如何理解SegNet的上采样层

时间：2016-09-29 07:23:47

标签： computer-vision neural-network deep-learning caffe image-segmentation

我注意到SegNet中有上采样层，它自己的图像是480 * 360，当我想使用我的图像（565 * 584）时，我遇到以下错误：

I0929 03:58:06.238135 22750 net.cpp:368] upsample4 -> pool4_D
I0929 03:58:06.238142 22750 net.cpp:120] Setting up upsample4
F0929 03:58:06.238164 22750 upsample_layer.cpp:63] Check failed: bottom[0]->height() == bottom[1]->height() (38 vs. 37)

这是定义：

layer {
  name: "upsample4"
  type: "Upsample"
  bottom: "conv5_1_D"
  top: "pool4_D"
  bottom: "pool4_mask"
  upsample_param {
    scale: 2
    upsample_w: 60
    upsample_h: 45
  }
}

我想我应该更改upsample_w和upsample_h，但我不知道确切的价值。任何人都可以告诉我scale upsample_w之间的关系upsample_h和图片大小或如何计算。

网络的整个定义：segnet_train.prototxt 

name: "VGG_ILSVRC_16_layer"
layer {
  name: "data"
  type: "DenseImageData"
  top: "data"
  top: "label"
  dense_image_data_param {
    source: "/home/zhaimo/SegNet/CamVid/mytrain.txt"    # Change this to the absolute path to your data file
    batch_size: 4               # Change this number to a batch size that will fit on your GPU
    shuffle: true
  }
}
layer {
  bottom: "data"
  top: "conv1_1"
  name: "conv1_1"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 64
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv1_1"
  top: "conv1_1"
  name: "conv1_1_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv1_1"
  top: "conv1_1"
  name: "relu1_1"
  type: "ReLU"
}
layer {
  bottom: "conv1_1"
  top: "conv1_2"
  name: "conv1_2"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 64
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv1_2"
  top: "conv1_2"
  name: "conv1_2_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv1_2"
  top: "conv1_2"
  name: "relu1_2"
  type: "ReLU"
}
layer {
  bottom: "conv1_2"
  top: "pool1"
  top: "pool1_mask"
  name: "pool1"
  type: "Pooling"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  bottom: "pool1"
  top: "conv2_1"
  name: "conv2_1"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 128
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv2_1"
  top: "conv2_1"
  name: "conv2_1_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv2_1"
  top: "conv2_1"
  name: "relu2_1"
  type: "ReLU"
}
layer {
  bottom: "conv2_1"
  top: "conv2_2"
  name: "conv2_2"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 128
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv2_2"
  top: "conv2_2"
  name: "conv2_2_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv2_2"
  top: "conv2_2"
  name: "relu2_2"
  type: "ReLU"
}
layer {
  bottom: "conv2_2"
  top: "pool2"
  top: "pool2_mask"
  name: "pool2"
  type: "Pooling"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  bottom: "pool2"
  top: "conv3_1"
  name: "conv3_1"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 256
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv3_1"
  top: "conv3_1"
  name: "conv3_1_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv3_1"
  top: "conv3_1"
  name: "relu3_1"
  type: "ReLU"
}
layer {
  bottom: "conv3_1"
  top: "conv3_2"
  name: "conv3_2"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 256
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv3_2"
  top: "conv3_2"
  name: "conv3_2_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv3_2"
  top: "conv3_2"
  name: "relu3_2"
  type: "ReLU"
}
layer {
  bottom: "conv3_2"
  top: "conv3_3"
  name: "conv3_3"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 256
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv3_3"
  top: "conv3_3"
  name: "conv3_3_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv3_3"
  top: "conv3_3"
  name: "relu3_3"
  type: "ReLU"
}
layer {
  bottom: "conv3_3"
  top: "pool3"
  top: "pool3_mask"
  name: "pool3"
  type: "Pooling"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  bottom: "pool3"
  top: "conv4_1"
  name: "conv4_1"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv4_1"
  top: "conv4_1"
  name: "conv4_1_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv4_1"
  top: "conv4_1"
  name: "relu4_1"
  type: "ReLU"
}
layer {
  bottom: "conv4_1"
  top: "conv4_2"
  name: "conv4_2"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv4_2"
  top: "conv4_2"
  name: "conv4_2_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv4_2"
  top: "conv4_2"
  name: "relu4_2"
  type: "ReLU"
}
layer {
  bottom: "conv4_2"
  top: "conv4_3"
  name: "conv4_3"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv4_3"
  top: "conv4_3"
  name: "conv4_3_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv4_3"
  top: "conv4_3"
  name: "relu4_3"
  type: "ReLU"
}
layer {
  bottom: "conv4_3"
  top: "pool4"
  top: "pool4_mask"
  name: "pool4"
  type: "Pooling"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  bottom: "pool4"
  top: "conv5_1"
  name: "conv5_1"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv5_1"
  top: "conv5_1"
  name: "conv5_1_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv5_1"
  top: "conv5_1"
  name: "relu5_1"
  type: "ReLU"
}
layer {
  bottom: "conv5_1"
  top: "conv5_2"
  name: "conv5_2"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv5_2"
  top: "conv5_2"
  name: "conv5_2_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv5_2"
  top: "conv5_2"
  name: "relu5_2"
  type: "ReLU"
}
layer {
  bottom: "conv5_2"
  top: "conv5_3"
  name: "conv5_3"
  type: "Convolution"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    weight_filler {
      type: "msra"
    }
    bias_filler {
      type: "constant"
    }
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  bottom: "conv5_3"
  top: "conv5_3"
  name: "conv5_3_bn"
  type: "BN"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 1
    decay_mult: 0
  }
  bn_param {
    scale_filler {
      type: "constant"
      value: 1
    }
    shift_filler {
      type: "constant"
      value: 0.001
    }
 }
}
layer {
  bottom: "conv5_3"
  top: "conv5_3"
  name: "relu5_3"
  type: "ReLU"
}
layer {
  bottom: "conv5_3"
  top: "pool5"
  top: "pool5_mask"
  name: "pool5"
  type: "Pooling"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "upsample5"
  type: "Upsample"
  bottom: "pool5"
  top: "pool5_D"
  bottom: "pool5_mask"
  upsample_param {
    scale: 2
     upsample_w: 30
     upsample_h: 23
  }
}
....(The rest is omitted)

1 个答案:

答案 0 :(得分：0)

您应该更改upsample_w和upsample_h。 每个Pool layer都会降低你的图像X2。因此，您应该计算您拥有的图层数量，然后根据图片的大小计算upsample。

相关问题
最新问题