Winodws10下利用CAFFE对DenseNet进行训练

最新推荐文章于 2020-11-20 18:53:07 发布
原创 最新推荐文章于 2020-11-20 18:53:07 发布 · 304 阅读 · 0 ·
CC 4.0 BY-SA版权
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
文章标签：

#DenseNet

本文详细介绍了使用Caffe深度学习框架进行图像分类的全过程，包括图片重命名、制作label、LMDB格式转换、计算均值文件、修改prototxt文件、网络训练、测试caffemodel以及绘制训练图像等关键步骤。

摘要生成于 C知道 ，由 DeepSeek-R1 满血版支持， 前往体验 >

1.将文件夹中的图片批量重命名
可以利用以下代码实现

#-*- coding: UTF-8 -*-
import os
path = " " #图片所在路径
filelist = os.listdir(path) #该文件夹下所有的文件（包括文件夹）
count=0
for file in filelist:
    print(file)
for file in filelist:   #遍历所有文件
    Olddir=os.path.join(path,file)   #原来的文件路径
    if os.path.isdir(Olddir):   #如果是文件夹则跳过
        continue
    filename=os.path.splitext(file)[0]   #文件名
    filetype=os.path.splitext(file)[1]   #文件扩展名
    Newdir=os.path.join(path,str(count).zfill(4)+filetype)  #用字符串函数zfill 以0补全所需位数
    os.rename(Olddir,Newdir)#重命名
    count+=1

2.制作label
在文件夹中新建一个TXT文件
复制以下代码

dir  *.*/b>train.txt
pause

将格式改为BAT，运行即可生成一个TXT文件，打开这个文件，利用CTRL+H将其替换。
然后复制粘贴将两个数据集的文件放在一起（label合成一个TXT）

3.制作LMDB格式
利用convert_imagesets.exe即可制作LMDB格式。

convert_imageset.exe的绝对路径名\convert_imageset.exe -参数1 -参数2 -参数3 -参数4

参数1：设置shuffle backend resize_hight resize_width

参数2：图片所存放的绝对路径

参数3：txt存放的绝对路径

参数4：转换后要保存的绝对路径

CMD中输入相应的参数即可

D:\caffe-Microsoft\caffe-master\Build\x64\Debug\convert_imageset.exe ^
--resize_height=32 --resize_width=32 ^
--backend="lmdb" ^
D:\caffe-Microsoft\caffe-master\models\bvlc_DenseNet\train\ ^
D:\caffe-Microsoft\caffe-master\models\bvlc_DenseNet\train\train_lable.txt ^
D:\caffe-Microsoft\caffe-master\models\bvlc_DenseNet\LMDB_train #不要创建这个文件夹，不然会报错
pause

4.计算均值文件
利用compute_image_mean.exe来计算均值文件。
若这一步报错，极可能是上一步的LMDB文件生成错误，建议检查一下上一步。

D:\caffe-Microsoft\caffe-master\Build\x64\Debug\compute_image_mean.exe D:\caffe-Microsoft\caffe-master\models\bvlc_DenseNet\LMDB_test D:\caffe-Microsoft\caffe-master\models\bvlc_DenseNet\LMDB_test\mean.binaryproto

pause

5.修改prototxt文件
将train_densenet.prototxt和test_densenet.prototxt文件内的
mean_file:和source: 进行修改，修改成自己的目录，电脑性能不好的话建议修改 batch_size的大小。
记得修改num_output

6.运行网络
新建一个TXT文件，写下如下代码。

D:/caffe-Microsoft/caffe-master/Build/x64/Debug/caffe.exe train --solver=D:/DenseNet/solver.prototxt >train.log 2>&1
 #>train.log 2>&1可以不加，这里加入>train.log 2>&1是为了新建一个log文件，用来绘图。
Pause

改成bat格式，运行，即可开始训练网络。
遇到了问题，想办法解决ing
——————分割线——————
遇到的问题是卡在加载均值文件上，一直都是在加载中，卡了一会我利用自带的make_densenet.py重新生成了prototxt文件，之后在运行居然开始成功训练了。
然后等待一段时间训练完成。
顺带记录一下sovler

train_net: "train_densenet.prototxt"#训练网络的网络文件，里面是路径，这里是相对路径，也可以改成绝对路径
test_net: "test_densenet.prototxt"#测试文件的网络文件，其他同上
test_iter: 200#测试次数
test_interval: 800#迭代多少次测试一次
base_lr: 0.001#基础学习率
display: 1000#训练多少次输出一次
max_iter: 50000#训练次数
lr_policy: "multistep"#
gamma: 0.1
momentum: 0.9
weight_decay: 0.0001#权重衰减
solver_mode: GPU#用显卡还是CPU训练
random_seed: 831486
stepvalue: 115000
stepvalue: 172500
type: "Nesterov"#caffe优化算法类型，有六种

