【神經網絡與深度學習】Caffe部署中的幾個train-test-solver-prototxt-deploy等說明

時間  2019-11-13
標籤 神經網絡與深度學習 caffe 部署 幾個 train test solver prototxt deploy 說明 简体版
原文   原文鏈接

一，train_val.prototxtcss

複製代碼 
name: "CIFAR10_quick"
layer {
  name: "cifar"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    # mirror: true
    # mean_file: "examples/cifar10/mean.binaryproto"uu
    mean_file: "myself/00b/00bmean.binaryproto" 
  }
  data_param {
    # source: "examples/cifar10/cifar10_train_lmdb"
    source: "myself/00b/00b_train_lmdb"
    batch_size: 50
    backend: LMDB
  }
}
layer {
  name: "cifar"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    # mean_file: "examples/cifar10/mean.binaryproto"
    mean_file: "myself/00b/00bmean.binaryproto"
  }
  data_param {
    # source: "examples/cifar10/cifar10_test_lmdb"
    source: "myself/00b/00b_val_lmdb"
    batch_size: 50
    backend: LMDB
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 32
    # pad: 1
    kernel_size: 4
    stride: 1
    weight_filler {
      type: "gaussian"
      std: 0.0001
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "pool1"
  top: "pool1"
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 32
    # pad: 2
    kernel_size: 4
    stride: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: AVE
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 32
    # pad: 2
    kernel_size: 4
    stride: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "pool3"
  type: "Pooling"
  bottom: "conv3"
  top: "pool3"
  pooling_param {
    pool: AVE
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "pool3"
  top: "conv4"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 32
    # pad: 2
    kernel_size: 4
    stride: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "pool4"
  type: "Pooling"
  bottom: "conv4"
  top: "pool4"
  pooling_param {
    pool: AVE
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool4"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 200
    weight_filler {
      type: "gaussian"
      std: 0.1
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 3
    weight_filler {
      type: "gaussian"
      std: 0.1
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "ip2"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip2"
  bottom: "label"
  top: "loss"
}
複製代碼

二，solver.prototxthtml

複製代碼 
# reduce the learning rate after 8 epochs (4000 iters) by a factor of 10

# The train/test net protocol buffer definition
net: "myself/00b/train_val.prototxt"
# test_iter specifies how many forward passes the test should carry out.
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
# covering the full 10,000 testing images.
test_iter: 10
# Carry out testing every 500 training iterations.
test_interval: 70
# The base learning rate, momentum and the weight decay of the network.
base_lr: 0.001
momentum: 0.9
weight_decay: 0.004
# The learning rate policy
lr_policy: "fixed"
# lr_policy: "step"
gamma: 0.1
stepsize: 100
# Display every 100 iterations
display: 10
# The maximum number of iterations
max_iter: 2000
# snapshot intermediate results
# snapshot: 3000
# snapshot_format: HDF5
 snapshot_prefix: "myself/00b/00b"
# solver mode: CPU or GPU
solver_mode: CPU
複製代碼

三，deploy.prototxtwindows

複製代碼 
name: "CIFAR10_quick"
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 1 dim: 3 dim: 101 dim: 101 } }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  convolution_param {
    num_output: 32
    kernel_size: 4
    stride: 1
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  convolution_param {
    num_output: 32
    kernel_size: 4
    stride: 1
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3"
  convolution_param {
    num_output: 32
    kernel_size: 4
    stride: 1
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "pool3"
  type: "Pooling"
  bottom: "conv3"
  top: "pool3"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "pool3"
  top: "conv4"
  convolution_param {
    num_output: 32
    kernel_size: 4
    stride: 1
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "pool4"
  type: "Pooling"
  bottom: "conv4"
  top: "pool4"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool4"
  top: "ip1"
  inner_product_param {
    num_output: 200
  }
}
layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  inner_product_param {
    num_output: 3
  }
}
layer {
  #name: "loss"

  name: "prob"
  type: "Softmax" 
  bottom: "ip2"
  top: "prob"

  #top: "loss"
}
複製代碼

參考一：網絡

模型就用程序自帶的caffenet模型，位置在 models/bvlc_reference_caffenet/文件夾下, 將須要的兩個配置文件，複製到myfile文件夾內ide

複製代碼 
# sudo cp models/bvlc_reference_caffenet/solver.prototxt examples/myfile/ # sudo cp models/bvlc_reference_caffenet/train_val.prototxt examples/myfile/

