2. 程式人生 > >Intel® Movidius™ Neural Compute SDK - video_objects

Intel® Movidius™ Neural Compute SDK - video_objects

阿新 • • 發佈：2018-11-07

Intel® Movidius™ Neural Compute SDK - video_objects

https://github.com/movidius/ncappzoo/tree/master/apps/video_objects

ncappzoo/apps/video_objects/

Introduction

This project uses SSD MobileNet to do object recognition and classification for a street camera. Rather than a camera, video files will be used to simulate a camera.

The provided Makefile does the following:

  1. Builds both caffe ssd mobilenet graph file from the caffe/SSD_MobileNet directory in the repository.
  2. Copies the built NCS graph file from the SSD_MobileNet directory to the project base directory
  3. Downloads some sample traffic video files.
  4. Runs the provided street_cam_ssd_mobilenet.py program which creates a GUI window that shows the video stream along with labels and boxes around the identified objects.

Prerequisites

This program requires:

  • 1 NCS device
  • NCSDK 1.11 or greater
  • opencv 3.3 with video for linux support

Note: The OpenCV version that installs with the current ncsdk (1.10.00) does not provide V4L support. To run this application you will need to replace the ncsdk version with a version built from source. To remove the old opencv and build and install a compatible version you can run the following command from the app’s base directory:

   make opencv

Note: All development and testing has been done on Ubuntu 16.04 on an x86-64 machine.

Makefile

Provided Makefile has various targets that help with the above mentioned tasks.

make help

Shows available targets.

make all

Builds and/or gathers all the required files needed to run the application except building and installing opencv (this must be done as a separate step with ‘make opencv’.)

make videos

Downloads example video files.

make opencv

Removes the version of OpenCV that was installed with the NCSDK and builds and installs a compatible version of OpenCV 3.3 for this app. This will take a while to finish. Once you have done this on your system you shouldn’t need to do it again.

make run_py

Runs the provided python program which shows the video stream along with the object boxes and classifications.

make clean

Removes all the temporary files that are created by the Makefile

[email protected]:~/ncs_work/ncappzoo/apps/video_objects$ make clean

making clean
rm -f graph
rm -f *.mp4
rm -f licenses.txt
[email protected]:~/ncs_work/ncappzoo/apps/video_objects$ 
[email protected]:~/ncs_work/ncappzoo/apps/video_objects$ make all

making prereqs

making videos
wget -c --no-cache -P . https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/licenses.txt; wget -c --no-cache -P . https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/bus_station_6094_960x540.mp4; wget -c --no-cache -P . https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/motorcycle_6098_shortened_960x540.mp4; wget -c --no-cache -P . https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/contrapicado_traffic_shortened_960x540.mp4; wget -c --no-cache -P . https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/police_car_6095_shortened_960x540.mp4; wget -c --no-cache -P . https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/scooters_5638_shortened_960x540.mp4;
--2018-11-01 09:50:57--  https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/licenses.txt
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.0.133, 151.101.64.133, 151.101.128.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.0.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 1353 (1.3K) [text/plain]
Saving to: ‘./licenses.txt’

licenses.txt              100%[====================================>]   1.32K  --.-KB/s    in 0s      

2018-11-01 09:50:57 (114 MB/s) - ‘./licenses.txt’ saved [1353/1353]

--2018-11-01 09:50:57--  https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/bus_station_6094_960x540.mp4
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.0.133, 151.101.64.133, 151.101.128.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.0.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 5692338 (5.4M) [application/octet-stream]
Saving to: ‘./bus_station_6094_960x540.mp4’

bus_station_6094_960x540. 100%[====================================>]   5.43M  2.58MB/s    in 2.1s    

2018-11-01 09:51:00 (2.58 MB/s) - ‘./bus_station_6094_960x540.mp4’ saved [5692338/5692338]

--2018-11-01 09:51:00--  https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/motorcycle_6098_shortened_960x540.mp4
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.192.133, 151.101.0.133, 151.101.64.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.192.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 4471322 (4.3M) [application/octet-stream]
Saving to: ‘./motorcycle_6098_shortened_960x540.mp4’

motorcycle_6098_shortened 100%[====================================>]   4.26M  1.67MB/s    in 2.6s    

2018-11-01 09:51:04 (1.67 MB/s) - ‘./motorcycle_6098_shortened_960x540.mp4’ saved [4471322/4471322]

--2018-11-01 09:51:04--  https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/contrapicado_traffic_shortened_960x540.mp4
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.128.133, 151.101.192.133, 151.101.0.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.128.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 10902636 (10M) [application/octet-stream]
Saving to: ‘./contrapicado_traffic_shortened_960x540.mp4’

contrapicado_traffic_shor 100%[====================================>]  10.40M  3.08MB/s    in 3.8s    

2018-11-01 09:51:09 (2.74 MB/s) - ‘./contrapicado_traffic_shortened_960x540.mp4’ saved [10902636/10902636]

--2018-11-01 09:51:09--  https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/police_car_6095_shortened_960x540.mp4
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.192.133, 151.101.0.133, 151.101.64.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.192.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 14325763 (14M) [application/octet-stream]
Saving to: ‘./police_car_6095_shortened_960x540.mp4’

police_car_6095_shortened_96 100%[============================================>]  13.66M  3.12MB/s    in 4.7s    

2018-11-01 09:51:14 (2.93 MB/s) - ‘./police_car_6095_shortened_960x540.mp4’ saved [14325763/14325763]

--2018-11-01 09:51:14--  https://raw.githubusercontent.com/nealvis/media/master/traffic_vid/scooters_5638_shortened_960x540.mp4
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.64.133, 151.101.128.133, 151.101.192.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.64.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 9621265 (9.2M) [application/octet-stream]
Saving to: ‘./scooters_5638_shortened_960x540.mp4’

scooters_5638_shortened_960x 100%[============================================>]   9.17M  1.18MB/s    in 8.1s    