7.测试caffemodle
利用classification.exe来对caffemodle进行测试
注意测试需要deploy.prototxt文件，但是我们没有这个文件，通过对train_densenet.prototxt进行修改即可获得。
修改后的具体内容

name: "DENSENET"
input: "Data1"
input_dim: 1
input_dim: 3
input_dim: 32
input_dim: 32

 
layer {
  name: "Convolution1"
  type: "Convolution"
  bottom: "Data1"
  top: "Convolution1"
  convolution_param {
    num_output: 16
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "BatchNorm1"
  type: "BatchNorm"
  bottom: "Convolution1"
  top: "BatchNorm1"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale1"
  type: "Scale"
  bottom: "BatchNorm1"
  top: "BatchNorm1"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU1"
  type: "ReLU"
  bottom: "BatchNorm1"
  top: "BatchNorm1"
}
layer {
  name: "Convolution2"
  type: "Convolution"
  bottom: "BatchNorm1"
  top: "Convolution2"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout1"
  type: "Dropout"
  bottom: "Convolution2"
  top: "Dropout1"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat1"
  type: "Concat"
  bottom: "Convolution1"
  bottom: "Dropout1"
  top: "Concat1"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm2"
  type: "BatchNorm"
  bottom: "Concat1"
  top: "BatchNorm2"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale2"
  type: "Scale"
  bottom: "BatchNorm2"
  top: "BatchNorm2"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU2"
  type: "ReLU"
  bottom: "BatchNorm2"
  top: "BatchNorm2"
}
layer {
  name: "Convolution3"
  type: "Convolution"
  bottom: "BatchNorm2"
  top: "Convolution3"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout2"
  type: "Dropout"
  bottom: "Convolution3"
  top: "Dropout2"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat2"
  type: "Concat"
  bottom: "Concat1"
  bottom: "Dropout2"
  top: "Concat2"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm3"
  type: "BatchNorm"
  bottom: "Concat2"
  top: "BatchNorm3"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale3"
  type: "Scale"
  bottom: "BatchNorm3"
  top: "BatchNorm3"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU3"
  type: "ReLU"
  bottom: "BatchNorm3"
  top: "BatchNorm3"
}
layer {
  name: "Convolution4"
  type: "Convolution"
  bottom: "BatchNorm3"
  top: "Convolution4"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout3"
  type: "Dropout"
  bottom: "Convolution4"
  top: "Dropout3"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat3"
  type: "Concat"
  bottom: "Concat2"
  bottom: "Dropout3"
  top: "Concat3"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm4"
  type: "BatchNorm"
  bottom: "Concat3"
  top: "BatchNorm4"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale4"
  type: "Scale"
  bottom: "BatchNorm4"
  top: "BatchNorm4"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU4"
  type: "ReLU"
  bottom: "BatchNorm4"
  top: "BatchNorm4"
}
layer {
  name: "Convolution5"
  type: "Convolution"
  bottom: "BatchNorm4"
  top: "Convolution5"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout4"
  type: "Dropout"
  bottom: "Convolution5"
  top: "Dropout4"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat4"
  type: "Concat"
  bottom: "Concat3"
  bottom: "Dropout4"
  top: "Concat4"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm5"
  type: "BatchNorm"
  bottom: "Concat4"
  top: "BatchNorm5"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale5"
  type: "Scale"
  bottom: "BatchNorm5"
  top: "BatchNorm5"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU5"
  type: "ReLU"
  bottom: "BatchNorm5"
  top: "BatchNorm5"
}
layer {
  name: "Convolution6"
  type: "Convolution"
  bottom: "BatchNorm5"
  top: "Convolution6"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout5"
  type: "Dropout"
  bottom: "Convolution6"
  top: "Dropout5"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat5"
  type: "Concat"
  bottom: "Concat4"
  bottom: "Dropout5"
  top: "Concat5"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm6"
  type: "BatchNorm"
  bottom: "Concat5"
  top: "BatchNorm6"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale6"
  type: "Scale"
  bottom: "BatchNorm6"
  top: "BatchNorm6"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU6"
  type: "ReLU"
  bottom: "BatchNorm6"
  top: "BatchNorm6"
}
layer {
  name: "Convolution7"
  type: "Convolution"
  bottom: "BatchNorm6"
  top: "Convolution7"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout6"
  type: "Dropout"
  bottom: "Convolution7"
  top: "Dropout6"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat6"
  type: "Concat"
  bottom: "Concat5"
  bottom: "Dropout6"
  top: "Concat6"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm7"
  type: "BatchNorm"
  bottom: "Concat6"
  top: "BatchNorm7"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale7"
  type: "Scale"
  bottom: "BatchNorm7"
  top: "BatchNorm7"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU7"
  type: "ReLU"
  bottom: "BatchNorm7"
  top: "BatchNorm7"
}
layer {
  name: "Convolution8"
  type: "Convolution"
  bottom: "BatchNorm7"
  top: "Convolution8"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout7"
  type: "Dropout"
  bottom: "Convolution8"
  top: "Dropout7"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat7"
  type: "Concat"
  bottom: "Concat6"
  bottom: "Dropout7"
  top: "Concat7"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm8"
  type: "BatchNorm"
  bottom: "Concat7"
  top: "BatchNorm8"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale8"
  type: "Scale"
  bottom: "BatchNorm8"
  top: "BatchNorm8"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU8"
  type: "ReLU"
  bottom: "BatchNorm8"
  top: "BatchNorm8"
}
layer {
  name: "Convolution9"
  type: "Convolution"
  bottom: "BatchNorm8"
