Caffe部署中的几个train-test-solver-prototxt-deploy等说明<三>

最新推荐文章于 2020-01-04 13:04:42 发布

海边的第八只螃蟹

最新推荐文章于 2020-01-04 13:04:42 发布

阅读量2.5k

点赞数

分类专栏： caffe

caffe 专栏收录该内容

28 篇文章 0 订阅

订阅专栏

转载地址： http://blog.csdn.net/lg1259156776/article/details/52550865

1:神经网络中，我们通过最小化神经网络来训练网络，所以在训练时最后一层是损失函数层（LOSS），

在测试时我们通过准确率来评价该网络的优劣，因此最后一层是准确率层（ACCURACY）。

但是当我们真正要使用训练好的数据时，我们需要的是网络给我们输入结果，对于分类问题，我们需要获得分类结果，如下右图最后一层我们得到

的是概率，我们不需要训练及测试阶段的LOSS，ACCURACY层了。

下图是能过$CAFFE_ROOT/Python/draw_net.py绘制$CAFFE_ROOT/models/caffe_reference_caffnet/train_val.prototxt , $CAFFE_ROOT/models/caffe_reference_caffnet/deploy.prototxt，分别代表训练时与最后使用时的网络结构。

我们一般将train与test放在同一个.prototxt中，需要在data层输入数据的source，

而在使用时.prototxt只需要定义输入图片的大小通道数据参数即可，如下图所示，分别是

$CAFFE_ROOT/models/caffe_reference_caffnet/train_val.prototxt , $CAFFE_ROOT/models/caffe_reference_caffnet/deploy.prototxt的data层

训练时, solver.prototxt中使用的是rain_val.prototxt

./build/tools/caffe/train -solver ./models/bvlc_reference_caffenet/solver.prototxt

使用上面训练的网络提取特征，使用的网络模型是deploy.prototxt

./build/tools/extract_features.bin models/bvlc_refrence_caffenet.caffemodel models/bvlc_refrence_caffenet/deploy.prototxt

2：

*_train_test.prototxt文件：这是训练与测试网络配置文件

*_deploy.prototxt文件：这是模型构造文件
deploy.prototxt文件书写：
注意在输出层的类型发生了变化一个是SoftmaxWithLoss，另一个是Softmax。另外为了方便区分训练与应用输出，训练是输出时是loss，应用时是prob。

deploy.prototxt文件代码
 
name: "CIFAR10_quick"
 layer {               #该层去掉
  name: "cifar"
   type: "Data"
   top: "data"
   top: "label"
   include {
     phase: TRAIN
   }
   transform_param {
     mean_file: "examples/cifar10/mean.binaryproto"
   }
   data_param {
     source: "examples/cifar10/cifar10_train_lmdb"
     batch_size: 100
     backend: LMDB
   }
 }
 layer {             #该层去掉
  name: "cifar"
   type: "Data"
   top: "data"
   top: "label"
   include {
     phase: TEST
   }
   transform_param {
     mean_file: "examples/cifar10/mean.binaryproto"
   }
   data_param {
     source: "examples/cifar10/cifar10_test_lmdb"
     batch_size: 100
     backend: LMDB
   }
 }
 layer {                        #将下方的weight_filler、bias_filler全部删除
  name: "conv1"
   type: "Convolution"
   bottom: "data"
   top: "conv1"
   param {
     lr_mult: 1
   }
   param {
     lr_mult: 2
   }
   convolution_param {
     num_output: 32
     pad: 2
     kernel_size: 5
     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: 3
     stride: 2
   }
 }
 layer {
   name: "relu1"
   type: "ReLU"
   bottom: "pool1"
   top: "pool1"
 }
 layer {                         #weight_filler、bias_filler删除
  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: 5
     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: 3
     stride: 2
   }
 }
 layer {                         #weight_filler、bias_filler删除
  name: "conv3"
   type: "Convolution"
   bottom: "pool2"
   top: "conv3"
   param {
     lr_mult: 1
   }
   param {
     lr_mult: 2
   }
   convolution_param {
     num_output: 64
     pad: 2
     kernel_size: 5
     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: 3
     stride: 2
   }
 }
 layer {                       #weight_filler、bias_filler删除
  name: "ip1"
   type: "InnerProduct"
   bottom: "pool3"
   top: "ip1"
   param {
     lr_mult: 1
   }
   param {
     lr_mult: 2
   }
   inner_product_param {
     num_output: 64
     weight_filler {
       type: "gaussian"
       std: 0.1
     }
     bias_filler {
       type: "constant"
     }
   }
 }
 layer {                              # weight_filler、bias_filler删除
  name: "ip2"
   type: "InnerProduct"
   bottom: "ip1"
   top: "ip2"
   param {
     lr_mult: 1
   }
   param {
     lr_mult: 2
   }
   inner_product_param {
     num_output: 10
     weight_filler {
       type: "gaussian"
       std: 0.1
     }
     bias_filler {
       type: "constant"
     }
   }
 }
 layer {                                  #将该层删除
  name: "accuracy"
   type: "Accuracy"
   bottom: "ip2"
   bottom: "label"
   top: "accuracy"
   include {
     phase: TEST
   }
 }
 layer {                                 #修改
  name: "loss"       #---loss  修改为  prob
   type: "SoftmaxWithLoss"             # SoftmaxWithLoss 修改为 softmax
   bottom: "ip2"
   bottom: "label"          #去掉
  top: "loss"
 }