2018-11-01 09:51:24 (1.13 MB/s) - ‘./scooters_5638_shortened_960x540.mp4’ saved [9621265/9621265]


making ssd_mobilenet
(cd ../../caffe/SSD_MobileNet; make compile; cd ../../apps/video_objects; cp ../../caffe/SSD_MobileNet/graph ./graph;) 
make[1]: Entering directory '/home/foreverstrong/ncs_work/ncappzoo/caffe/SSD_MobileNet'

making caffemodel

Attempting download of caffemodel file from this url: 
https://github.com/chuanqi305/MobileNet-SSD/blob/master/mobilenet_iter_73000.caffemodel

--2018-11-01 09:51:24--  https://raw.githubusercontent.com/chuanqi305/MobileNet-SSD/master/mobilenet_iter_73000.caffemodel
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.0.133, 151.101.64.133, 151.101.128.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.0.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 23306119 (22M) [application/octet-stream]
Saving to: ‘./mobilenet_iter_73000.caffemodel’

mobilenet_iter_73000.caffemo 100%[============================================>]  22.23M  2.94MB/s    in 8.2s    

2018-11-01 09:51:33 (2.70 MB/s) - ‘./mobilenet_iter_73000.caffemodel’ saved [23306119/23306119]


making prototxt
Downloading Prototxt file
--2018-11-01 09:51:33--  https://raw.githubusercontent.com/chuanqi305/MobileNet-SSD/master/deploy.prototxt
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.0.133, 151.101.64.133, 151.101.128.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.0.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 44667 (44K) [text/plain]
Saving to: ‘deploy.prototxt’

ploy.prototxt                100%[============================================>]  43.62K  --.-KB/s    in 0.1s    

2018-11-01 09:51:34 (333 KB/s) - ‘deploy.prototxt’ saved [44667/44667]

prototxt file downloaded.
patching prototxt.
patching file patched_deploy.prototxt (read from deploy.prototxt)
Hunk #1 succeeded at 3096 (offset 1190 lines).
Hunk #2 succeeded at 3099 (offset 1190 lines).
if [ -e merge_bn.py ] ; \
then \
	echo "merge_bn.py already exists. skipping download."; \
else \
	echo ""; \
	echo "Attempting download of merge_bn.py from this url: "; \
	echo "https://raw.githubusercontent.com/chuanqi305/MobileNet-SSD/master/merge_bn.py"; \
	wget -P . https://raw.githubusercontent.com/chuanqi305/MobileNet-SSD/master/merge_bn.py; \
	python3 merge_bn.py --model deploy.prototxt --weight mobilenet_iter_73000.caffemodel; \
fi; \


Attempting download of merge_bn.py from this url: 
https://raw.githubusercontent.com/chuanqi305/MobileNet-SSD/master/merge_bn.py
--2018-11-01 09:51:34--  https://raw.githubusercontent.com/chuanqi305/MobileNet-SSD/master/merge_bn.py
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.64.133, 151.101.128.133, 151.101.192.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.64.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 4426 (4.3K) [text/plain]
Saving to: ‘./merge_bn.py’

merge_bn.py                  100%[============================================>]   4.32K  --.-KB/s    in 0s      

2018-11-01 09:51:35 (55.4 MB/s) - ‘./merge_bn.py’ saved [4426/4426]