  top: "Convolution9"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout8"
  type: "Dropout"
  bottom: "Convolution9"
  top: "Dropout8"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat8"
  type: "Concat"
  bottom: "Concat7"
  bottom: "Dropout8"
  top: "Concat8"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm9"
  type: "BatchNorm"
  bottom: "Concat8"
  top: "BatchNorm9"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale9"
  type: "Scale"
  bottom: "BatchNorm9"
  top: "BatchNorm9"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU9"
  type: "ReLU"
  bottom: "BatchNorm9"
  top: "BatchNorm9"
}
layer {
  name: "Convolution10"
  type: "Convolution"
  bottom: "BatchNorm9"
  top: "Convolution10"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout9"
  type: "Dropout"
  bottom: "Convolution10"
  top: "Dropout9"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat9"
  type: "Concat"
  bottom: "Concat8"
  bottom: "Dropout9"
  top: "Concat9"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm10"
  type: "BatchNorm"
  bottom: "Concat9"
  top: "BatchNorm10"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale10"
  type: "Scale"
  bottom: "BatchNorm10"
  top: "BatchNorm10"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU10"
  type: "ReLU"
  bottom: "BatchNorm10"
  top: "BatchNorm10"
}
layer {
  name: "Convolution11"
  type: "Convolution"
  bottom: "BatchNorm10"
  top: "Convolution11"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout10"
  type: "Dropout"
  bottom: "Convolution11"
  top: "Dropout10"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat10"
  type: "Concat"
  bottom: "Concat9"
  bottom: "Dropout10"
  top: "Concat10"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm11"
  type: "BatchNorm"
  bottom: "Concat10"
  top: "BatchNorm11"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale11"
  type: "Scale"
  bottom: "BatchNorm11"
  top: "BatchNorm11"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU11"
  type: "ReLU"
  bottom: "BatchNorm11"
  top: "BatchNorm11"
}
layer {
  name: "Convolution12"
  type: "Convolution"
  bottom: "BatchNorm11"
  top: "Convolution12"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout11"
  type: "Dropout"
  bottom: "Convolution12"
  top: "Dropout11"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat11"
  type: "Concat"
  bottom: "Concat10"
  bottom: "Dropout11"
  top: "Concat11"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm12"
  type: "BatchNorm"
  bottom: "Concat11"
  top: "BatchNorm12"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale12"
  type: "Scale"
  bottom: "BatchNorm12"
  top: "BatchNorm12"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU12"
  type: "ReLU"
  bottom: "BatchNorm12"
  top: "BatchNorm12"
}
layer {
  name: "Convolution13"
  type: "Convolution"
  bottom: "BatchNorm12"
  top: "Convolution13"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout12"
  type: "Dropout"
  bottom: "Convolution13"
  top: "Dropout12"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat12"
  type: "Concat"
  bottom: "Concat11"
  bottom: "Dropout12"
  top: "Concat12"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm13"
  type: "BatchNorm"
  bottom: "Concat12"
  top: "BatchNorm13"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale13"
  type: "Scale"
  bottom: "BatchNorm13"
  top: "BatchNorm13"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU13"
  type: "ReLU"
  bottom: "BatchNorm13"
  top: "BatchNorm13"
}
layer {
  name: "Convolution14"
  type: "Convolution"
  bottom: "BatchNorm13"
  top: "Convolution14"
  convolution_param {
    num_output: 160
    bias_term: false
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout13"
  type: "Dropout"
  bottom: "Convolution14"
  top: "Dropout13"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Pooling1"
  type: "Pooling"
  bottom: "Dropout13"
  top: "Pooling1"
  pooling_param {
    pool: AVE
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "BatchNorm14"
  type: "BatchNorm"
  bottom: "Pooling1"
  top: "BatchNorm14"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale14"
  type: "Scale"
  bottom: "BatchNorm14"
  top: "BatchNorm14"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU14"
  type: "ReLU"
  bottom: "BatchNorm14"
  top: "BatchNorm14"
}
layer {
  name: "Convolution15"
  type: "Convolution"
  bottom: "BatchNorm14"
  top: "Convolution15"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout14"
  type: "Dropout"
  bottom: "Convolution15"
  top: "Dropout14"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat13"
  type: "Concat"
  bottom: "Pooling1"
  bottom: "Dropout14"
  top: "Concat13"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm15"
  type: "BatchNorm"
  bottom: "Concat13"
  top: "BatchNorm15"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale15"
  type: "Scale"
  bottom: "BatchNorm15"
  top: "BatchNorm15"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU15"
  type: "ReLU"
  bottom: "BatchNorm15"
  top: "BatchNorm15"
}
layer {
  name: "Convolution16"
  type: "Convolution"
  bottom: "BatchNorm15"
  top: "Convolution16"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout15"
  type: "Dropout"
  bottom: "Convolution16"
  top: "Dropout15"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat14"
  type: "Concat"
  bottom: "Concat13"
  bottom: "Dropout15"
  top: "Concat14"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm16"
  type: "BatchNorm"
  bottom: "Concat14"
  top: "BatchNorm16"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale16"
  type: "Scale"
  bottom: "BatchNorm16"
  top: "BatchNorm16"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU16"
  type: "ReLU"
  bottom: "BatchNorm16"
  top: "BatchNorm16"
}
layer {
  name: "Convolution17"
