# 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.
#
# For alignment to work, we set:
# (1) input dimension equal to
# $n = 16 * k + 2$, e.g., 306 (for k = 19)
# (2) dimension after 4th max-pooling
# $m = 2 * k + 3$ (41 if k = 19)
# (3) interp dimension equal to
# $m + (m-1) * 7 = 8 * m - 7 = n + 15$, (321 if k = 19)
# (4) Crop 7 pixels at the begin and 8 pixels at the
# end of the interpolated signal to produce the expected $n$
# 

name: "${NET_ID}"

layers {
  name: "data"
  type: IMAGE_SEG_DATA
  top: "data"
  image_data_param {
    root_folder: "/rmt/data/pascal/VOCdevkit/VOC2012"
    source: "voc12/list/${TEST_SET}.txt"
    batch_size: 1
    has_label: false
  }
  transform_param {
    mean_value: 104.008
    mean_value: 116.669
    mean_value: 122.675
    crop_size: 514 #  = 32 * 16 + 2
    mirror: false
  }
  include: { phase: TEST }
}

### 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: 2
    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: 2
    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: 2
    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: 2
    pad: 1
    #stride: 2
    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: "fc6"
  name: "fc6"
  type: CONVOLUTION
  strict_dim: false
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 4096
    pad: 6
    hole: 4
    kernel_size: 4
  }
}
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: 4096
    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_pascal"
  name: "fc8_pascal"
  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: "fc8_pascal"
  top: "fc8_interp"
  name: "fc8_interp"
  type: INTERP
  interp_param {
    zoom_factor: 8
  }
}
layers {
  bottom: "fc8_interp"
  top: "fc8_crop"
  name: "fc8_crop"
  type: PADDING
  padding_param {
    pad_beg: -7
    pad_end: -8
  }
}

layers {
  name: "loss"
  type: SOFTMAX_LOSS
  bottom: "fc8_crop"
  bottom: "label"
  softmaxloss_param {
    #weight_source: "voc12/loss_weight/loss_weight_train.txt"
  }
  include: { phase: TRAIN }
}
layers {
  name: "accuracy"
  type: SEG_ACCURACY
  bottom: "fc8_crop"
  bottom: "label"
  top: "accuracy"
  include: { phase: TRAIN }
}

# layers {
#   name: "im_data"
#   type: IMSHOW
#   bottom: "data"
# }
# layers {
#   name: "im_scores"
#   type: IMSHOW
#   bottom: "fc8_pascal"
# }

layers {
  name: "fc8_crop_mat"
  type: MAT_WRITE
  bottom: "fc8_crop"
  mat_write_param {
    prefix: "${FEATURE_DIR}/${TEST_SET}/fc8/"
    source: "voc12/list/${TEST_SET}_id.txt"
    strip: 0
    period: 1
  }
  include: { phase: TEST }
}