修改train_val.protxt，只須要修改兩個階段的data層就能夠了，其它能夠不用管。學習

 
  
 
   
 
    複製代碼 
   
 
   
 
    複製代碼 
   
 
   
name: "CaffeNet" layer { name: "data" type: "Data" top: "data" top: "label" include { phase: TRAIN } transform_param { mirror: true crop_size: 227 mean_file: "examples/myfile/mean.binaryproto" } data_param { source: "examples/myfile/img_train_lmdb" batch_size: 256 backend: LMDB } } layer { name: "data" type: "Data" top: "data" top: "label" include { phase: TEST } transform_param { mirror: false crop_size: 227 mean_file: "examples/myfile/mean.binaryproto" } data_param { source: "examples/myfile/img_test_lmdb" batch_size: 50 backend: LMDB } }
 
   
 
    複製代碼 
   
 
  
 
  
 
 
  
實際上就是修改兩個data layer的mean_file和source這兩個地方，其它都沒有變化 。測試
 
  
修改其中的solver.prototxtui
 
  
 
   
# sudo vi examples/myfile/solver.prototxt
 
  
 
  
 
   
 
    複製代碼 
   
 
   
 
    複製代碼 
   
 
   
net: "examples/myfile/train_val.prototxt" test_iter: 2 test_interval: 50 base_lr: 0.001 lr_policy: "step" gamma: 0.1 stepsize: 100 display: 20 max_iter: 500 momentum: 0.9 weight_decay: 0.005 solver_mode: GPU
 
   
 
    複製代碼 
   
 
   
 
    複製代碼 
   
 
  
 
  
100個測試數據，batch_size爲50，所以test_iter設置爲2，就能全cover了。在訓練過程當中，調整學習率，逐步變小。google
 
  
 
   複製代碼 
  
 
 
 
 
 參考二：spa
 
 
 前面作好了lmdb和均值文件，下面以Googlenet爲例修改網絡並訓練模型。
 
 
  
 
 
 咱們將caffe-master\models下的bvlc_googlenet文件夾複製到caffe-master\examples\imagenet下。（由於咱們的lmdb和均值都在這裏，放一塊兒方便些）
 
 
 打開train_val.txt，修改：
 
 
 1.修改data層：
 
 
  
 
 
 
  
     
   
  1.  layer {  
    2.  
   
  2.    name: "data"  
    3.  
   
  3.    type: "Data"  
    4.  
   
  4.    top: "data"  
    5.  
   
  5.    top: "label"  
    6.  
   
  6.    include {  
    7.  
   
  7.      phase: TRAIN  
    8.  
   
  8.    }  
    9.  
   
  9.    transform_param {  
    10.  
   
  10.      mirror: true  
    11.  
   
  11.      crop_size: 224  
    12.  
   
  12.      mean_file: "examples/imagenet/mydata_mean.binaryproto" #均值文件  
    13.  
   
  13.      #mean_value: 104 #這些註釋掉  
    14.  
   
  14.      #mean_value: 117  
    15.  
   
  15.      #mean_value: 123  
    16.  
   
  16.    }  
    17.  
   
  17.    data_param {  
    18.  
   
  18.      source: "examples/imagenet/mydata_train_lmdb" #訓練集的lmdb  
    19.  
   
  19.      batch_size: 32 #根據GPU修改  
    20.  
   
  20.      backend: LMDB  
    21.  
   
  21.    }  
    22.  
   
  22.  }  
    23.  
  
 
 
 
 
 
 
 
 
  
     
   
  1.  layer {  
    2.  
   
  2.    name: "data"  
    3.  
   
  3.    type: "Data"  
    4.  
   
  4.    top: "data"  
    5.  
   
  5.    top: "label"  
    6.  
   
  6.    include {  
    7.  
   
  7.      phase: TEST  
    8.  
   
  8.    }  
    9.  
   
  9.    transform_param {  
    10.  
   
  10.      mirror: false  
    11.  
   
  11.      crop_size: 224  
    12.  
   
  12.      mean_file: "examples/imagenet/mydata_mean.binaryproto" #均值文件  
    13.  
   
  13.      #mean_value: 104  
    14.  
   
  14.      #mean_value: 117  
    15.  
   
  15.      #mean_value: 123  
    16.  
   
  16.    }  
    17.  
   
  17.    data_param {  
    18.  
   