  type: "Convolution"
  bottom: "BatchNorm16"
  top: "Convolution17"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout16"
  type: "Dropout"
  bottom: "Convolution17"
  top: "Dropout16"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat15"
  type: "Concat"
  bottom: "Concat14"
  bottom: "Dropout16"
  top: "Concat15"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm17"
  type: "BatchNorm"
  bottom: "Concat15"
  top: "BatchNorm17"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale17"
  type: "Scale"
  bottom: "BatchNorm17"
  top: "BatchNorm17"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU17"
  type: "ReLU"
  bottom: "BatchNorm17"
  top: "BatchNorm17"
}
layer {
  name: "Convolution18"
  type: "Convolution"
  bottom: "BatchNorm17"
  top: "Convolution18"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout17"
  type: "Dropout"
  bottom: "Convolution18"
  top: "Dropout17"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat16"
  type: "Concat"
  bottom: "Concat15"
  bottom: "Dropout17"
  top: "Concat16"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm18"
  type: "BatchNorm"
  bottom: "Concat16"
  top: "BatchNorm18"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale18"
  type: "Scale"
  bottom: "BatchNorm18"
  top: "BatchNorm18"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU18"
  type: "ReLU"
  bottom: "BatchNorm18"
  top: "BatchNorm18"
}
layer {
  name: "Convolution19"
  type: "Convolution"
  bottom: "BatchNorm18"
  top: "Convolution19"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout18"
  type: "Dropout"
  bottom: "Convolution19"
  top: "Dropout18"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat17"
  type: "Concat"
  bottom: "Concat16"
  bottom: "Dropout18"
  top: "Concat17"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm19"
  type: "BatchNorm"
  bottom: "Concat17"
  top: "BatchNorm19"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale19"
  type: "Scale"
  bottom: "BatchNorm19"
  top: "BatchNorm19"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU19"
  type: "ReLU"
  bottom: "BatchNorm19"
  top: "BatchNorm19"
}
layer {
  name: "Convolution20"
  type: "Convolution"
  bottom: "BatchNorm19"
  top: "Convolution20"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout19"
  type: "Dropout"
  bottom: "Convolution20"
  top: "Dropout19"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat18"
  type: "Concat"
  bottom: "Concat17"
  bottom: "Dropout19"
  top: "Concat18"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm20"
  type: "BatchNorm"
  bottom: "Concat18"
  top: "BatchNorm20"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale20"
  type: "Scale"
  bottom: "BatchNorm20"
  top: "BatchNorm20"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU20"
  type: "ReLU"
  bottom: "BatchNorm20"
  top: "BatchNorm20"
}
layer {
  name: "Convolution21"
  type: "Convolution"
  bottom: "BatchNorm20"
  top: "Convolution21"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout20"
  type: "Dropout"
  bottom: "Convolution21"
  top: "Dropout20"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat19"
  type: "Concat"
  bottom: "Concat18"
  bottom: "Dropout20"
  top: "Concat19"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm21"
  type: "BatchNorm"
  bottom: "Concat19"
  top: "BatchNorm21"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale21"
  type: "Scale"
  bottom: "BatchNorm21"
  top: "BatchNorm21"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU21"
  type: "ReLU"
  bottom: "BatchNorm21"
  top: "BatchNorm21"
}
layer {
  name: "Convolution22"
  type: "Convolution"
  bottom: "BatchNorm21"
  top: "Convolution22"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout21"
  type: "Dropout"
  bottom: "Convolution22"
  top: "Dropout21"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat20"
  type: "Concat"
  bottom: "Concat19"
  bottom: "Dropout21"
  top: "Concat20"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm22"
  type: "BatchNorm"
  bottom: "Concat20"
  top: "BatchNorm22"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale22"
  type: "Scale"
  bottom: "BatchNorm22"
  top: "BatchNorm22"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU22"
  type: "ReLU"
  bottom: "BatchNorm22"
  top: "BatchNorm22"
}
layer {
  name: "Convolution23"
  type: "Convolution"
  bottom: "BatchNorm22"
  top: "Convolution23"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout22"
  type: "Dropout"
  bottom: "Convolution23"
  top: "Dropout22"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat21"
  type: "Concat"
  bottom: "Concat20"
  bottom: "Dropout22"
  top: "Concat21"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm23"
  type: "BatchNorm"
  bottom: "Concat21"
  top: "BatchNorm23"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale23"
  type: "Scale"
  bottom: "BatchNorm23"
  top: "BatchNorm23"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU23"
  type: "ReLU"
  bottom: "BatchNorm23"
  top: "BatchNorm23"
}
layer {
  name: "Convolution24"
  type: "Convolution"
  bottom: "BatchNorm23"
  top: "Convolution24"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout23"
  type: "Dropout"
  bottom: "Convolution24"
  top: "Dropout23"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat22"
  type: "Concat"
  bottom: "Concat21"
  bottom: "Dropout23"
  top: "Concat22"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm24"
  type: "BatchNorm"
  bottom: "Concat22"
  top: "BatchNorm24"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale24"
  type: "Scale"
  bottom: "BatchNorm24"
  top: "BatchNorm24"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU24"
  type: "ReLU"
  bottom: "BatchNorm24"
  top: "BatchNorm24"
}
layer {
