Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

@Flipajs, duplication of pad and kernel_size parameters looks confusing but they are correct.

layer {
  name: "conv1_2_H"
  type: "Convolution"
  bottom: "conv1_2_V"
  top: "conv1_2_H"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  convolution_param {
    num_output: 22
    bias_term: true
    pad: 0
    pad: 1
    kernel_size: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"

from caffe.proto:

  // Pad, kernel size, and stride are all given as a single value for equal
  // dimensions in all spatial dimensions, or once per spatial dimension.

There are pad_h and pad_w with kernel_h and kernel_w to define paddings and kernel sizes correspondingly for each dimension. So you can replace an every duplication to corresponding *_h and *_w parameters because OpenCV cannot manage it for now.