CAFFE CIFAR10 MODEL IMAGE 之 cifar10 full sigmoid

最新推荐文章于 2023-04-09 17:32:09 发布

明明可以早点起

最新推荐文章于 2023-04-09 17:32:09 发布

阅读量562

点赞数

分类专栏： deeplearning 文章标签： caffe cifar10 deeplearning 拓扑图

本文链接：https://blog.csdn.net/LIXIAOLONGJIEQUAN/article/details/52727752

版权

deeplearning 专栏收录该内容

19 篇文章 0 订阅

订阅专栏

cifar10 添加sigmoid层后的拓扑文件为：

name: "CIFAR10_full"
layer {
  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: 111
    backend: LMDB
  }
}
layer {
  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: 1000
    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: 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: "Sigmoid1"
  type: "Sigmoid"
  bottom: "pool1"
  top: "Sigmoid1"
}

layer {
  name: "conv2"
  type: "Convolution"
  bottom: "Sigmoid1"
  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: "Sigmoid2"
  type: "Sigmoid"
  bottom: "conv2"
  top: "Sigmoid2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "Sigmoid2"
  top: "pool2"
  pooling_param {
    pool: AVE
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3"
  convolution_param {
    num_output: 64
    pad: 2
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
    }
  }
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 1
  }

}

layer {
  name: "Sigmoid3"
  type: "Sigmoid"
  bottom: "conv3"
  top: "Sigmoid3"
}

layer {
  name: "pool3"
  type: "Pooling"
  bottom: "Sigmoid3"
  top: "pool3"
  pooling_param {
    pool: AVE
    kernel_size: 3
    stride: 2
  }
}

layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool3"
  top: "ip1"
  param {
    lr_mult: 1
    decay_mult: 0
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 10
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "ip1"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip1"
  bottom: "label"
  top: "loss"
}

拓扑图就变为：