  name: "Convolution25"
  type: "Convolution"
  bottom: "BatchNorm24"
  top: "Convolution25"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout24"
  type: "Dropout"
  bottom: "Convolution25"
  top: "Dropout24"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat23"
  type: "Concat"
  bottom: "Concat22"
  bottom: "Dropout24"
  top: "Concat23"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm25"
  type: "BatchNorm"
  bottom: "Concat23"
  top: "BatchNorm25"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale25"
  type: "Scale"
  bottom: "BatchNorm25"
  top: "BatchNorm25"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU25"
  type: "ReLU"
  bottom: "BatchNorm25"
  top: "BatchNorm25"
}
layer {
  name: "Convolution26"
  type: "Convolution"
  bottom: "BatchNorm25"
  top: "Convolution26"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout25"
  type: "Dropout"
  bottom: "Convolution26"
  top: "Dropout25"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat24"
  type: "Concat"
  bottom: "Concat23"
  bottom: "Dropout25"
  top: "Concat24"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm26"
  type: "BatchNorm"
  bottom: "Concat24"
  top: "BatchNorm26"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale26"
  type: "Scale"
  bottom: "BatchNorm26"
  top: "BatchNorm26"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU26"
  type: "ReLU"
  bottom: "BatchNorm26"
  top: "BatchNorm26"
}
layer {
  name: "Convolution27"
  type: "Convolution"
  bottom: "BatchNorm26"
  top: "Convolution27"
  convolution_param {
    num_output: 304
    bias_term: false
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout26"
  type: "Dropout"
  bottom: "Convolution27"
  top: "Dropout26"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Pooling2"
  type: "Pooling"
  bottom: "Dropout26"
  top: "Pooling2"
  pooling_param {
    pool: AVE
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "BatchNorm27"
  type: "BatchNorm"
  bottom: "Pooling2"
  top: "BatchNorm27"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale27"
  type: "Scale"
  bottom: "BatchNorm27"
  top: "BatchNorm27"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU27"
  type: "ReLU"
  bottom: "BatchNorm27"
  top: "BatchNorm27"
}
layer {
  name: "Convolution28"
  type: "Convolution"
  bottom: "BatchNorm27"
  top: "Convolution28"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout27"
  type: "Dropout"
  bottom: "Convolution28"
  top: "Dropout27"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat25"
  type: "Concat"
  bottom: "Pooling2"
  bottom: "Dropout27"
  top: "Concat25"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm28"
  type: "BatchNorm"
  bottom: "Concat25"
  top: "BatchNorm28"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale28"
  type: "Scale"
  bottom: "BatchNorm28"
  top: "BatchNorm28"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU28"
  type: "ReLU"
  bottom: "BatchNorm28"
  top: "BatchNorm28"
}
layer {
  name: "Convolution29"
  type: "Convolution"
  bottom: "BatchNorm28"
  top: "Convolution29"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout28"
  type: "Dropout"
  bottom: "Convolution29"
  top: "Dropout28"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat26"
  type: "Concat"
  bottom: "Concat25"
  bottom: "Dropout28"
  top: "Concat26"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm29"
  type: "BatchNorm"
  bottom: "Concat26"
  top: "BatchNorm29"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale29"
  type: "Scale"
  bottom: "BatchNorm29"
  top: "BatchNorm29"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU29"
  type: "ReLU"
  bottom: "BatchNorm29"
  top: "BatchNorm29"
}
layer {
  name: "Convolution30"
  type: "Convolution"
  bottom: "BatchNorm29"
  top: "Convolution30"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout29"
  type: "Dropout"
  bottom: "Convolution30"
  top: "Dropout29"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat27"
  type: "Concat"
  bottom: "Concat26"
  bottom: "Dropout29"
  top: "Concat27"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm30"
  type: "BatchNorm"
  bottom: "Concat27"
  top: "BatchNorm30"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale30"
  type: "Scale"
  bottom: "BatchNorm30"
  top: "BatchNorm30"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU30"
  type: "ReLU"
  bottom: "BatchNorm30"
  top: "BatchNorm30"
}
layer {
  name: "Convolution31"
  type: "Convolution"
  bottom: "BatchNorm30"
  top: "Convolution31"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout30"
  type: "Dropout"
  bottom: "Convolution31"
  top: "Dropout30"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat28"
  type: "Concat"
  bottom: "Concat27"
  bottom: "Dropout30"
  top: "Concat28"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm31"
  type: "BatchNorm"
  bottom: "Concat28"
  top: "BatchNorm31"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale31"
  type: "Scale"
  bottom: "BatchNorm31"
  top: "BatchNorm31"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU31"
  type: "ReLU"
  bottom: "BatchNorm31"
  top: "BatchNorm31"
}
layer {
  name: "Convolution32"
  type: "Convolution"
  bottom: "BatchNorm31"
  top: "Convolution32"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout31"
  type: "Dropout"
  bottom: "Convolution32"
  top: "Dropout31"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat29"
  type: "Concat"
  bottom: "Concat28"
  bottom: "Dropout31"
  top: "Concat29"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm32"
  type: "BatchNorm"
  bottom: "Concat29"
  top: "BatchNorm32"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale32"
  type: "Scale"
  bottom: "BatchNorm32"
  top: "BatchNorm32"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU32"
