dongzhuoyao

#
input: "data"
input_dim: 1
input_dim: 3
input_dim: 713
input_dim: 713

layer {
  name: "conv1_1_3x3_s2"
  type: "Convolution"

dongzhuoyao

layer {
  name: "data"
  type: "Python"
  top: "data"
  top: "label"
  python_param {
    module: "voc_layers"
    layer: "SBDDSegDataLayer"
    param_str: "{\'sbdd_dir\': \'../data/sbdd/dataset\', \'seed\': 1337, \'split\': \'train\', \'mean\': (104.00699, 116.66877, 122.67892)}"
  }

dongzhuoyao

layer {
  name: "data"
  type: "Python"
  top: "data"
  top: "label"
  python_param {
    module: "voc_layers"
    layer: "SBDDSegDataLayer"
    param_str: "{\'sbdd_dir\': \'../../data/sbdd/dataset\', \'seed\': 1337, \'split\': \'train\', \'mean\': (104.00699, 116.66877, 122.67892)}"
  }

dongzhuoyao

layer {
  name: "data"
  type: "Python"
  top: "data"
  top: "label"
  python_param {
    module: "voc_layers"
    layer: "SBDDSegDataLayer"
    param_str: "{\'sbdd_dir\': \'../data/sbdd/dataset\', \'seed\': 1337, \'split\': \'train\', \'mean\': (104.00699, 116.66877, 122.67892)}"
  }

dongzhuoyao

name: "resnet-34"
layer {
  name: "data"
  type: "MemoryData"
  top: "data"
  top: "label"
  transform_param {
    crop_size: 224
  }
  memory_data_param {

dongzhuoyao

name: "VGG_VOC2012ext"
layer {
  name: "data"
  type: "Data"
  top: "data"
  include {
    phase: TRAIN
  }
  transform_param {
    mean_value: 104.00699

dongzhuoyao

name: "VGG_ILSVRC_16_layers_fc_reduced"
input: "data"
input_dim: 10
input_dim: 3
input_dim: 500
input_dim: 500
layers {
  bottom: "data"
  top: "conv1_1"
  name: "conv1_1"

dongzhuoyao

# VGG 16-layer network convolutional finetuning
# Network modified to have smaller receptive field (128 pixels)
# nand 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):

dongzhuoyao

# VGG 16-layer network convolutional finetuning
# Network modified to have smaller receptive field (128 pixels)
# nand 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):

dongzhuoyao

# VGG 16-layer network convolutional finetuning
# Network modified to have smaller receptive field (128 pixels)
# nand 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):