WARNING: Logging before InitGoogleLogging() is written to STDERR
W1101 09:51:36.099043  7224 _caffe.cpp:122] DEPRECATION WARNING - deprecated use of Python interface
W1101 09:51:36.099136  7224 _caffe.cpp:123] Use this instead (with the named "weights" parameter):
W1101 09:51:36.099159  7224 _caffe.cpp:125] Net('deploy.prototxt', 1, weights='mobilenet_iter_73000.caffemodel')
I1101 09:51:36.101335  7224 upgrade_proto.cpp:67] Attempting to upgrade input file specified using deprecated input fields: deploy.prototxt
I1101 09:51:36.101434  7224 upgrade_proto.cpp:70] Successfully upgraded file specified using deprecated input fields.
W1101 09:51:36.101460  7224 upgrade_proto.cpp:72] Note that future Caffe releases will only support input layers and not input fields.
I1101 09:51:36.101483  7224 upgrade_proto.cpp:77] Attempting to upgrade batch norm layers using deprecated params: deploy.prototxt
I1101 09:51:36.101510  7224 upgrade_proto.cpp:80] Successfully upgraded batch norm layers using deprecated params.
I1101 09:51:36.102473  7224 net.cpp:58] Initializing net from parameters: 
name: "MobileNet-SSD"
state {
  phase: TEST
  level: 0
}
layer {
  name: "input"
  type: "Input"
  top: "data"
  input_param {
    shape {
      dim: 1
      dim: 3
      dim: 300
      dim: 300
    }
  }
}
layer {
  name: "conv0"
  type: "Convolution"
  bottom: "data"
  top: "conv0"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 32
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv0/bn"
  type: "BatchNorm"
  bottom: "conv0"
  top: "conv0"
}
layer {
  name: "conv0/scale"
  type: "Scale"
  bottom: "conv0"
  top: "conv0"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv0/relu"
  type: "ReLU"
  bottom: "conv0"
  top: "conv0"
}
layer {
  name: "conv1/dw"
  type: "Convolution"
  bottom: "conv0"
  top: "conv1/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 32
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 32
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv1/dw/bn"
  type: "BatchNorm"
  bottom: "conv1/dw"
  top: "conv1/dw"
}
layer {
  name: "conv1/dw/scale"
  type: "Scale"
  bottom: "conv1/dw"
  top: "conv1/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv1/dw/relu"
  type: "ReLU"
  bottom: "conv1/dw"
  top: "conv1/dw"
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "conv1/dw"
  top: "conv1"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 64
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv1/bn"
  type: "BatchNorm"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "conv1/scale"
  type: "Scale"
  bottom: "conv1"
  top: "conv1"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv1/relu"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "conv2/dw"
  type: "Convolution"
  bottom: "conv1"
  top: "conv2/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 64
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 64
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv2/dw/bn"
  type: "BatchNorm"
  bottom: "conv2/dw"
  top: "conv2/dw"
}
layer {
  name: "conv2/dw/scale"
  type: "Scale"
  bottom: "conv2/dw"
  top: "conv2/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv2/dw/relu"
  type: "ReLU"
  bottom: "conv2/dw"
  top: "conv2/dw"
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "conv2/dw"
  top: "conv2"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv2/bn"
  type: "BatchNorm"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "conv2/scale"
  type: "Scale"
  bottom: "conv2"
  top: "conv2"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv2/relu"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "conv3/dw"
  type: "Convolution"
  bottom: "conv2"
  top: "conv3/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 128
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv3/dw/bn"
  type: "BatchNorm"
  bottom: "conv3/dw"
  top: "conv3/dw"
}
layer {
  name: "conv3/dw/scale"
  type: "Scale"
  bottom: "conv3/dw"
  top: "conv3/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv3/dw/relu"
  type: "ReLU"
  bottom: "conv3/dw"
  top: "conv3/dw"
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "conv3/dw"
  top: "conv3"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv3/bn"
  type: "BatchNorm"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv3/scale"
  type: "Scale"
  bottom: "conv3"
  top: "conv3"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv3/relu"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4/dw"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 128
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv4/dw/bn"
  type: "BatchNorm"
  bottom: "conv4/dw"
  top: "conv4/dw"
}
layer {
  name: "conv4/dw/scale"
  type: "Scale"
  bottom: "conv4/dw"
  top: "conv4/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv4/dw/relu"
  type: "ReLU"
  bottom: "conv4/dw"
  top: "conv4/dw"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv4/dw"
  top: "conv4"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv4/bn"
  type: "BatchNorm"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv4/scale"
  type: "Scale"
  bottom: "conv4"
  top: "conv4"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv4/relu"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5/dw"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 256
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv5/dw/bn"
  type: "BatchNorm"
  bottom: "conv5/dw"
  top: "conv5/dw"
}
layer {
  name: "conv5/dw/scale"
  type: "Scale"
  bottom: "conv5/dw"
  top: "conv5/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv5/dw/relu"
  type: "ReLU"
  bottom: "conv5/dw"
  top: "conv5/dw"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv5/dw"
  top: "conv5"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv5/bn"
  type: "BatchNorm"
  bottom: "conv5"
  top: "conv5"
}
layer {
  name: "conv5/scale"
  type: "Scale"
  bottom: "conv5"
  top: "conv5"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv5/relu"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
}
layer {
  name: "conv6/dw"
  type: "Convolution"
  bottom: "conv5"
  top: "conv6/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 256
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv6/dw/bn"
  type: "BatchNorm"
  bottom: "conv6/dw"
  top: "conv6/dw"
}
layer {
  name: "conv6/dw/scale"
  type: "Scale"
  bottom: "conv6/dw"
  top: "conv6/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv6/dw/relu"
  type: "ReLU"
  bottom: "conv6/dw"
  top: "conv6/dw"
}
layer {
  name: "conv6"
  type: "Convolution"
  bottom: "conv6/dw"
  top: "conv6"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv6/bn"
  type: "BatchNorm"
  bottom: "conv6"
  top: "conv6"
}
layer {
  name: "conv6/scale"
  type: "Scale"
  bottom: "conv6"
  top: "conv6"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv6/relu"
  type: "ReLU"
  bottom: "conv6"
  top: "conv6"
}
layer {
  name: "conv7/dw"
  type: "Convolution"
  bottom: "conv6"
  top: "conv7/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 512
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv7/dw/bn"
  type: "BatchNorm"
