如何使用Caffe为NVIDIA-Digits中的MNIST数据集训练自动编码器？

Question

我想在mnist_generic上使用NVIDIA数字中的caffe实现autoencoder。 我根据这里解释的方法制作了数据集： https://github.com/NVIDIA/DIGITS/tree/master/examples/autoencoder

但我不想使用Torch或Tensorflow来构建自动编码器。我想和Caffe一起做。

我使用了caffe中提供的mnist_autoencoder并在DIGITS中运行了它。

但我得到的错误如下：

ERROR: cannot specify two val image data layers

当我删除一个测试层（架构中的第三层）时，我收到了这个错误：

ERROR: Check failed: bottom[0]->count() == bottom[1]->count() (78400 vs. 235200) SIGMOID_CROSS_ENTROPY_LOSS layer inputs must have the same count.

这是自动编码器架构：

name: "MNISTAutoencoder"
layer {
  name: "data"
  type: "Data"
  top: "data"
  include {
    phase: TRAIN
  }
  transform_param {
    scale: 0.0039215684
  }
  data_param {
    batch_size: 100
    backend: LMDB
  }
}
layer {
  name: "data"
  type: "Data"
 top: "data"
 include {
 phase: TEST
 stage: "test-on-train"
 }
 transform_param {
scale: 0.0039215684
 }
data_param {
batch_size: 100
backend: LMDB
  }
}
layer {
  name: "data"
  type: "Data"
  top: "data"
  include {
    phase: TEST
   stage: "test-on-test"
  }
  transform_param {
    scale: 0.0039215684
  }
  data_param {
    batch_size: 100
    backend: LMDB
  }
 }
layer {
  name: "flatdata"
  type: "Flatten"
  bottom: "data"
  top: "flatdata"
}
layer {
  name: "encode1"
  type: "InnerProduct"
  bottom: "data"
  top: "encode1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1000
    weight_filler {
      type: "gaussian"
      std: 1
      sparse: 15
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "encode1neuron"
  type: "Sigmoid"
  bottom: "encode1"
  top: "encode1neuron"
}
layer {
  name: "encode2"
  type: "InnerProduct"
  bottom: "encode1neuron"
  top: "encode2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
   decay_mult: 0
  }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "gaussian"
      std: 1
      sparse: 15
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "encode2neuron"
  type: "Sigmoid"
  bottom: "encode2"
  top: "encode2neuron"
}
layer {
  name: "encode3"
  type: "InnerProduct"
  bottom: "encode2neuron"
  top: "encode3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  inner_product_param {
     num_output: 250
   weight_filler {
      type: "gaussian"
      std: 1
      sparse: 15
    }
    bias_filler {
        type: "constant"
        value: 0
      }
    }
  }
  layer {
    name: "encode3neuron"
    type: "Sigmoid"
    bottom: "encode3"
    top: "encode3neuron"
  }
  layer {
    name: "encode4"
    type: "InnerProduct"
    bottom: "encode3neuron"
    top: "encode4"
    param {
      lr_mult: 1
      decay_mult: 1
    }
    param {
      lr_mult: 1
      decay_mult: 0
    }
    inner_product_param {
      num_output: 30
      weight_filler {
        type: "gaussian"
        std: 1
        sparse: 15
      }
      bias_filler {
        type: "constant"
        value: 0
      }
    }
  }
  layer {
    name: "decode4"
    type: "InnerProduct"
    bottom: "encode4"
    top: "decode4"
    param {
      lr_mult: 1
      decay_mult: 1
    }
    param {
      lr_mult: 1
      decay_mult: 0
    }
    inner_product_param {
      num_output: 250
      weight_filler {
        type: "gaussian"
        std: 1
        sparse: 15
      }
      bias_filler {
        type: "constant"
        value: 0
      }
    }
  }
  layer {
    name: "decode4neuron"
    type: "Sigmoid"
    bottom: "decode4"
    top: "decode4neuron"
  }
  layer {
    name: "decode3"
    type: "InnerProduct"
    bottom: "decode4neuron"
    top: "decode3"
    param {
      lr_mult: 1
      decay_mult: 1
    }
    param {
      lr_mult: 1
      decay_mult: 0
    }
    inner_product_param {
     num_output: 500
      weight_filler {
        type: "gaussian"
        std: 1
        sparse: 15
      }
      bias_filler {
        type: "constant"
        value: 0
      }
    }
  }
  layer {
    name: "decode3neuron"
    type: "Sigmoid"
    bottom: "decode3"
    top: "decode3neuron"
  }
  layer {
    name: "decode2"
    type: "InnerProduct"
    bottom: "decode3neuron"
    top: "decode2"
    param {
      lr_mult: 1
      decay_mult: 1
    }
    param {
      lr_mult: 1
      decay_mult: 0
    }
    inner_product_param {
      num_output: 1000
      weight_filler {
        type: "gaussian"
        std: 1
        sparse: 15
      }
      bias_filler {
        type: "constant"
        value: 0
      }
    }
  }
  layer {
    name: "decode2neuron"
    type: "Sigmoid"
    bottom: "decode2"
    top: "decode2neuron"
  }
  layer {
    name: "decode1"
    type: "InnerProduct"
    bottom: "decode2neuron"
    top: "decode1"
    param {
      lr_mult: 1
      decay_mult: 1
    }
    param {
      lr_mult: 1
      decay_mult: 0
    }
    inner_product_param {
      num_output: 784
      weight_filler {
        type: "gaussian"
        std: 1
        sparse: 15
      }
      bias_filler {
        type: "constant"
        value: 0
      }
    }
  }
  layer {
    name: "loss"
    type: "SigmoidCrossEntropyLoss"
    bottom: "decode1"
    bottom: "flatdata"
    top: "cross_entropy_loss"
    loss_weight: 1
    include {
      phase: TRAIN
    }
  }
  layer {
    name: "decode1neuron"
    type: "Sigmoid"
    bottom: "decode1"
    top: "decode1neuron"
  }
  layer {
    name: "loss"
    type: "EuclideanLoss"
    bottom: "decode1neuron"
    bottom: "flatdata"
    top: "l2_error"
    loss_weight: 0
    include {
      phase: TRAIN
    }
  }

你知道如何在nvidia-digits中使用caffe训练这个mnist自动编码器吗？