  18.      source: "examples/imagenet/mydata_val_lmdb" #驗證集lmdb  
    19.  
   
  19.      batch_size: 50 #和solver中的test_iter相乘約等於驗證集大小  
    20.  
   
  20.      backend: LMDB  
    21.  
   
  21.    }  
    22.  
   
  22.  }  
    23.  
  
 
 
 
 
 
 
 
 2.修改輸出：
 
 
 因爲Googlenet有三個輸出，因此改三個地方，其餘網絡通常只有一個輸出，則改一個地方便可。
 
 
 若是是微調，那麼輸出層的層名也要修改。（參數根據層名來初始化，因爲輸出改了，該層參數就不對應了，所以要更名）
 
 
 
 
 
 
layer {
  name: "loss1/classifier"
  type: "InnerProduct"
  bottom: "loss1/fc"
  top: "loss1/classifier"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1000 #改爲你的數據集類別數
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
 
 
 
 
 
 
layer {
  name: "loss2/classifier"
  type: "InnerProduct"
  bottom: "loss2/fc"
  top: "loss2/classifier"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1000 #改爲你的數據集類別數
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
 
 
 
 
 
 
layer {
  name: "loss3/classifier"
  type: "InnerProduct"
  bottom: "pool5/7x7_s1"
  top: "loss3/classifier"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1000 #改爲你的數據集類別數
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
 
 
 3.打開deploy.prototxt，修改：
 
 
 
 
 
 
layer {
  name: "loss3/classifier"
  type: "InnerProduct"
  bottom: "pool5/7x7_s1"
  top: "loss3/classifier"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1000 #改爲你的數據集類別數
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
 
 
 若是是微調，該層層名和train_val.prototxt修改一致。
 
 
 接着，打開solver，修改：
 
 
 
 
 
 
net: "examples/imagenet/bvlc_googlenet/train_val.prototxt" #路徑不要錯
test_iter: 1000 #前面已說明該值
test_interval: 4000 #迭代多少次測試一次
test_initialization: false
display: 40
average_loss: 40
base_lr: 0.01
lr_policy: "step"
stepsize: 320000 #迭代多少次改變一次學習率
gamma: 0.96
max_iter: 10000000 #迭代次數
momentum: 0.9
weight_decay: 0.0002
snapshot: 40000
snapshot_prefix: "examples/imagenet/bvlc_googlenet" #生成的caffemodel保存在imagenet下，形如bvlc_googlenet_iter_***.caffemodel
solver_mode: GPU

 
 
 這時，咱們回到caffe-master\examples\imagenet下，打開train_caffenet.sh，修改：
 
 
 (若是是微調，在腳本里加入-weights **/**/**.caffemodel便可，即用來微調的caffemodel路徑)
 
 
 
  
 
   [plain] 
  
 
 
 
 
#!/usr/bin/env sh

./build/tools/caffe train \
    -solver examples/imagenet/bvlc_googlenet/solver.prototxt -gpu 0

 
 
 （若是有多個GPU，可自行選擇） 而後，在caffe-master下執行改腳本便可開始訓練:$caffe-master ./examples/imagenet/train_caffenet.sh
 
 
 訓練獲得的caffemodel就能夠用來作圖像分類了，此時，須要（1）獲得的labels.txt，（2）獲得的mydata_mean.binaryproto，（3）獲得的caffemodel以及已經修改過的deploy.prototxt，共四個文件，具體過程看：http://blog.csdn.net/sinat_30071459/article/details/50974695
 
 
 參考三：
 
 
 *_train_test.prototxt,*_deploy.prototxt,*_slover.prototxt文件編寫時注意
 
 
 一、*_train_test.prototxt文件
 
 
 這是訓練與測試網絡配置文件
 
 
 （1）在數據層中 參數include{
 
 
                                  phase：TRAIN/TEST
 
 
                              }
 
 
 TRAIN與TEST不能有「...」不然會報錯，還好提示信息裏，會提示哪一行出現了問題，以下圖：
 
 
 
 
 
 數字8就表明配置文件的第8行出現了錯誤
 
 
 （2）卷積層和全鏈接層類似：卷積層（Convolution），全鏈接層（InnerProduct，容易翻譯成內積層）類似處有兩個【1】：都有兩個param{lr_mult：1
 