  bottom: "conv7/dw"
  top: "conv7/dw"
}
layer {
  name: "conv7/dw/scale"
  type: "Scale"
  bottom: "conv7/dw"
  top: "conv7/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv7/dw/relu"
  type: "ReLU"
  bottom: "conv7/dw"
  top: "conv7/dw"
}
layer {
  name: "conv7"
  type: "Convolution"
  bottom: "conv7/dw"
  top: "conv7"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv7/bn"
  type: "BatchNorm"
  bottom: "conv7"
  top: "conv7"
}
layer {
  name: "conv7/scale"
  type: "Scale"
  bottom: "conv7"
  top: "conv7"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv7/relu"
  type: "ReLU"
  bottom: "conv7"
  top: "conv7"
}
layer {
  name: "conv8/dw"
  type: "Convolution"
  bottom: "conv7"
  top: "conv8/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 512
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv8/dw/bn"
  type: "BatchNorm"
  bottom: "conv8/dw"
  top: "conv8/dw"
}
layer {
  name: "conv8/dw/scale"
  type: "Scale"
  bottom: "conv8/dw"
  top: "conv8/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv8/dw/relu"
  type: "ReLU"
  bottom: "conv8/dw"
  top: "conv8/dw"
}
layer {
  name: "conv8"
  type: "Convolution"
  bottom: "conv8/dw"
  top: "conv8"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv8/bn"
  type: "BatchNorm"
  bottom: "conv8"
  top: "conv8"
}
layer {
  name: "conv8/scale"
  type: "Scale"
  bottom: "conv8"
  top: "conv8"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv8/relu"
  type: "ReLU"
  bottom: "conv8"
  top: "conv8"
}
layer {
  name: "conv9/dw"
  type: "Convolution"
  bottom: "conv8"
  top: "conv9/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 512
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv9/dw/bn"
  type: "BatchNorm"
  bottom: "conv9/dw"
  top: "conv9/dw"
}
layer {
  name: "conv9/dw/scale"
  type: "Scale"
  bottom: "conv9/dw"
  top: "conv9/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv9/dw/relu"
  type: "ReLU"
  bottom: "conv9/dw"
  top: "conv9/dw"
}
layer {
  name: "conv9"
  type: "Convolution"
  bottom: "conv9/dw"
  top: "conv9"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv9/bn"
  type: "BatchNorm"
  bottom: "conv9"
  top: "conv9"
}
layer {
  name: "conv9/scale"
  type: "Scale"
  bottom: "conv9"
  top: "conv9"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv9/relu"
  type: "ReLU"
  bottom: "conv9"
  top: "conv9"
}
layer {
  name: "conv10/dw"
  type: "Convolution"
  bottom: "conv9"
  top: "conv10/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 512
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv10/dw/bn"
  type: "BatchNorm"
  bottom: "conv10/dw"
  top: "conv10/dw"
}
layer {
  name: "conv10/dw/scale"
  type: "Scale"
  bottom: "conv10/dw"
  top: "conv10/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv10/dw/relu"
  type: "ReLU"
  bottom: "conv10/dw"
  top: "conv10/dw"
}
layer {
  name: "conv10"
  type: "Convolution"
  bottom: "conv10/dw"
  top: "conv10"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv10/bn"
  type: "BatchNorm"
  bottom: "conv10"
  top: "conv10"
}
layer {
  name: "conv10/scale"
  type: "Scale"
  bottom: "conv10"
  top: "conv10"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv10/relu"
  type: "ReLU"
  bottom: "conv10"
  top: "conv10"
}
layer {
  name: "conv11/dw"
  type: "Convolution"
  bottom: "conv10"
  top: "conv11/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 512
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv11/dw/bn"
  type: "BatchNorm"
  bottom: "conv11/dw"
  top: "conv11/dw"
}
layer {
  name: "conv11/dw/scale"
  type: "Scale"
  bottom: "conv11/dw"
  top: "conv11/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv11/dw/relu"
  type: "ReLU"
  bottom: "conv11/dw"
  top: "conv11/dw"
}
layer {
  name: "conv11"
  type: "Convolution"
  bottom: "conv11/dw"
  top: "conv11"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv11/bn"
  type: "BatchNorm"
  bottom: "conv11"
  top: "conv11"
}
layer {
  name: "conv11/scale"
  type: "Scale"
  bottom: "conv11"
  top: "conv11"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv11/relu"
  type: "ReLU"
  bottom: "conv11"
  top: "conv11"
}
layer {
  name: "conv12/dw"
  type: "Convolution"
  bottom: "conv11"
  top: "conv12/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 512
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv12/dw/bn"
  type: "BatchNorm"
  bottom: "conv12/dw"
  top: "conv12/dw"
}
layer {
  name: "conv12/dw/scale"
  type: "Scale"
  bottom: "conv12/dw"
  top: "conv12/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv12/dw/relu"
  type: "ReLU"
  bottom: "conv12/dw"
  top: "conv12/dw"
}
layer {
  name: "conv12"
  type: "Convolution"
  bottom: "conv12/dw"
  top: "conv12"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 1024
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv12/bn"
  type: "BatchNorm"
  bottom: "conv12"
  top: "conv12"
}
layer {
  name: "conv12/scale"
  type: "Scale"
  bottom: "conv12"
  top: "conv12"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv12/relu"
  type: "ReLU"
  bottom: "conv12"
  top: "conv12"
}
layer {
  name: "conv13/dw"
  type: "Convolution"
  bottom: "conv12"
  top: "conv13/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 1024
    bias_term: false
    pad: 1
    kernel_size: 3
    group: 1024
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv13/dw/bn"
  type: "BatchNorm"
  bottom: "conv13/dw"
  top: "conv13/dw"
}
layer {
  name: "conv13/dw/scale"
  type: "Scale"
  bottom: "conv13/dw"
  top: "conv13/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv13/dw/relu"
  type: "ReLU"
  bottom: "conv13/dw"
  top: "conv13/dw"
}
layer {
  name: "conv13"
  type: "Convolution"
  bottom: "conv13/dw"
  top: "conv13"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 1024
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv13/bn"
  type: "BatchNorm"
  bottom: "conv13"
  top: "conv13"
}
layer {
  name: "conv13/scale"
  type: "Scale"
  bottom: "conv13"
  top: "conv13"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv13/relu"
  type: "ReLU"
  bottom: "conv13"
  top: "conv13"
}
layer {
  name: "conv14_1"
  type: "Convolution"
  bottom: "conv13"
  top: "conv14_1"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv14_1/bn"
  type: "BatchNorm"
  bottom: "conv14_1"
  top: "conv14_1"
}
layer {
  name: "conv14_1/scale"
  type: "Scale"
  bottom: "conv14_1"
  top: "conv14_1"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv14_1/relu"
  type: "ReLU"
  bottom: "conv14_1"
  top: "conv14_1"
}
layer {
  name: "conv14_2"
  type: "Convolution"
  bottom: "conv14_1"
  top: "conv14_2"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv14_2/bn"
  type: "BatchNorm"
  bottom: "conv14_2"
  top: "conv14_2"
}
layer {
  name: "conv14_2/scale"
  type: "Scale"
  bottom: "conv14_2"
  top: "conv14_2"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv14_2/relu"
  type: "ReLU"
  bottom: "conv14_2"
  top: "conv14_2"
}
layer {
  name: "conv15_1"
  type: "Convolution"
  bottom: "conv14_2"
  top: "conv15_1"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv15_1/bn"
  type: "BatchNorm"
