CIFAR-10 Network in Network with fix for cuDNN

solver.prototxt

net: "train_val.prototxt"
test_iter: 100
test_interval: 500
base_lr: 0.1
momentum: 0.9
weight_decay: 0.0001
lr_policy: "step"
gamma: 0.1
stepsize: 100000
display: 100
max_iter: 120000
snapshot: 10000
snapshot_prefix: "cifar10_nin"
solver_mode: GPU

train_val.prototxt

name: "CIFAR10_full"
layer {
  name: "cifar"
  type: "HDF5Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  hdf5_data_param {
    source: "../cifar-train.txt"
    batch_size: 128
    shuffle: false
  }
}
layer {
  name: "cifar"
  type: "HDF5Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  hdf5_data_param {
    source: "../cifar-test.txt"
    batch_size: 100
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 192
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "gaussian"
      std: 0.05
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "cccp1"
  type: "Convolution"
  bottom: "conv1"
  top: "cccp1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 160
    kernel_size: 1
    group: 1
    weight_filler {
      type: "gaussian"
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu_cccp1"
  type: "ReLU"
  bottom: "cccp1"
  top: "cccp1"
}
layer {
  name: "cccp2"
  type: "Convolution"
  bottom: "cccp1"
  top: "cccp2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    kernel_size: 1
    group: 1
    weight_filler {
      type: "gaussian"
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu_cccp2"
  type: "ReLU"
  bottom: "cccp2"
  top: "cccp2"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "cccp2"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
    engine: CAFFE
  }
}
layer {
  name: "drop3"
  type: "Dropout"
  bottom: "pool1"
  top: "pool1"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 192
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "gaussian"
      std: 0.05
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "cccp3"
  type: "Convolution"
  bottom: "conv2"
  top: "cccp3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 192
    kernel_size: 1
    group: 1
    weight_filler {
      type: "gaussian"
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu_cccp3"
  type: "ReLU"
  bottom: "cccp3"
  top: "cccp3"
}
layer {
  name: "cccp4"
  type: "Convolution"
  bottom: "cccp3"
  top: "cccp4"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 192
    kernel_size: 1
    group: 1
    weight_filler {
      type: "gaussian"
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu_cccp4"
  type: "ReLU"
  bottom: "cccp4"
  top: "cccp4"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "cccp4"
  top: "pool2"
  pooling_param {
    pool: AVE
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "drop6"
  type: "Dropout"
  bottom: "pool2"
  top: "pool2"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 192
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "gaussian"
      std: 0.05
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "cccp5"
  type: "Convolution"
  bottom: "conv3"
  top: "cccp5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 192
    kernel_size: 1
    group: 1
    weight_filler {
      type: "gaussian"
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu_cccp5"
  type: "ReLU"
  bottom: "cccp5"
  top: "cccp5"
}
layer {
  name: "cccp6"
  type: "Convolution"
  bottom: "cccp5"
  top: "cccp6"
  param {
    lr_mult: 0.1
    decay_mult: 1
  }
  param {
    lr_mult: 0.1
    decay_mult: 0
  }
  convolution_param {
    num_output: 10
    kernel_size: 1
    group: 1
    weight_filler {
      type: "gaussian"
      std: 0.05
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu_cccp6"
  type: "ReLU"
  bottom: "cccp6"
  top: "cccp6"
}
layer {
  name: "pool3"
  type: "Pooling"
  bottom: "cccp6"
  top: "pool3"
  pooling_param {
    pool: AVE
    kernel_size: 8
    stride: 1
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "pool3"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "pool3"
  bottom: "label"
  top: "loss"
}

Why does layer pool2 use average pooling?

layer {
  name: "pool2"
  type: "Pooling"
  bottom: "cccp4"
  top: "pool2"
  pooling_param {
    pool: AVE # shouldn't this be MAX?
    kernel_size: 3
    stride: 2
  }
}