  type: "ReLU"
  bottom: "BatchNorm32"
  top: "BatchNorm32"
}
layer {
  name: "Convolution33"
  type: "Convolution"
  bottom: "BatchNorm32"
  top: "Convolution33"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout32"
  type: "Dropout"
  bottom: "Convolution33"
  top: "Dropout32"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat30"
  type: "Concat"
  bottom: "Concat29"
  bottom: "Dropout32"
  top: "Concat30"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm33"
  type: "BatchNorm"
  bottom: "Concat30"
  top: "BatchNorm33"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale33"
  type: "Scale"
  bottom: "BatchNorm33"
  top: "BatchNorm33"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU33"
  type: "ReLU"
  bottom: "BatchNorm33"
  top: "BatchNorm33"
}
layer {
  name: "Convolution34"
  type: "Convolution"
  bottom: "BatchNorm33"
  top: "Convolution34"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout33"
  type: "Dropout"
  bottom: "Convolution34"
  top: "Dropout33"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat31"
  type: "Concat"
  bottom: "Concat30"
  bottom: "Dropout33"
  top: "Concat31"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm34"
  type: "BatchNorm"
  bottom: "Concat31"
  top: "BatchNorm34"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale34"
  type: "Scale"
  bottom: "BatchNorm34"
  top: "BatchNorm34"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU34"
  type: "ReLU"
  bottom: "BatchNorm34"
  top: "BatchNorm34"
}
layer {
  name: "Convolution35"
  type: "Convolution"
  bottom: "BatchNorm34"
  top: "Convolution35"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout34"
  type: "Dropout"
  bottom: "Convolution35"
  top: "Dropout34"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat32"
  type: "Concat"
  bottom: "Concat31"
  bottom: "Dropout34"
  top: "Concat32"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm35"
  type: "BatchNorm"
  bottom: "Concat32"
  top: "BatchNorm35"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale35"
  type: "Scale"
  bottom: "BatchNorm35"
  top: "BatchNorm35"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU35"
  type: "ReLU"
  bottom: "BatchNorm35"
  top: "BatchNorm35"
}
layer {
  name: "Convolution36"
  type: "Convolution"
  bottom: "BatchNorm35"
  top: "Convolution36"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout35"
  type: "Dropout"
  bottom: "Convolution36"
  top: "Dropout35"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat33"
  type: "Concat"
  bottom: "Concat32"
  bottom: "Dropout35"
  top: "Concat33"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm36"
  type: "BatchNorm"
  bottom: "Concat33"
  top: "BatchNorm36"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale36"
  type: "Scale"
  bottom: "BatchNorm36"
  top: "BatchNorm36"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU36"
  type: "ReLU"
  bottom: "BatchNorm36"
  top: "BatchNorm36"
}
layer {
  name: "Convolution37"
  type: "Convolution"
  bottom: "BatchNorm36"
  top: "Convolution37"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout36"
  type: "Dropout"
  bottom: "Convolution37"
  top: "Dropout36"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat34"
  type: "Concat"
  bottom: "Concat33"
  bottom: "Dropout36"
  top: "Concat34"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm37"
  type: "BatchNorm"
  bottom: "Concat34"
  top: "BatchNorm37"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale37"
  type: "Scale"
  bottom: "BatchNorm37"
  top: "BatchNorm37"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU37"
  type: "ReLU"
  bottom: "BatchNorm37"
  top: "BatchNorm37"
}
layer {
  name: "Convolution38"
  type: "Convolution"
  bottom: "BatchNorm37"
  top: "Convolution38"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout37"
  type: "Dropout"
  bottom: "Convolution38"
  top: "Dropout37"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat35"
  type: "Concat"
  bottom: "Concat34"
  bottom: "Dropout37"
  top: "Concat35"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm38"
  type: "BatchNorm"
  bottom: "Concat35"
  top: "BatchNorm38"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale38"
  type: "Scale"
  bottom: "BatchNorm38"
  top: "BatchNorm38"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU38"
  type: "ReLU"
  bottom: "BatchNorm38"
  top: "BatchNorm38"
}
layer {
  name: "Convolution39"
  type: "Convolution"
  bottom: "BatchNorm38"
  top: "Convolution39"
  convolution_param {
    num_output: 12
    bias_term: false
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "Dropout38"
  type: "Dropout"
  bottom: "Convolution39"
  top: "Dropout38"
  dropout_param {
    dropout_ratio: 0.2
  }
}
layer {
  name: "Concat36"
  type: "Concat"
  bottom: "Concat35"
  bottom: "Dropout38"
  top: "Concat36"
  concat_param {
    axis: 1
  }
}
layer {
  name: "BatchNorm39"
  type: "BatchNorm"
  bottom: "Concat36"
  top: "BatchNorm39"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "Scale39"
  type: "Scale"
  bottom: "BatchNorm39"
  top: "BatchNorm39"
  scale_param {
    filler {
      value: 1
    }
    bias_term: true
    bias_filler {
      value: 0
    }
  }
}
layer {
  name: "ReLU39"
  type: "ReLU"
  bottom: "BatchNorm39"
  top: "BatchNorm39"
}
layer {
  name: "Pooling3"
  type: "Pooling"
  bottom: "BatchNorm39"
  top: "Pooling3"
  pooling_param {
    pool: AVE
    global_pooling: true
  }
}
layer {
  name: "InnerProduct1"
  type: "InnerProduct"
  bottom: "Pooling3"
  top: "InnerProduct1"
  inner_product_param {
    num_output: 2
    bias_term: true
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "prob"
  type: "Softmax"
  bottom: "InnerProduct1"  
  top: "softmax"
}

