dongzhuoyao

# 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.
#

name: "deeplabv2_vgg16_test"

dongzhuoyao

name: "deeplabv2_resnet101_deploy"

layer {
  name: "data"
  type: "MemoryData"
  top: "data"
  top: "label"
  top: "data_dim"

  memory_data_param {

dongzhuoyao

name: "segnet_vgg16_train"
layer {
  name: "data"
  type: "DenseImageData"
  top: "data"
  top: "label"
  dense_image_data_param {
    source: "/SegNet/CamVid/train.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

dongzhuoyao

name: "segnet_vgg16_deploy"
layer {
  name: "data"
  type: "DenseImageData"
  top: "data"
  top: "label"
  dense_image_data_param {
    source: "/SegNet/CamVid/test.txt"	# Change this to the absolute path to your data file
    batch_size: 1
  }

dongzhuoyao

name: "bayesian_segnet_train"
layer {
  name: "data"
  type: "DenseImageData"
  top: "data"
  top: "label"
  dense_image_data_param {
    source: "/SegNet/CamVid/train.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

dongzhuoyao

name: "VGG_ILSVRC_16_layer"
layer {
  name: "data"
  type: "DenseImageData"
  top: "data"
  top: "label"
  dense_image_data_param {
    source: "/SegNet/CamVid/test.txt"	# Change this to the absolute path to your data file
    batch_size: 4			# Change this to be the number of Monte Carlo Dropout samples you wish to make
  }

dongzhuoyao

# 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):

dongzhuoyao

# 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.
#
name: "DeepLab-LargeFOV"

dongzhuoyao

#
input: "data"
input_dim: 1
input_dim: 3
input_dim: 473
input_dim: 473

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

dongzhuoyao

#
input: "data"
input_dim: 1
input_dim: 3
input_dim: 473
input_dim: 473

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