如何理解caffe的双线性上采样

Question

caffe‘’doc说

layer {
  name: "upsample", type: "Deconvolution"
  bottom: "{{bottom_name}}" top: "{{top_name}}"
  convolution_param {
    kernel_size: {{2 * factor - factor % 2}} stride: {{factor}}
    num_output: {{C}} group: {{C}}
    pad: {{ceil((factor - 1) / 2.)}}
    weight_filler: { type: "bilinear" } bias_term: false
  }
  param { lr_mult: 0 decay_mult: 0 }
}

我不知道为什么要这样设置kenrel_size、stride和pad？

Answer 1

对于上采样，如果希望调整大小因子为2，则参数应为kernel_size: 4，stride:2，pad:1