machine-learning - 在 caffe 中可视化卷积核

Question

我一直在关注一个 Caffe 示例来绘制我的 ConvNet 中的卷积核。我在我的内核下方附上了一张图片，但它看起来与示例中的内核完全不同。我已经完全按照示例进行了操作，有人知道可能是什么问题吗？

我的网络是在一组模拟图像（有两个类）上训练的，网络的性能非常好，大约 80% 的测试准确率。

layer {
  name: "input"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mean_file: "/tmp/stage5/mean/mean.binaryproto"
  }
  data_param {
    source: "/tmp/stage5/train/train-lmdb"
    batch_size: 100
    backend: LMDB
  }
}
layer {
  name: "input"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    mean_file: "/tmp/stage5/mean/mean.binaryproto"
  }
  data_param {
    source: "/tmp/stage5/validation/validation-lmdb"
    batch_size: 10
    backend: LMDB
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1.0
  }
  param {
    lr_mult: 2.0
  }
  convolution_param {
    num_output: 40
    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: 3
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool1"
  top: "ip1"
  param {
    lr_mult: 1.0
  }
  param {
    lr_mult: 2.0
  }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  param {
    lr_mult: 1.0
  }
  param {
    lr_mult: 2.0
  }
  inner_product_param {
    num_output: 2
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip2"
  bottom: "label"
  top: "loss"
}

Answer 1

好吧，当您调用 imshow 时，您可能需要将插值参数设置为“无”。你指的是这个吗？

Answer 2

要获得“更平滑”的过滤器，您可以尝试向 conv1 层添加少量 L2 权重衰减 (decay_mult)。

另见http://caffe.berkeleyvision.org/tutorial/layers.html

layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  # learning rate and decay multipliers for the filters
  param { lr_mult: 1 decay_mult: 1 }
  # learning rate and decay multipliers for the biases
  param { lr_mult: 2 decay_mult: 0 }
  convolution_param {
    num_output: 96     # learn 96 filters
    kernel_size: 11    # each filter is 11x11
    stride: 4          # step 4 pixels between each filter application
    weight_filler {
      type: "gaussian" # initialize the filters from a Gaussian
      std: 0.01        # distribution with stdev 0.01 (default mean: 0)
    }
    bias_filler {
      type: "constant" # initialize the biases to zero (0)
      value: 0
    }
  }
}