新建TXT文件，然后填入调用的分类，修改为bat文件，运行。
以下是我填入的内容

D:\caffe-Microsoft\caffe-master\Build\x64\Debug\classification.exe D:\DenseNet\deploy.prototxt D:\DenseNet\_iter_50000.caffemodel D:\DenseNet\mean.binaryproto C:\Users\tianshan\Desktop\car\panduan\synset_words.txt C:\Users\tianshan\Desktop\car\panduan\2.jpg
pause

第一个参数是classification的绝对路径，第二个是deploy文件的路径，第三个是生成的caffemodle的路径，第四个是均值文件的路径，第五个是label的路径，第六个是你需要判断图片的路径。

8.绘制图像
python parse_log.py train.log ./
python plot_training_log.py 0 colaugAvI.png train.log

各类深度学习框架详解+深度学习训练环境搭建-GPU版本
master_hunter的博客
10-23 4520
工欲善其事必先利其器，对工具的熟练程度很多时候决定你工程项目的质量和上限。对于人工智能工程师来说，搭建本地深度学习环境来说是比较麻烦的一件事，其中涉及到较多的相关硬件和软件的兼容问题。很多初学者安装的深度学习框架环境仅能够使用CPU运行并没有利用到GPU，关于很多硬件关联的深度学习训练框架并没有清楚的认知，导致配置环境的时候很容易出现各类错误。所以本篇文章主要讲述清楚如何搭建深度学习环境以及框架选择和自己硬件匹配的系统。如果你发现深度学习看似难以掌握，我将尽力简化知识，将其转化为我们更容易理解的内容。
DenseNet网络实践（caffe版）
GL3_24的博客
05-23 1982
论文名称：Densely Connected Convolutional Networks（CVPR 2017, Best Paper Award） 论文链接：https://arxiv.org/pdf/1608.06993.pdf 源码链接：https://github.com/liuzhuang13/DenseNet caffe版源码： https://github.com/liuzhuang...
DenseNet-caffe
guojingjuan的博客
02-22 4643
https://github.com/liuzhuang13/DenseNetCaffe G. Huang, Z. Liu, and K.Q. Weinberger, “Denselyconnected convolutional networks,”
Caffe学习（四）：Windows使用Cifar10训练及测试Caffe版DenseNet
夜风里唱的专栏
07-08 627
论文名称：Densely Connected Convolutional Networks（CVPR 2017, Best Paper Award） 论文链接：https://arxiv.org/pdf/1608.06993.pdf 源码链接：https://github.com/liuzhuang13/DenseNet caffe版源码： https://github.com/liuzhuang...
Caffe 运行平台支持DenseNet模型
喜欢打酱油的老鸟
03-25 3808
https://www.toutiao.com/a6671617314464465412/ 在计算机视觉领域，卷积神经网络（CNN）已经成为最主流的方法，比如GoogLenet、VGG-19、Incepetion等模型。CNN史上的一个里程碑事件是ResNet模型的出现，ResNet可以训练出更深的CNN模型，从而实现更高的准确度。ResNet模型的核心是通过建立前面层与后面层之...
cudnn-9.0-windows10-x64-v7.6.0.64.zip
09-10
2. **新功能支持**：增加了对新的深度学习模型和操作的支持，比如对ResNeXt、DenseNet等架构的优化。 3. **API稳定性**：此版本的API更加稳定，减少了不兼容性问题，有助于保证软件的长期可维护性。 4. **内存管理...
10大深度学习架构：计算机视觉优秀从业者必备（附代码实现）1
08-03
AlexNet由卷积层、池化层和全连接层构成，利用GPU加速训练，显著提升了训练速度。 论文：《ImageNet Classification with Deep Convolutional Neural Networks》 链接：...
cudnn7.5for cuda 10 win10
04-05
cuDNN 7.5不仅提升了性能，还增加了对新模型架构的支持，如ResNet、DenseNet和MobileNet等，以及对其他深度学习框架的兼容性，如TensorFlow、PyTorch和Caffe等。 安装cuDNN需要以下步骤： 1. 解压下载的压缩包，...
python模型训练框架_深度学习三大框架（对比）
weixin_39864571的博客
11-20 1557
