deeplab v1的感受野

最新推荐文章于 2022-11-19 11:35:07 发布

dadaHaHa1234

最新推荐文章于 2022-11-19 11:35:07 发布

阅读量414

点赞数

文章标签：感受野空洞卷积 deeplabv1

本文链接：https://blog.csdn.net/qq_32425195/article/details/102552450

版权

基于vgg16的deeplab v1的感受野与原始的vgg16的感受野的计算：

deeplabv1为了获得更大的特征图，保留更多的信息，去掉了后面两个池化层，同时为了保证感受野，所以使用了空洞卷积。

其中，deeplab v1的train.prototxt的如下,在该train.prototxt中，pooling层并不是直接去掉，而是换成stride的pool层：

# VGG 16-layer network convolutional finetuning
# Network modified to have smaller receptive field (128 pixels)
# and smaller stride (8 pixels) when run in convolutional mode.
#
# In this model we also change max pooling size in the first 4 layers
# from 2 to 3 while retaining stride = 2
# which makes it easier to exactly align responses at different layers.
#
# For alignment to work, we set (we choose 32x so as to be able to evaluate
# the model for all different subsampling sizes):
# (1) input dimension equal to
# $n = 32 * k - 31$, e.g., 321 (for k = 11)
# Dimension after pooling w. subsampling:
# (16 * k - 15); (8 * k - 7); (4 * k - 3); (2 * k - 1); (k).
# For k = 11, these translate to
#           161;          81;          41;          21;  11
# 

name: "vgg128_noup"

layers {
  name: "data"
  type: IMAGE_SEG_DATA
  top: "data"
  top: "label"
  image_data_param {
    root_folder: "/media/ali/VOCdevkit/VOC2012"
    source: "voc12/list/train_aug.txt"
    label_type: PIXEL
    batch_size: 30
    shuffle: true
  }
  transform_param {
    mean_value: 104.008
    mean_value: 116.669
    mean_value: 122.675
    crop_size: 321
    mirror: true
  }
  include: { phase: TRAIN }
}

### NETWORK ###

layers {
  bottom: "data"
  top: "conv1_1"
  name: "conv1_1"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv1_1"
  top: "conv1_1"
  name: "relu1_1"
  type: RELU
}
layers {
  bottom: "conv1_1"
  top: "conv1_2"
  name: "conv1_2"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv1_2"
  top: "conv1_2"
  name: "relu1_2"
  type: RELU
}
layers {
  bottom: "conv1_2"
  top: "pool1"
  name: "pool1"
  type: POOLING
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
    pad: 1
  }
}
layers {
  bottom: "pool1"
  top: "conv2_1"
  name: "conv2_1"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv2_1"
  top: "conv2_1"
  name: "relu2_1"
  type: RELU
}
layers {
  bottom: "conv2_1"
  top: "conv2_2"
  name: "conv2_2"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv2_2"
  top: "conv2_2"
  name: "relu2_2"
  type: RELU
}
layers {
  bottom: "conv2_2"
  top: "pool2"
  name: "pool2"
  type: POOLING
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
    pad: 1
  }
}
layers {
  bottom: "pool2"
  top: "conv3_1"
  name: "conv3_1"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv3_1"
  top: "conv3_1"
  name: "relu3_1"
  type: RELU
}
layers {
  bottom: "conv3_1"
  top: "conv3_2"
  name: "conv3_2"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv3_2"
  top: "conv3_2"
  name: "relu3_2"
  type: RELU
}
layers {
  bottom: "conv3_2"
  top: "conv3_3"
  name: "conv3_3"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv3_3"
  top: "conv3_3"
  name: "relu3_3"
  type: RELU
}
layers {
  bottom: "conv3_3"
  top: "pool3"
  name: "pool3"
  type: POOLING
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
    pad: 1
  }
}
layers {
  bottom: "pool3"
  top: "conv4_1"
  name: "conv4_1"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv4_1"
  top: "conv4_1"
  name: "relu4_1"
  type: RELU
}
layers {
  bottom: "conv4_1"
  top: "conv4_2"
  name: "conv4_2"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv4_2"
  top: "conv4_2"
  name: "relu4_2"
  type: RELU
}
layers {
  bottom: "conv4_2"
  top: "conv4_3"
  name: "conv4_3"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv4_3"
  top: "conv4_3"
  name: "relu4_3"
  type: RELU
}
layers {
  bottom: "conv4_3"
  top: "pool4"
  name: "pool4"
  type: POOLING
  pooling_param {
    pool: MAX
    kernel_size: 3
    pad: 1
    stride: 1
  }
}
layers {
  bottom: "pool4"
  top: "conv5_1"
  name: "conv5_1"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 512
    #pad: 1
    pad: 2
    hole: 2
    kernel_size: 3
  }
}
layers {
  bottom: "conv5_1"
  top: "conv5_1"
  name: "relu5_1"
  type: RELU
}
layers {
  bottom: "conv5_1"
  top: "conv5_2"
  name: "conv5_2"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 512
    #pad: 1
    pad: 2
    hole: 2
    kernel_size: 3
  }
}
layers {
  bottom: "conv5_2"
  top: "conv5_2"
  name: "relu5_2"
  type: RELU
}
layers {
  bottom: "conv5_2"
  top: "conv5_3"
  name: "conv5_3"
  type: CONVOLUTION
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 512
    #pad: 1
    pad: 2
    hole: 2
    kernel_size: 3
  }
}
layers {
  bottom: "conv5_3"
  top: "conv5_3"
  name: "relu5_3"
  type: RELU
}
layers {
  bottom: "conv5_3"
  top: "pool5"
  name: "pool5"
  type: POOLING
  pooling_param {
    pool: MAX
    #kernel_size: 2
    #stride: 2
    kernel_size: 3
    stride: 1
    pad: 1
  }
}