 
                                            decay_mult：1                            
 
 
                                }
 
 
                              param{lr_mult： 2
 
 
                                         decay_mult: 0            
 
 
                               }
 
 
 【2】：convolution_param{}與inner_product_param{}裏面的參數類似，甚至相同
 
 
 今天有事，明天再續！
 
 
 續上！
 
 
 （3）平均值文件*_mean.binaryproto要放在transform_param{}裏，訓練與測試數據集放在data_param{}裏
 
 
 2.*_deploy.prototxt文件
 
 
 【1】*_deploy.prototxt文件的構造和*_train_test.prototxt文件的構造稍有不一樣首先沒有test網絡中的test模塊，只有訓練模塊
 
 
 【2】數據層的寫法和原來也有不一樣，更加簡潔：
 
 
 input: "data" input_dim: 1 input_dim: 3 input_dim: 32 input_dim: 32
 
 
 注意紅色部分，那是數據層的名字，沒有這個的話，第一卷積層沒法找到數據，我一開始沒有加這句就報錯。下面的四個參數有點相似batch_size（1,3,32,32）裏四個參數
 
 
 【3】卷積層和全鏈接層中weight_filler{}與bias_filler{}兩個參數不用再填寫，應爲這兩個參數的值，由已經訓練好的模型*.caffemodel文件提供
 
 
 【4】輸出層的變化（1）沒有了test模塊測試精度（2）輸出層
 
 
 *_train_test.prototxt文件：
 
 
 layer{   name: "loss"   type: "SoftmaxWithLoss"#注意此處與下面的不一樣   bottom: "ip2"   bottom: "label"#注意標籤項在下面沒有了，由於下面的預測屬於哪一個標籤，所以不能提供標籤   top: "loss" }
 
 
 *_deploy.prototxt文件：
 
 
 layer {   name: "prob"   type: "Softmax"   bottom: "ip2"   top: "prob" }
 
 
 ***注意在兩個文件中輸出層的類型都發生了變化一個是SoftmaxWithLoss，另外一個是Softmax。另外爲了方便區分訓練與應用輸出，訓練是輸出時是loss，應用時是prob。
 
 
 三、*_slover.prototxt
 
 
 net: "test.prototxt" #訓練網絡的配置文件 test_iter: 100 #test_iter 指明在測試階段有多上個前向過程（也就是有多少圖片）被執行。 在MNIST例子裏，在網絡配置文件裏已經設置test網絡的batch size=100，這裏test_iter 設置爲100，那在測試階段共有100*100=10000 圖片被處理 test_interval: 500 #每500次訓練迭代後，執行一次test base_lr: 0.01 #學習率初始化爲0.01 momentum：0.9 #u=0.9 weight_decay:0.0005 # lr_policy: "inv" gamma: 0.0001 power: 0.75 #以上三個參數都和下降學習率有關，詳細的學習策略和計算公式見下面 // The learning rate decay policy. The currently implemented learning rate  
 
 
 // policies are as follows:  
 
 
 //    - fixed: always return base_lr.  
 
 
 //    - step: return base_lr * gamma ^ (floor(iter / step))  
 
 
 //    - exp: return base_lr * gamma ^ iter
 
 
 //    - inv: return base_lr * (1 + gamma * iter) ^ (- power)  
 
 
 //    - multistep: similar to step but it allows non uniform steps defined by  
 
 
 //      stepvalue  
 
 
 //    - poly: the effective learning rate follows a polynomial decay, to be  
 
 
 //      zero by the max_iter. return base_lr (1 - iter/max_iter) ^ (power)  
 
 
 //    - sigmoid: the effective learning rate follows a sigmod decay  
 
 
 //      return base_lr ( 1/(1 + exp(-gamma * (iter - stepsize))))  
 
 
 // where base_lr, max_iter, gamma, step, stepvalue and power are defined  
 
 
 // in the solver parameter protocol buffer, and iter is the current iteration. display:100 #每100次迭代，顯示結果 snapshot: 5000 #每5000次迭代，保存一次快照 snapshot_prefix: "path_prefix" #快照保存前綴：更準確的說是快照保存路徑+前綴，應爲文件名後的名字是固定的 solver_mode:GPU #選擇解算器是用cpu仍是gpu
 
 
 批處理文件編寫：
 
 
 F:/caffe/caffe-windows-master/bin/caffe.exe train --solver=C:/Users/Administrator/Desktop/caffe_test/cifar-10/cifar10_slover_prototxt --gpu=all pause
 
 
 參考四：
 
 
  
 
 

   06 
 
 
 
  
 
 
 
  原 
 
 
 
  
 
 
 將train_val.prototxt 轉換成deploy.prototxt
 
 
  
 
 
 
  
                         
 
  
                                                                                                                                              
 
 
 
 
  
 
 
 
  
1.刪除輸入數據（如：type:data...inckude{phase: TRAIN}），而後添加一個數據維度描述。
 
  
 
 
  
 
   
     
    
  1.  input: "data"   
    2.  
    