人工智能的浪潮正席卷全球，诸多词汇时刻萦绕在我们的耳边，如人工智能，机器学习，深度学习等。“人工智能”的概念早在1956年就被提出，顾名思义用计算机来构造复杂的，拥有与人类智慧同样本质特性的机器。经过几十年的发展，在2012年后，得益于数据量的上涨，运算力的提升和机器学习算法(深度学习)的出现，人工智能开始大爆发。但目前的科研工作都集中在弱人工智能部分，即让机器具备观察和感知能力，可以一定程度的理...
使用densenet 实现ocr 字符序列训练识别
04-23
本代码实现了从造样本到训练和识别代码 基于densenet 和 ctc的loss 实现
使用Densenet模型训练自己的数据集
热门推荐
YYLin
07-02 1万+
前言： 之前四篇文章分别介绍了如何使用AlexNet、VGG19、ResNet_152 、Inception_V4训练自己数据集，本节将介绍最后一个经典图像识别模型Densenet，Densenet是CVPR2017年的Best Paper, DenseNet脱离了加深网络层数(ResNet)和加宽网络结构(Inception)来提升网络性能的定式思维。它建立的是前面所有层与后面层的密...
Caffe架构的搭建及Caffe架构下DenseNet网络的构建
HenryHan110的博客
02-08 1006
笔者发现国内的教程对Caffe架构的搭建鲜有bug较少的，于是我也来写一篇来做一个备忘，也希望能帮到大家~转载请注明出处。0.软件准备：需要准备哪些软件不是凭空而来的。大家要养成认真看readme的习惯，readme如果强调了版本问题的话那就最好按照文档上的版本来搭建，否则遇到问题再返回来修改版本问题得不偿失。首先，官方的caffe链接在这里：https://github.com/Microsof...
caffe ResNet & DenseNet
sunnygirl's house
05-08 389
ResNet ResNet prototxt 链接https://github.com/antingshen/resnet-protofiles 其中包含ResNet18，ResNet34，ResNet50，ResNet101以及ResNet152 ResNet50，ResNet101以及ResNet152对应的caffe模型 链接：https://pan.baidu.com/...
caffe学习（二）Windows10+Cifar10+DenseNet 训练和预测（C++）详细过程（训练自己的图片也试用）附：问题总结
mqyw29995的博客
02-25 1799
caffe学习（二）Windows10+Cifar10+DenseNet实现训练和预测 前言 论文名称：Densely Connected Convolutional Networks（CVPR 2017, Best Paper Award） 论文链接：https://arxiv.org/pdf/1608.06993.pdf 源码链接：https://github.com/liuzhuang13/...
记录一下caffe1.0里添加densenet
mjiansun的专栏
07-18 887
DenseNet网络是应用由于分类任务中，在目前较好的分类网络ResNets，他们之前存在着很多的不同。下面先来说一说。  先来看一看网络模型结构：  DenseNet主要解决的问题是缓解了消失梯度的问题，增强了特征的传播，促进了特征再利用，大大减少了参数的数量，使网络模型模型进行缩减。  这篇文章中作者主要用了DenseNet-121（k=32），DenseNet-169（k=32），Dense...
使用内存精简版caffe运行densenet
m0_37477175的博客
01-03 3429
有关densenet的相关资料除了查看论文外还可参考博客1以及博客2,本文主要关注densenet的使用。 目前有两个版本的densenet网络配置文件分别对应两个版本的caffe： 论文所带的caffe代码。此网络结构可直接放到一般版本的caffe中运行，但是不能适应太大的图片尺寸，对cifar10中的32*32的图片可正常运行，但是memorysize仍比其他的网络大很多。 适应densenet
DenseNet_161 caffemodel 转 tensorflow 手把手教程
dengzelu的博客
09-26 2755
手把手教你如何将caffemodel转成tensorflow
【语义分割小白教程】手把手教你训练自己的数据集（基于轻量级的FCN-DenseNet）
梁瑛平的博客
04-15 7593
【语义分割小白教程】手把手教你训练自己的数据集（基于轻量级的FCN-DenseNet）0. 任务描述：1. 标注数据：1.1 Labelme 的安装：1.2 Labelme 的使用：1.3 转换标注格式：2. 数据的目录结构：3. 下载源码：4. 下载预训练模型：5. 安装 pytorch：6. 运行训练： 0. 任务描述： 正好这几天有时间，就写一下一个小白教程，用来教大家如何用一个轻量级的 F...
在Windows环境使用Caffe进行模型训练与测试
### Caffe在Windows环境下的模型训练测试知识点详解 #### 1. Caffe框架概述 Caffe是一个深度学习框架，由伯克利AI研究(BAIR)实验室开发，它以表达力强、速度快和模块化著称，特别适合于卷积神经网络（CNNs）的研究...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值