Caffe，批次之间的操作

Question

由于我有一个基于单个补丁分数的分类器，我想将网络为不同图像生成的预测加在一起。

来自 https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto、Reduction 不支持与上一个轴不同的轴操作。此外，池化操作会产生其输入的平均值，但显然不会影响整个批次。

我已经实现了一个 python 层，但这对于大规模实验来说速度不够快。

有没有办法"sum"，或者更一般地说，使用已有的工具在第一个轴上操作？

Answer 1

是的。你可以。如果你有 N x p x q x r blob 预测，首先使用 Slice (SliceLayer), creating N blobs, each of shape 1 x p x q x r. Then use these N blobs as N bottoms for the eltwise (EltwiseLayer) 层生成单个顶部。

Answer 2

如果您的预测具有维度：N x c（对于 N 和 c 通道的小批量大小），那么您可以将其拼接成 c blob维度 N。您可以将它们输入 Reduction 层。

例如，您将以下内容编写为 Jinja2 模板：

layer {
  name: "pred-slice"
  type: "Slice"
  bottom: "pred"
{%- for num in range(10) %}
  top: "pred-{{ num }}-vector"
{%- endfor %}
  slice_param {
    slice_dim: 1
{%- for num in range(1, 10) %}
    slice_point: {{ num }}
{%- endfor %}
  }
  include {
    phase: TEST
  }
}

{%- for num in range(10) %}
layer {
  name: "pred-{{num}}"
  type: "Reduction"
  bottom: "pred-{{ num }}-vector"
  top: "pred-{{ num }}"
  include {
    phase: TEST
  }
  reduction_param {
    operation: MEAN
  }
}
{%- endfor %}

扩展为：

layer {
  name: "pred-slice"
  type: "Slice"
  bottom: "pred"
  top: "pred-0-vector"
  top: "pred-1-vector"
  top: "pred-2-vector"
  top: "pred-3-vector"
  top: "pred-4-vector"
  top: "pred-5-vector"
  top: "pred-6-vector"
  top: "pred-7-vector"
  top: "pred-8-vector"
  top: "pred-9-vector"
  slice_param {
    slice_dim: 1
    slice_point: 1
    slice_point: 2
    slice_point: 3
    slice_point: 4
    slice_point: 5
    slice_point: 6
    slice_point: 7
    slice_point: 8
    slice_point: 9
  }
  include {
    phase: TEST
  }
}
layer {
  name: "pred-0"
  type: "Reduction"
  bottom: "pred-0-vector"
  top: "pred-0"
  include {
    phase: TEST
  }
  reduction_param {
    operation: MEAN
  }
}
layer {
  name: "pred-1"
  type: "Reduction"
  bottom: "pred-1-vector"
  top: "pred-1"
  include {
    phase: TEST
  }
  reduction_param {
    operation: MEAN
  }
}
layer {
  name: "pred-2"
  type: "Reduction"
  bottom: "pred-2-vector"
  top: "pred-2"
  include {
    phase: TEST
  }
  reduction_param {
    operation: MEAN
  }
}
layer {
  name: "pred-3"
  type: "Reduction"
  bottom: "pred-3-vector"
  top: "pred-3"
  include {
    phase: TEST
  }
  reduction_param {
    operation: MEAN
  }
}
layer {
  name: "pred-4"
  type: "Reduction"
  bottom: "pred-4-vector"
  top: "pred-4"
  include {
    phase: TEST
  }
  reduction_param {
    operation: MEAN
  }
}
layer {
  name: "pred-5"
  type: "Reduction"
  bottom: "pred-5-vector"
  top: "pred-5"
  include {
    phase: TEST
  }
  reduction_param {
    operation: MEAN
  }
}
layer {
  name: "pred-6"
  type: "Reduction"
  bottom: "pred-6-vector"
  top: "pred-6"
  include {
    phase: TEST
  }
  reduction_param {
    operation: MEAN
  }
}
layer {
  name: "pred-7"
  type: "Reduction"
  bottom: "pred-7-vector"
  top: "pred-7"
  include {
    phase: TEST
  }
  reduction_param {
    operation: MEAN
  }
}
layer {
  name: "pred-8"
  type: "Reduction"
  bottom: "pred-8-vector"
  top: "pred-8"
  include {
    phase: TEST
  }
  reduction_param {
    operation: MEAN
  }
}
layer {
  name: "pred-9"
  type: "Reduction"
  bottom: "pred-9-vector"
  top: "pred-9"
  include {
    phase: TEST
  }
  reduction_param {
    operation: MEAN
  }
}

Caffe，批次之间的操作

Caffe, operations among batches

neural-network

deep-learning

caffe

conv-neural-network