
+    across_spatial: false
+    scale_filler {
+      type: "constant"
+      value: 20
+    }
+    channel_shared: false
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_loc"
+  type: "Convolution"
+  bottom: "conv4_3_norm"
+  top: "conv4_3_norm_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 16
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv4_3_norm_mbox_loc"
+  top: "conv4_3_norm_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv4_3_norm_mbox_loc_perm"
+  top: "conv4_3_norm_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_conf"
+  type: "Convolution"
+  bottom: "conv4_3_norm"
+  top: "conv4_3_norm_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 8 # 84
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv4_3_norm_mbox_conf"
+  top: "conv4_3_norm_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv4_3_norm_mbox_conf_perm"
+  top: "conv4_3_norm_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv4_3_norm"
+  bottom: "data"
+  top: "conv4_3_norm_mbox_priorbox"
+  prior_box_param {
+    min_size: 30.0
+    max_size: 60.0
+    aspect_ratio: 2
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 8
+    offset: 0.5
+  }
+}
+layer {
+  name: "fc7_mbox_loc"
+  type: "Convolution"
+  bottom: "fc7"
+  top: "fc7_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 24
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "fc7_mbox_loc_perm"
+  type: "Permute"
+  bottom: "fc7_mbox_loc"
+  top: "fc7_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "fc7_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "fc7_mbox_loc_perm"
+  top: "fc7_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "fc7_mbox_conf"
+  type: "Convolution"
+  bottom: "fc7"
+  top: "fc7_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 12 # 126
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "fc7_mbox_conf_perm"
+  type: "Permute"
+  bottom: "fc7_mbox_conf"
+  top: "fc7_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "fc7_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "fc7_mbox_conf_perm"
+  top: "fc7_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "fc7_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "fc7"
+  bottom: "data"
+  top: "fc7_mbox_priorbox"
+  prior_box_param {
+    min_size: 60.0
+    max_size: 111.0
+    aspect_ratio: 2
+    aspect_ratio: 3
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 16
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv6_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv6_2_h"
+  top: "conv6_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 24
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv6_2_mbox_loc"
+  top: "conv6_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv6_2_mbox_loc_perm"
+  top: "conv6_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv6_2_h"
+  top: "conv6_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 12 # 126
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv6_2_mbox_conf"
+  top: "conv6_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv6_2_mbox_conf_perm"
+  top: "conv6_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv6_2_h"
+  bottom: "data"
+  top: "conv6_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 111.0
+    max_size: 162.0
+    aspect_ratio: 2
+    aspect_ratio: 3
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 32
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv7_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv7_2_h"
+  top: "conv7_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 24
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv7_2_mbox_loc"
+  top: "conv7_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv7_2_mbox_loc_perm"
+  top: "conv7_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv7_2_h"
+  top: "conv7_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 12 # 126
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv7_2_mbox_conf"
+  top: "conv7_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv7_2_mbox_conf_perm"
+  top: "conv7_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv7_2_h"
+  bottom: "data"
+  top: "conv7_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 162.0
+    max_size: 213.0
+    aspect_ratio: 2
+    aspect_ratio: 3
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 64
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv8_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv8_2_h"
+  top: "conv8_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 16
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv8_2_mbox_loc"
+  top: "conv8_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv8_2_mbox_loc_perm"
+  top: "conv8_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv8_2_h"
+  top: "conv8_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 8 # 84
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv8_2_mbox_conf"
+  top: "conv8_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv8_2_mbox_conf_perm"
+  top: "conv8_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv8_2_h"
+  bottom: "data"
+  top: "conv8_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 213.0
+    max_size: 264.0
+    aspect_ratio: 2
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 100
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv9_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv9_2_h"
+  top: "conv9_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 16
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv9_2_mbox_loc"
+  top: "conv9_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv9_2_mbox_loc_perm"
+  top: "conv9_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv9_2_h"
+  top: "conv9_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 8 # 84
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv9_2_mbox_conf"
+  top: "conv9_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv9_2_mbox_conf_perm"
+  top: "conv9_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv9_2_h"
+  bottom: "data"
+  top: "conv9_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 264.0
+    max_size: 315.0
+    aspect_ratio: 2
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 300
+    offset: 0.5
+  }
+}
+layer {
+  name: "mbox_loc"
+  type: "Concat"
+  bottom: "conv4_3_norm_mbox_loc_flat"
+  bottom: "fc7_mbox_loc_flat"
+  bottom: "conv6_2_mbox_loc_flat"
+  bottom: "conv7_2_mbox_loc_flat"
+  bottom: "conv8_2_mbox_loc_flat"
+  bottom: "conv9_2_mbox_loc_flat"
+  top: "mbox_loc"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_conf"
+  type: "Concat"
+  bottom: "conv4_3_norm_mbox_conf_flat"
+  bottom: "fc7_mbox_conf_flat"
+  bottom: "conv6_2_mbox_conf_flat"
+  bottom: "conv7_2_mbox_conf_flat"
+  bottom: "conv8_2_mbox_conf_flat"
+  bottom: "conv9_2_mbox_conf_flat"
+  top: "mbox_conf"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_priorbox"
+  type: "Concat"
+  bottom: "conv4_3_norm_mbox_priorbox"
+  bottom: "fc7_mbox_priorbox"
+  bottom: "conv6_2_mbox_priorbox"
+  bottom: "conv7_2_mbox_priorbox"
+  bottom: "conv8_2_mbox_priorbox"
+  bottom: "conv9_2_mbox_priorbox"
+  top: "mbox_priorbox"
+  concat_param {
+    axis: 2
+  }
+}
+
+layer {
+  name: "mbox_conf_reshape"
+  type: "Reshape"
+  bottom: "mbox_conf"
+  top: "mbox_conf_reshape"
+  reshape_param {
+    shape {
+      dim: 0
+      dim: -1
+      dim: 2
+    }
+  }
+}
+layer {
+  name: "mbox_conf_softmax"
+  type: "Softmax"
+  bottom: "mbox_conf_reshape"
+  top: "mbox_conf_softmax"
+  softmax_param {
+    axis: 2
+  }
+}
+layer {
+  name: "mbox_conf_flatten"
+  type: "Flatten"
+  bottom: "mbox_conf_softmax"
+  top: "mbox_conf_flatten"
+  flatten_param {
+    axis: 1
+  }
+}
+
+layer {
+  name: "detection_out"
+  type: "DetectionOutput"
+  bottom: "mbox_loc"
+  bottom: "mbox_conf_flatten"
+  bottom: "mbox_priorbox"
+  top: "detection_out"
+  include {
+    phase: TEST
+  }
+  detection_output_param {
+    num_classes: 2
+    share_location: true
+    background_label_id: 0
+    nms_param {
+      nms_threshold: 0.45
+      top_k: 400
+    }
+    code_type: CENTER_SIZE
+    keep_top_k: 200
+    confidence_threshold: 0.01
+  }
+}