Caffe(caffe-fast-rcnn)配置Center Loss(其他网络层类似方法)

一、首先是配置CenterLoss
原版的caffe是没有Centerloss这一层的。所以需要手动添加。
参考博客:http://blog.csdn.net/samylee/article/details/76640240
主要配置是一下几个文件:
    src/caffe/proto/caffe.proto
    include/caffe/layers/center_loss_layer.hpp
    src/caffe/layers/center_loss_layer.cpp
    src/caffe/layers/center_loss_layer.cu
1.下载这几个文件:https://github.com/ydwen/caffe-face 上下载caffe-face
从相关路径下吧center_loss_layer.hpp,复制到include/caffe/layers/ 下
吧center_loss_layer.cpp 和center_loss_layer.cu 复制到src/caffe/layers/ 下

2.在原本caffe/src/caffe/proto/caffe.proto 路径下对caffe.proto进行修改:
在message LayerParameter{}中添加如下代码:
optional CenterLossParameter center_loss_param = 147;
(其中147为当前最后一个ID,根据自己的提示来改)

在文档最后加入:
message CenterLossParameter {  
  optional uint32 num_output = 1; // The number of outputs for the layer  
  optional FillerParameter center_filler = 2; // The filler for the centers  
  // The first axis to be lumped into a single inner product computation;  
  // all preceding axes are retained in the output.  
  // May be negative to index from the end (e.g., -1 for the last axis).  
  optional int32 axis = 3 [default = 1];  
}

3.重新编译caffe
make clean
make all -16j
make test -j16
make runtest -j16
make pycaffe -j16
make matcaffe -j16(使用Matlab的话需要)

二、关于CenterLoss的使用
CenterLoss不能单独使用,需要和SoftmaxWithLoss联合使用才行。
例如:将下面的网络复制http://ethereon.github.io/netscope/#/editor  中便可看到网络结构。
name: "LeNet"
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "examples/mnist/mnist_train_lmdb"
    batch_size: 64
    backend: LMDB
  }
}
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "examples/mnist/mnist_test_lmdb"
    batch_size: 100
    backend: LMDB
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 20
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
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"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 50
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool2"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}
layer {
  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: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "ip2"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}

############# softmax loss ###############
layer {
  name: "softmax_loss"
  type: "SoftmaxWithLoss"
  bottom: "ip2"
  bottom: "label"
  top: "softmax_loss"
}
############# center loss ###############
layer {
  name: "center_loss"
  type: "CenterLoss"
  bottom: "ip1"
  bottom: "label"
  top: "center_loss"
  param {
    lr_mult: 1
    decay_mult: 0
  }
  center_loss_param {
    num_output: 10
    center_filler {
      type: "xavier"
    }
  }
  loss_weight: 0.01
}
阅读更多
想对作者说点什么? 我来说一句

没有更多推荐了,返回首页