layers {
  bottom: "pool5"
  top: "pool5a"
  name: "pool5a"
  type: POOLING
  pooling_param {
    pool: AVE
    kernel_size: 3
    stride: 1
    pad: 1
  }
}

layers {
  bottom: "pool5a"
  top: "fc6"
  name: "fc6"
  type: CONVOLUTION
#  strict_dim: false
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 1024
    pad: 12
    hole: 12
    kernel_size: 3
  }
}
layers {
  bottom: "fc6"
  top: "fc6"
  name: "relu6"
  type: RELU
}
layers {
  bottom: "fc6"
  top: "fc6"
  name: "drop6"
  type: DROPOUT
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  bottom: "fc6"
  top: "fc7"
  name: "fc7"
  type: CONVOLUTION
#  strict_dim: false
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 1024
    kernel_size: 1
  }
}
layers {
  bottom: "fc7"
  top: "fc7"
  name: "relu7"
  type: RELU
}
layers {
  bottom: "fc7"
  top: "fc7"
  name: "drop7"
  type: DROPOUT
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  bottom: "fc7"
  top: "fc8_voc12"
  name: "fc8_voc12"
  type: CONVOLUTION
#  strict_dim: false
  blobs_lr: 10
  blobs_lr: 20
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 21
    kernel_size: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}

layers {
  bottom: "label"
  top: "label_shrink"
  name: "label_shrink"
  type: INTERP
  interp_param {
    shrink_factor: 8
    pad_beg: 0
    pad_end: 0
  }
}
layers {
  name: "loss"
  type: SOFTMAX_LOSS
  bottom: "fc8_voc12"
  bottom: "label_shrink"
  softmaxloss_param {
    #weight_source: "voc12/loss_weight/loss_weight_train.txt"
    ignore_label: 255
  }
  include: { phase: TRAIN }
}
layers {
  name: "accuracy"
  type: SEG_ACCURACY
  bottom: "fc8_voc12"
  bottom: "label_shrink"
  top: "accuracy"
  seg_accuracy_param {
    ignore_label: 255
  } 
}