  bottom: "conv15_1"
  top: "conv15_1"
}
layer {
  name: "conv15_1/scale"
  type: "Scale"
  bottom: "conv15_1"
  top: "conv15_1"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv15_1/relu"
  type: "ReLU"
  bottom: "conv15_1"
  top: "conv15_1"
}
layer {
  name: "conv15_2"
  type: "Convolution"
  bottom: "conv15_1"
  top: "conv15_2"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv15_2/bn"
  type: "BatchNorm"
  bottom: "conv15_2"
  top: "conv15_2"
}
layer {
  name: "conv15_2/scale"
  type: "Scale"
  bottom: "conv15_2"
  top: "conv15_2"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv15_2/relu"
  type: "ReLU"
  bottom: "conv15_2"
  top: "conv15_2"
}
layer {
  name: "conv16_1"
  type: "Convolution"
  bottom: "conv15_2"
  top: "conv16_1"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv16_1/bn"
  type: "BatchNorm"
  bottom: "conv16_1"
  top: "conv16_1"
}
layer {
  name: "conv16_1/scale"
  type: "Scale"
  bottom: "conv16_1"
  top: "conv16_1"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv16_1/relu"
  type: "ReLU"
  bottom: "conv16_1"
  top: "conv16_1"
}
layer {
  name: "conv16_2"
  type: "Convolution"
  bottom: "conv16_1"
  top: "conv16_2"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv16_2/bn"
  type: "BatchNorm"
  bottom: "conv16_2"
  top: "conv16_2"
}
layer {
  name: "conv16_2/scale"
  type: "Scale"
  bottom: "conv16_2"
  top: "conv16_2"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv16_2/relu"
  type: "ReLU"
  bottom: "conv16_2"
  top: "conv16_2"
}
layer {
  name: "conv17_1"
  type: "Convolution"
  bottom: "conv16_2"
  top: "conv17_1"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 64
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv17_1/bn"
  type: "BatchNorm"
  bottom: "conv17_1"
  top: "conv17_1"
}
layer {
  name: "conv17_1/scale"
  type: "Scale"
  bottom: "conv17_1"
  top: "conv17_1"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv17_1/relu"
  type: "ReLU"
  bottom: "conv17_1"
  top: "conv17_1"
}
layer {
  name: "conv17_2"
  type: "Convolution"
  bottom: "conv17_1"
  top: "conv17_2"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv17_2/bn"
  type: "BatchNorm"
  bottom: "conv17_2"
  top: "conv17_2"
}
layer {
  name: "conv17_2/scale"
  type: "Scale"
  bottom: "conv17_2"
  top: "conv17_2"
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "conv17_2/relu"
  type: "ReLU"
  bottom: "conv17_2"
  top: "conv17_2"
}
layer {
  name: "conv11_mbox_loc"
  type: "Convolution"
  bottom: "conv11"
  top: "conv11_mbox_loc"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  convolution_param {
    num_output: 12
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv11_mbox_loc_perm"
  type: "Permute"
  bottom: "conv11_mbox_loc"
  top: "conv11_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv11_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv11_mbox_loc_perm"
  top: "conv11_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv11_mbox_conf"
  type: "Convolution"
  bottom: "conv11"
  top: "conv11_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 63
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv11_mbox_conf_perm"
  type: "Permute"
  bottom: "conv11_mbox_conf"
  top: "conv11_mbox_conf_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv11_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv11_mbox_conf_perm"
  top: "conv11_mbox_conf_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv11_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv11"
  bottom: "data"
  top: "conv11_mbox_priorbox"
  prior_box_param {
    min_size: 60
    aspect_ratio: 2
    flip: true
    clip: false
    variance: 0.1
    variance: 0.1
    variance: 0.2
    variance: 0.2
    offset: 0.5
  }
}
layer {
  name: "conv13_mbox_loc"
  type: "Convolution"
  bottom: "conv13"
  top: "conv13_mbox_loc"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  convolution_param {
    num_output: 24
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv13_mbox_loc_perm"
  type: "Permute"
  bottom: "conv13_mbox_loc"
  top: "conv13_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv13_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv13_mbox_loc_perm"
  top: "conv13_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv13_mbox_conf"
  type: "Convolution"
  bottom: "conv13"
  top: "conv13_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 126
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv13_mbox_conf_perm"
  type: "Permute"
  bottom: "conv13_mbox_conf"
  top: "conv13_mbox_conf_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv13_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv13_mbox_conf_perm"
  top: "conv13_mbox_conf_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv13_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv13"
  bottom: "data"
  top: 
I1101 09:51:36.112706  7224 layer_factory.hpp:77] Creating layer input
I1101 09:51:36.113342  7224 net.cpp:100] Creating Layer input
I1101 09:51:36.113798  7224 net.cpp:408] input -> data
I1101 09:51:36.113819  7224 net.cpp:150] Setting up input
I1101 09:51:36.113826  7224 net.cpp:157] Top shape: 1 3 300 300 (270000)
I1101 09:51:36.113829  7224 net.cpp:165] Memory required for data: 1080000
I1101 09:51:36.113833  7224 layer_factory.hpp:77] Creating layer data_input_0_split
I1101 09:51:36.113840  7224 net.cpp:100] Creating Layer data_input_0_split
I1101 09:51:36.113844  7224 net.cpp:434] data_input_0_split <- data
I1101 09:51:36.113849  7224 net.cpp:408] data_input_0_split -> data_input_0_split_0
I1101 09:51:36.113855  7224 net.cpp:408] data_input_0_split -> data_input_0_split_1
I1101 09:51:36.113862  7224 net.cpp:408] data_input_0_split -> data_input_0_split_2
I1101 09:51:36.113950  7224 net.cpp:408] data_input_0_split -> data_input_0_split_3
I1101 09:51:36.113960  7224 net.cpp:408] data_input_0_split -> data_input_0_split_4
I1101 09:51:36.113965  7224 net.cpp:408] data_input_0_split -> data_input_0_split_5
I1101 09:51:36.113970  7224 net.cpp:408] data_input_0_split -> data_input_0_split_6
I1101 09:51:36.113978  7224 net.cpp:150] Setting up data_input_0_split
I1101 09:51:36.113983  7224 net.cpp:157] Top shape: 1 3 300 300 (270000)
I1101 09:51:36.113988  7224 net.cpp:157] Top shape: 1 3 300 300 (270000)
I1101 09:51:36.113992  7224 net.cpp:157] Top shape: 1 3 300 300 (270000)
I1101 09:51:36.113996  7224 net.cpp:157] Top shape: 1 3 300 300 (270000)
I1101 09:51:36.114001  7224 net.cpp:157] Top shape: 1 3 300 300 (270000)
I1101 09:51:36.114004  7224 net.cpp:157] Top shape: 1 3 300 300 (270000)
I1101 09:51:36.114008  7224 net.cpp:157] Top shape: 1 3 300 300 (270000)
I1101 09:51:36.114012  7224 net.cpp:165] Memory required for data: 8640000
......
......
......
I1101 09:51:36.312430  7224 net.cpp:283] Network initialization done.
I1101 09:51:36.333739  7224 upgrade_proto.cpp:77] Attempting to upgrade batch norm layers using deprecated params: mobilenet_iter_73000.caffemodel
I1101 09:51:36.333778  7224 upgrade_proto.cpp:80] Successfully upgraded batch norm layers using deprecated params.
I1101 09:51:36.334020  7224 net.cpp:761] Ignoring source layer data
