--darknet 转战 caffe--

1. darknet的cfg文件转换成caffe的prototxt文件

> 卷积层重写：

# darknet 的cfg文件
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky

# caffe的prototxt书写
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: 3
    stride: 1
    weight_filler {
      type: "gaussian"
      std: 0.0001
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
    name: "batch_norm1"
    type: "BatchNorm"
    bottom: "conv1"
    top: "conv1"
    batch_norm_param {
        use_global_stats: false
    }
    include {
        phase: TRAIN
    }
}
layer {
    name: "batch_norm1"
    type: "BatchNorm"
    bottom: "conv1"
    top: "conv1"
    batch_norm_param {
        use_global_stats: true
    }
    include {
        phase: TEST
    }
}
layer {
    name: "scale1"
    type: "Scale"
    bottom: "conv1"
    top: "conv1"
    scale_param {
        bias_term: true
    }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
  relu_param{
    negative_slope: 0.1
  }
}

• 为什么要分成BatchNorm和Scale两个层: 博客1，博客2，ResNet.prototxt的书写

标签：layer,bottom,DarkNet,param,学习,conv1,Caffe,type,top
来源： https://blog.csdn.net/qipeng_master/article/details/85113415