Caffe中卷积层的输出是不同的

时间:2017-05-10 14:55:39

标签: caffe pycaffe

  1. 我用两个输入的caffe编写了一个类似暹罗语的网络。具有第一输入的卷积层的输出总是相同的,而第二输出每次都改变。输入层和卷积层如下:
  2. layer {
      name: "input"
      type: "Input"
      top: "data1"
      top: "data2"
      input_param {
        shape {dim: 1
               dim: 1
               dim: 28
               dim: 28
        }
      }
    }
    layer {
      name: "conv1"
      type: "Convolution"
      bottom: "data1"
      top: "conv1_1"
      convolution_param {
        num_output: 20
        kernel_size: 5
        weight_filler {
          type: "xavier"
        }
      }
    }
    layer {
      name: "conv1"
      type: "Convolution"
      bottom: "data2"
      top: "conv1_2"
      convolution_param {
        num_output: 20
        kernel_size: 5
        bias_term: false
        weight_filler {
          type: "xavier"
        }
      }
    }
    
    1. 我可以用python层构建卷积层吗?如果是的话,如何

0 个答案:

没有答案