I1101 09:51:36.334048  7224 net.cpp:761] Ignoring source layer data_data_0_split
I1101 09:51:36.340283  7224 net.cpp:761] Ignoring source layer mbox_loss
I1101 09:51:36.345633  7224 upgrade_proto.cpp:67] Attempting to upgrade input file specified using deprecated input fields: no_bn.prototxt
I1101 09:51:36.348554  7224 upgrade_proto.cpp:70] Successfully upgraded file specified using deprecated input fields.
W1101 09:51:36.348590  7224 upgrade_proto.cpp:72] Note that future Caffe releases will only support input layers and not input fields.
I1101 09:51:36.349210  7224 net.cpp:58] Initializing net from parameters: 
name: "MobileNet-SSD"
state {
  phase: TEST
  level: 0
}
layer {
  name: "input"
  type: "Input"
  top: "data"
  input_param {
    shape {
      dim: 1
      dim: 3
      dim: 300
      dim: 300
    }
  }
}
layer {
  name: "conv0"
  type: "Convolution"
  bottom: "data"
  top: "conv0"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 32
    bias_term: true
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv0/relu"
  type: "ReLU"
  bottom: "conv0"
  top: "conv0"
}
layer {
  name: "conv1/dw"
  type: "Convolution"
  bottom: "conv0"
  top: "conv1/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 32
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 32
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv1/dw/relu"
  type: "ReLU"
  bottom: "conv1/dw"
  top: "conv1/dw"
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "conv1/dw"
  top: "conv1"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 64
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv1/relu"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "conv2/dw"
  type: "Convolution"
  bottom: "conv1"
  top: "conv2/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 64
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 64
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv2/dw/relu"
  type: "ReLU"
  bottom: "conv2/dw"
  top: "conv2/dw"
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "conv2/dw"
  top: "conv2"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv2/relu"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "conv3/dw"
  type: "Convolution"
  bottom: "conv2"
  top: "conv3/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 128
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv3/dw/relu"
  type: "ReLU"
  bottom: "conv3/dw"
  top: "conv3/dw"
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "conv3/dw"
  top: "conv3"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv3/relu"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4/dw"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 128
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv4/dw/relu"
  type: "ReLU"
  bottom: "conv4/dw"
  top: "conv4/dw"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv4/dw"
  top: "conv4"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv4/relu"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5/dw"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 256
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv5/dw/relu"
  type: "ReLU"
  bottom: "conv5/dw"
  top: "conv5/dw"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv5/dw"
  top: "conv5"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv5/relu"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
}
layer {
  name: "conv6/dw"
  type: "Convolution"
  bottom: "conv5"
  top: "conv6/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 256
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv6/dw/relu"
  type: "ReLU"
  bottom: "conv6/dw"
  top: "conv6/dw"
}
layer {
  name: "conv6"
  type: "Convolution"
  bottom: "conv6/dw"
  top: "conv6"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv6/relu"
  type: "ReLU"
  bottom: "conv6"
  top: "conv6"
}
layer {
  name: "conv7/dw"
  type: "Convolution"
  bottom: "conv6"
  top: "conv7/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 512
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv7/dw/relu"
  type: "ReLU"
  bottom: "conv7/dw"
  top: "conv7/dw"
}
layer {
  name: "conv7"
  type: "Convolution"
  bottom: "conv7/dw"
  top: "conv7"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv7/relu"
  type: "ReLU"
  bottom: "conv7"
  top: "conv7"
}
layer {
  name: "conv8/dw"
  type: "Convolution"
  bottom: "conv7"
  top: "conv8/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 512
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv8/dw/relu"
  type: "ReLU"
  bottom: "conv8/dw"
  top: "conv8/dw"
}
layer {
  name: "conv8"
  type: "Convolution"
  bottom: "conv8/dw"
  top: "conv8"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv8/relu"
  type: "ReLU"
  bottom: "conv8"
  top: "conv8"
}
layer {
  name: "conv9/dw"
  type: "Convolution"
  bottom: "conv8"
  top: "conv9/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 512
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv9/dw/relu"
  type: "ReLU"
  bottom: "conv9/dw"
  top: "conv9/dw"
}
layer {
  name: "conv9"
  type: "Convolution"
  bottom: "conv9/dw"
  top: "conv9"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv9/relu"
  type: "ReLU"
  bottom: "conv9"
  top: "conv9"
}
layer {
  name: "conv10/dw"
  type: "Convolution"
  bottom: "conv9"
  top: "conv10/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 512
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv10/dw/relu"
  type: "ReLU"
  bottom: "conv10/dw"
  top: "conv10/dw"
}
layer {
  name: "conv10"
  type: "Convolution"
  bottom: "conv10/dw"
  top: "conv10"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv10/relu"
  type: "ReLU"
  bottom: "conv10"
  top: "conv10"
}
layer {
  name: "conv11/dw"
  type: "Convolution"
  bottom: "conv10"
  top: "conv11/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 512
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv11/dw/relu"
  type: "ReLU"
  bottom: "conv11/dw"
  top: "conv11/dw"
}
layer {
  name: "conv11"
  type: "Convolution"
  bottom: "conv11/dw"
  top: "conv11"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv11/relu"
  type: "ReLU"
  bottom: "conv11"
  top: "conv11"
}
layer {
  name: "conv12/dw"
  type: "Convolution"
  bottom: "conv11"
  top: "conv12/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 512
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv12/dw/relu"
  type: "ReLU"
  bottom: "conv12/dw"
  top: "conv12/dw"
}
layer {
  name: "conv12"
  type: "Convolution"
  bottom: "conv12/dw"
  top: "conv12"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 1024
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv12/relu"
  type: "ReLU"
  bottom: "conv12"
  top: "conv12"
}
layer {
  name: "conv13/dw"
  type: "Convolution"
  bottom: "conv12"
  top: "conv13/dw"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 1024
    bias_term: true
    pad: 1
    kernel_size: 3
    group: 1024
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv13/dw/relu"
  type: "ReLU"
  bottom: "conv13/dw"
  top: "conv13/dw"
}
layer {
  name: "conv13"
  type: "Convolution"
  bottom: "conv13/dw"