  2.  input_dim: 1   
    3.  
    
  3.  input_dim: 3   
    4.  
    
  4.  input_dim: 224   
    5.  
    
  5.  input_dim: 224  
    6.  
    
  6.  force_backward: true  
    7.  
   
 
  
 
  
input: "data" 
input_dim: 1 
input_dim: 3 
input_dim: 224 
input_dim: 224
force_backward: true
 
  
 
 
  
 
  
 
 
  
2.移除最後的「loss」 和「accuracy」 層，加入「prob」層。
 
  
 
 
  
 
   
     
    
  1.  layers {  
    2.  
    
  2.    name: "prob"  
    3.  
    
  3.    type: SOFTMAX  
    4.  
    
  4.    bottom: "fc8"  
    5.  
    
  5.    top: "prob"  
    6.  
    
  6.  }  
    7.  
   
 
   
 
     
   
 
  
 
  
layers {
  name: "prob"
  type: SOFTMAX
  bottom: "fc8"
  top: "prob"
}
若是train_val文件中還有其餘的預處理層，就稍微複雜點。以下，在'data'層，在‘data’層和‘conv1’層 
  (with bottom:」data」  / top:」conv1″). 插入一個層來計算輸入數據的均值。 
  
 
 
  
 
 
  
 
   
     
    
  1.  layer {  
    2.  
    
  2.  name: 「mean」  
    3.  
    
  3.  type: 「Convolution」  
    4.  
    
  4.  <strong>bottom: 「data」  
    5.  
    
  5.  top: 「data」</strong>  
    6.  
    
  6.  param {  
    7.  
    
  7.  lr_mult: 0  
    8.  
    
  8.  decay_mult: 0  
    9.  
    
  9.  }  
    10.  
    
  10.    
    11.  
    
  11.  …}  
    12.  
   
 
  
 
  
<span style="line-height: 1.5; margin: 0px; padding: 0px; border: 0px currentcolor; vertical-align: baseline;">在deploy.prototxt文件中，「mean」 層必須保留，只是容器改變，相應的‘conv1’也要改變<span style="line-height: 24px; color: rgb(68, 68, 68); font-family: "Open Sans", Helvetica, Arial, sans-serif; font-size: 14px;"> ( <span style="margin: 0px; padding: 0px; border: 0px currentcolor; vertical-align: baseline;"><span style="line-height: 1.5; margin: 0px; padding: 0px; border: 0px currentcolor; vertical-align: baseline;">bottom:」mean」/ <span style="line-height: 24px; margin: 0px; padding: 0px; border: 0px currentcolor; vertical-align: baseline;">top:」conv1″ )。</span></span></span></span></span>
 
  
 
   
     
    
  1.  layer {  
    2.  
    
  2.  name: 「mean」  
    3.  
    
  3.  type: 「Convolution」  
    4.  
    
  4.  <strong>bottom: 「data」  
    5.  
    
  5.  top: 「mean「</strong>  
    6.  
    
  6.  param {  
    7.  
    
  7.  lr_mult: 0  
    8.  
    
  8.  decay_mult: 0  
    9.  
    
  9.  }  
    10.  
    
  10.    
    11.  
    
  11.  …}  
    12.  
   
 
  
 
 
  



        

            

        	





    

		

            
相關文章

            

                

                

                    

                

            


            
相關標籤/搜索

            
        


    

        

            

        

        

        
        

        

        

    




	

    





    

    	

    

        每日一句
    

    
    
    	每一个你不满意的现在，都有一个你没有努力的曾经。
    







    

    


    



    

        本站公眾號
    

    

           歡迎關注本站公眾號,獲取更多信息

        
    




    

    




	


	







    

        聯繫我們
        最近搜索
        最新文章
        
        沪ICP备13005482号-10

            MyBatis教程
            SQL 教程
            MySQL教程
            Java 教程
            Thymeleaf 教程
            Hibernate教程
            Spring教程 
            Redis教程