c3d_ucf101_train_test.prototxt

name: "c3d_ucf101"

# ----- video/label input -----
# ----- for training
layer {
  name: "data"
  type: "VideoData"
  top: "data"
  top: "label"
  video_data_param {
    source: "examples/c3d_ucf101/c3d_ucf101_train_split1.txt"
    # 6GB GPU: use batch_size of ~30. 12GB: ~50. Adjust for your GPU memory
    batch_size: 50
    new_height: 128
    new_width: 171
    new_length: 16
    shuffle: true
  }
  include {
    phase: TRAIN
  }
  transform_param {
    crop_size: 112
    mirror: true
    # using mean RGB values yields almost identical results as using full mean
    # cube. mean cube can be downloaded at the following URL:
    # https://dl.dropboxusercontent.com/u/306922/video-caffe-model/ucf101_train_mean.binaryproto
    #mean_file: "examples/c3d_ucf101/ucf101_train_mean.binaryproto"
    mean_value: 90
    mean_value: 98
    mean_value: 102
  }
}
# ----- for validation
layer {
  name: "data"
  type: "VideoData"
  top: "data"
  top: "label"
  video_data_param {
    source: "examples/c3d_ucf101/c3d_ucf101_train_split1.txt"
    batch_size: 5
    new_height: 128
    new_width: 171
    new_length: 16
    shuffle: true
  }
  include {
    # test-on-train is disabled by default. turn it on in solver file to monitor
    # overfitting
    phase: TEST
    stage: "test-on-train"
  }
  transform_param {
    crop_size: 112
    mirror: false
    #mean_file: "examples/c3d_ucf101/ucf101_train_mean.binaryproto"
    mean_value: 90
    mean_value: 98
    mean_value: 102
  }
}
layer {
  name: "data"
  type: "VideoData"
  top: "data"
  top: "label"
  video_data_param {
    source: "examples/c3d_ucf101/c3d_ucf101_test_split1.txt"
    batch_size: 5
    new_height: 128
    new_width: 171
    new_length: 16
    shuffle: true
  }
  include {
    phase: TEST
    stage: "test-on-val"
  }
  transform_param {
    crop_size: 112
    mirror: false
    #mean_file: "examples/c3d_ucf101/ucf101_train_mean.binaryproto"
    mean_value: 90
    mean_value: 98
    mean_value: 102
  }
}

# ----- 1st group -----
layer {
  name: "conv1a"
  type: "NdConvolution"
  bottom: "data"
  top: "conv1a"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    kernel_shape { dim: 3 dim: 3 dim: 3 }
    stride_shape { dim: 1 dim: 1 dim: 1 }
    pad_shape    { dim: 1 dim: 1 dim: 1 }
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1a"
  type: "ReLU"
  bottom: "conv1a"
  top: "conv1a"
}
layer {
  name: "pool1"
  type: "NdPooling"
  bottom: "conv1a"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_shape { dim: 1 dim: 2 dim: 2 }
    stride_shape { dim: 1 dim: 2 dim: 2 }
  }
}

# ----- 2nd group -----
layer {
  name: "conv2a"
  type: "NdConvolution"
  bottom: "pool1"
  top: "conv2a"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_shape { dim: 3 dim: 3 dim: 3 }
    stride_shape { dim: 1 dim: 1 dim: 1 }
    pad_shape    { dim: 1 dim: 1 dim: 1 }
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu2a"
  type: "ReLU"
  bottom: "conv2a"
  top: "conv2a"
}
layer {
  name: "pool2"
  type: "NdPooling"
  bottom: "conv2a"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_shape { dim: 2 dim: 2 dim: 2 }
    stride_shape { dim: 2 dim: 2 dim: 2 }
  }
}

# ----- 3rd group -----
layer {
  name: "conv3a"
  type: "NdConvolution"
  bottom: "pool2"
  top: "conv3a"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_shape { dim: 3 dim: 3 dim: 3 }
    stride_shape { dim: 1 dim: 1 dim: 1 }
    pad_shape    { dim: 1 dim: 1 dim: 1 }
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu3a"
  type: "ReLU"
  bottom: "conv3a"
  top: "conv3a"
}
layer {
  name: "pool3"
  type: "NdPooling"
  bottom: "conv3a"
  top: "pool3"
  pooling_param {
    pool: MAX
    kernel_shape { dim: 2 dim: 2 dim: 2 }
    stride_shape { dim: 2 dim: 2 dim: 2 }
  }
}

# ----- 4th group -----
layer {
  name: "conv4a"
  type: "NdConvolution"
  bottom: "pool3"
  top: "conv4a"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_shape { dim: 3 dim: 3 dim: 3 }
    stride_shape { dim: 1 dim: 1 dim: 1 }
    pad_shape    { dim: 1 dim: 1 dim: 1 }
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu4a"
  type: "ReLU"
  bottom: "conv4a"
  top: "conv4a"
}
layer {
  name: "pool4"
  type: "NdPooling"
  bottom: "conv4a"
  top: "pool4"
  pooling_param {
    pool: MAX
    kernel_shape { dim: 2 dim: 2 dim: 2 }
    stride_shape { dim: 2 dim: 2 dim: 2 }
  }
}

# ----- 5th group -----
layer {
  name: "conv5a"
  type: "NdConvolution"
  bottom: "pool4"
  top: "conv5a"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    kernel_shape { dim: 3 dim: 3 dim: 3 }
    stride_shape { dim: 1 dim: 1 dim: 1 }
    pad_shape    { dim: 1 dim: 1 dim: 1 }
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu5a"
  type: "ReLU"
  bottom: "conv5a"
  top: "conv5a"
}
layer {
  name: "pool5"
  type: "NdPooling"
  bottom: "conv5a"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_shape { dim: 2 dim: 2 dim: 2 }
    stride_shape { dim: 2 dim: 2 dim: 2 }
  }
}

# ----- 1st fc group -----
layer {
  name: "fc6"
  type: "InnerProduct"
  bottom: "pool5"
  top: "fc6"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 2048
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "fc6"
  top: "fc6"
}
layer {
  name: "drop6"
  type: "Dropout"
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}

# ----- 2nd fc group -----
layer {
  name: "fc7"
  type: "InnerProduct"
  bottom: "fc6"
  top: "fc7"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 2048
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "fc7"
  top: "fc7"
}
layer {
  name: "drop7"
  type: "Dropout"
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}

# ----- 3rd fc group -----
layer {
  name: "fc8"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc8"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 101
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "prob"
  type: "Softmax"
  bottom: "fc8"
  top: "prob"
  include {
    phase: TEST
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "prob"
  bottom: "label"
  top: "accuracy/top-1"
  include {
    phase: TEST
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "prob"
  bottom: "label"
  top: "accuracy/top-5"
  include {
    phase: TEST
  }
  accuracy_param {
    top_k: 5
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "fc8"
  bottom: "label"
  top: "loss"
}