  top: "conv13"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 1024
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv13/relu"
  type: "ReLU"
  bottom: "conv13"
  top: "conv13"
}
layer {
  name: "conv14_1"
  type: "Convolution"
  bottom: "conv13"
  top: "conv14_1"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv14_1/relu"
  type: "ReLU"
  bottom: "conv14_1"
  top: "conv14_1"
}
layer {
  name: "conv14_2"
  type: "Convolution"
  bottom: "conv14_1"
  top: "conv14_2"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 512
    bias_term: true
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv14_2/relu"
  type: "ReLU"
  bottom: "conv14_2"
  top: "conv14_2"
}
layer {
  name: "conv15_1"
  type: "Convolution"
  bottom: "conv14_2"
  top: "conv15_1"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv15_1/relu"
  type: "ReLU"
  bottom: "conv15_1"
  top: "conv15_1"
}
layer {
  name: "conv15_2"
  type: "Convolution"
  bottom: "conv15_1"
  top: "conv15_2"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: true
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv15_2/relu"
  type: "ReLU"
  bottom: "conv15_2"
  top: "conv15_2"
}
layer {
  name: "conv16_1"
  type: "Convolution"
  bottom: "conv15_2"
  top: "conv16_1"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv16_1/relu"
  type: "ReLU"
  bottom: "conv16_1"
  top: "conv16_1"
}
layer {
  name: "conv16_2"
  type: "Convolution"
  bottom: "conv16_1"
  top: "conv16_2"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 256
    bias_term: true
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv16_2/relu"
  type: "ReLU"
  bottom: "conv16_2"
  top: "conv16_2"
}
layer {
  name: "conv17_1"
  type: "Convolution"
  bottom: "conv16_2"
  top: "conv17_1"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 64
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv17_1/relu"
  type: "ReLU"
  bottom: "conv17_1"
  top: "conv17_1"
}
layer {
  name: "conv17_2"
  type: "Convolution"
  bottom: "conv17_1"
  top: "conv17_2"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  convolution_param {
    num_output: 128
    bias_term: true
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "conv17_2/relu"
  type: "ReLU"
  bottom: "conv17_2"
  top: "conv17_2"
}
layer {
  name: "conv11_mbox_loc"
  type: "Convolution"
  bottom: "conv11"
  top: "conv11_mbox_loc"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  convolution_param {
    num_output: 12
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv11_mbox_loc_perm"
  type: "Permute"
  bottom: "conv11_mbox_loc"
  top: "conv11_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv11_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv11_mbox_loc_perm"
  top: "conv11_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv11_mbox_conf"
  type: "Convolution"
  bottom: "conv11"
  top: "conv11_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 63
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv11_mbox_conf_perm"
  type: "Permute"
  bottom: "conv11_mbox_conf"
  top: "conv11_mbox_conf_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv11_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv11_mbox_conf_perm"
  top: "conv11_mbox_conf_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv11_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv11"
  bottom: "data"
  top: "conv11_mbox_priorbox"
  prior_box_param {
    min_size: 60
    aspect_ratio: 2
    flip: true
    clip: false
    variance: 0.1
    variance: 0.1
    variance: 0.2
    variance: 0.2
    offset: 0.5
  }
}
layer {
  name: "conv13_mbox_loc"
  type: "Convolution"
  bottom: "conv13"
  top: "conv13_mbox_loc"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  convolution_param {
    num_output: 24
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv13_mbox_loc_perm"
  type: "Permute"
  bottom: "conv13_mbox_loc"
  top: "conv13_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv13_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv13_mbox_loc_perm"
  top: "conv13_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv13_mbox_conf"
  type: "Convolution"
  bottom: "conv13"
  top: "conv13_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 126
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv13_mbox_conf_perm"
  type: "Permute"
  bottom: "conv13_mbox_conf"
  top: "conv13_mbox_conf_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv13_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv13_mbox_conf_perm"
  top: "conv13_mbox_conf_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv13_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv13"
  bottom: "data"
  top: "conv13_mbox_priorbox"
  prior_box_param {
    min_size: 105
    max_size: 150
    aspect_ratio: 2
    aspect_ratio: 3
    flip: true
    clip: false
    variance: 0.1
    variance: 0.1
    variance: 0.2
    variance: 0.2
    offset: 0.5
  }
}
layer {
  name: "conv14_2_mbox_loc"
  type: "Convolution"
  bottom: "conv14_2"
  top: "conv14_2_mbox_loc"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  convolution_param {
    num_output: 24
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv14_2_mbox_loc_perm"
  type: "Permute"
  bottom: "conv14_2_mbox_loc"
  top: "conv14_2_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv14_2_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv14_2_mbox_loc_perm"
  top: "conv14_2_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv14_2_mbox_conf"
  type: "Convolution"
  bottom: "conv14_2"
  top: "conv14_2_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 126
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv14_2_mbox_conf_perm"
  type: "Permute"
  bottom: "conv14_2_mbox_conf"
  top: "conv14_2_mbox_conf_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv14_2_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv14_2_mbox_conf_perm"
  top: "conv14_2_mbox_conf_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv14_2_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv14_2"
  bottom: "data"
  top: "conv14_2_mbox_priorbox"
  prior_box_param {
    min_size: 150
    max_size: 195
    aspect_ratio: 2
    aspect_ratio: 3
    flip: true
    clip: false
    variance: 0.1
    variance: 0.1
    variance: 0.2
    variance: 0.2
    offset: 0.5
  }
}
layer {
  name: "conv15_2_mbox_loc"
  type: "Convolution"
  bottom: "conv15_2"
  top: "conv15_2_mbox_loc"
  param {
    lr_mult: 0.1
    decay_mult: 0.1
  }
  param {
    lr_mult: 0.2
    decay_mult: 0
  }
  convolution_param {
    num_output: 24
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "conv15_2_mbox_loc_perm"
  type: "Permute"
  bottom: "conv15_2_mbox_loc"
  top: "conv15_2_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv15_2_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv15_2_mbox_loc_perm"
  top: "conv15_2_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv15_2_mbox_conf"
  type: "Convolution"
  bottom: "conv15_2"
  top: "conv15_2_mbox_conf"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 126
    bias_term: true
    kernel_size: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}

