如何在张量流中实现caffe反卷积填充?

时间:2019-02-21 15:44:10

标签: tensorflow deep-learning caffe

此层每侧都有填充4个像素,但是在张量流中,它仅具有“ SAME”和“ VALID”填充模式。如何在张量流中实现这一层?

layer {
  name: "conv3"
  type: "Deconvolution"
  bottom: "conv26"
  top: "conv3"
  param {
    lr_mult: 0.1
  }
  param {
    lr_mult: 0.1
  }
  convolution_param {
    num_output: 1
    kernel_size: 9
    stride: 3
    pad: 4
    weight_filler {
      type: "gaussian"
      std: 0.001
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}

1 个答案:

答案 0 :(得分:0)

您可以使用tf.pad进行自定义填充。为每个空间维度填充名称为my_tensor的张量(batch_size, height, width, channels),形状为my_padded_tensor = tf.pad( tensor=my_tensor, paddings=tf.constant([[0, 0,], [4, 4], [4,4], [0,0]], dtype=tf.int32), mode='CONSTANT', constant_values=0 ) ,并且在两个空间的两侧都带有四个零:

{{1}}