相關推薦

Intel® Movidius™ Neural Compute SDK - video_objects

Intel® Movidius™ Neural Compute SDK - video_objects https://github.com/movidius/ncappzoo/tree/master/apps/video_objects ncappzoo/apps/video_ob

Intel® Movidius™ Neural Compute SDK - object-detector

Intel® Movidius™ Neural Compute SDK - object-detector https://github.com/movidius/ncappzoo/tree/master/apps/object-detector ncappzoo/apps/obje

Intel® Movidius™ Neural Compute SDK - TinyYolo

Intel® Movidius™ Neural Compute SDK - TinyYolo https://github.com/movidius/ncappzoo/tree/master/caffe/TinyYolo ncappzoo/caffe/TinyYolo/ Intr

intel Movidius Neural Network Stick各種網路速度測試

make examples 網路名 time(ms) caffe_alexnet 88.04 caffe_googlelenet 93.65 caffe_squeezenet 46.70 tf_inc

Qualcomm Heterogeneous Compute SDK(1)

1.What is Qualcomm Heterogeneous Compute SDK?     Qualcomm Heterogeneous Compute SDK 是高通開發者工具集中用於開發階段的重要工具，它可以幫助開發者更好地利用 高通平臺硬體的效能，提升應用的效

Flir's Firefly camera uses Intel Movidius chips for on

Flir Systems, a sensor company that primarily makes thermal imaging products, is launching the Firefly camera -- a small piece of hardware that uses Intel'

Intel Movidius Intel Newsroom

Movidius, an Intel company, is transforming the future of computer vision and artificial intelligence (AI) to accelerate innovation for the next generation

Intel--巧用Media SDK檢查系統硬體加速

         Media SDK是Intel強大的視音訊軟體開發包。它提供了相應的豐富的DShow filters，而且也提供了功能完備的視音訊APIs。本文主要將闡述如何巧用這些APIs來實現系統硬體加速功能。         在使用這些API之前，我們必須瞭解一點基

美國高通 Snapdragon Neural Processing Engine SDK （SNPE） 系列 （1）：使用者自定義層JNI實現

轉自：https://blog.csdn.net/guvcolie/article/details/77937786         Snapdragon Neural Processing Engine SDK是美國高通公司出品的神經網路處理引擎（SNP

Eta Compute Debuts Spiking Neural Network Chip for Edge AI

At Arm Tech Con today, West Lake Village, Calif.-based startup Eta Compute showed off what it believes is the first commercial low-power AI chip capable of

Ubuntu 16.04下Intel SGX驅動、平臺軟體和SDK安裝

本文作者：邱朋飛 1.下載SDK、SGX驅動和平臺軟體： 1.1 網址：https://01.org/zh/intel-software-guard-extensions/downloads?langredirect=1 1.2 選擇Intel SGX Linux

intel media sdk 使用時必須開啟整合顯示卡

1、使用intel media sdk 時，因為要使用硬體加速的原因，必須開啟整合顯示卡 2、可是一般的桌上型電腦，預設是選擇獨立顯示卡，所以需要在bios設定一下 3、整合顯示卡開啟方式可以參考，

Android SDK安裝時出錯“android Failed to rename directory”的解決方法

add size android-s 目錄 解決 androi director lpack lis Android SDK安裝時出錯“android Failed to rename directory”的解決的方法 安裝Android SDK時遇到Faile

Microsoft Speech SDK開發包 使用

world 選擇 錯誤信息 安裝 erl 編寫 targe 如何 tdi 下載開發包。我們首先從微軟的官網上面下載開發包，下載地址如下： http://www.microsoft.com/en-us/download/details.aspx?id=10121我們主要

暴走吧！Snapdragon SDK開發速成指南

電視 新建 芯片 數據 光標 利用 android安裝 賬號 集體 （文/Aurora J） Qualcomm的Snapdragon處理器。它快如閃電、效率極高。擅長挑戰多任務極限，而且擁有攻城獅們夢寐以求的無限潛能。它能確保您的手機集4G LTE、極速體驗、長久續航

極光IM初始化SDK出錯

tle register 方便 ads spa scheme jnilibs opened mas 1.項目的applicationID要和你在極光官網申請的應用ID保持一致 2. 因為我沒有使用JCenter的自動集成功能，而是直接把so文件和極光jar包復制進了Andr

獲取iOS系統版本號，慎重使用[[[UIDevice currentDevice] systemVersion] floatValue]——【sdk缺陷】

net 版本 ice system family class 失效 color -s iOS 最常見的獲取系統版本的方法是： [[[UIDevice currentDevice] systemVersion] floatValue] 可是。這個floatValue是

Machine Learning：Neural Network---Representation

white div and for 設計 rop out fcm multi Machine Learning：Neural Network---Representation 1。Non-Linear Classification 假設還採取簡

Vertebrae 發布了新的SDK！

本地 科技 新的 lan .html art 賺錢 支付 ebr ? （52VR開發網2017年5月15日訊） VR的優先級列表中的貨幣化很高。 雖然科技公司和品牌已經開始投入更多的內容瀏覽器創作，但從內容瀏覽器中賺錢仍然是一場艱巨的戰鬥。 ?但是，貨

OCR車牌識別SDK特點，雲脈SaaS平臺可API接入

雲脈車牌識別技術是指能夠檢測到受監控路面的車輛並自動提取車輛牌照信息（含漢字字符、英文字母、阿拉伯數字及號牌顏色）進行處理的技術。是現代智能交通系統中的重要組成部分之一，應用十分廣泛。 OCR車牌識別SDK特點： 1.識別速度快，平均識別時間少於3秒（測試機型：三星