Caffe Vision 层 - 卷积层 ConvLayer

  layer {
    name: "conv1"
    type: "Convolution"
    bottom: "data"
    top: "conv1"
    # learning rate and decay multipliers for the filters
    param { 
        lr_mult: 1 
        decay_mult: 1 
    }
    # learning rate and decay multipliers for the biases
    param { 
        lr_mult: 2 
        decay_mult: 0 
    }
    convolution_param {
      num_output: 96     # learn 96 filters
      kernel_size: 11    # each filter is 11x11
      stride: 4          # step 4 pixels between each filter application
      weight_filler {
        type: "gaussian" # initialize the filters from a Gaussian
        std: 0.01        # distribution with stdev 0.01 (default mean: 0)
      }
      bias_filler {
        type: "constant" # initialize the biases to zero (0)
        value: 0
      }
    }
  }

message ConvolutionParameter {
  optional uint32 num_output = 1;  // 网络层输出数
  optional bool bias_term = 2 [default = true]; // 是否有 bias 项

  // Pad, kernel size, and stride are all given as a single value for equal
  // dimensions in all spatial dimensions, or once per spatial dimension.
  repeated uint32 pad = 3; // The padding size; defaults to 0
  repeated uint32 kernel_size = 4; // The kernel size
  repeated uint32 stride = 6; // The stride; defaults to 1

  // Factor used to dilate the kernel, (implicitly) zero-filling the resulting holes.
  repeated uint32 dilation = 18; // The dilation; defaults to 1

  // For 2D convolution only, the *_h and *_w versions may also be used to
  // specify both spatial dimensions.
  optional uint32 pad_h = 9 [default = 0]; // The padding height (2D only)
  optional uint32 pad_w = 10 [default = 0]; // The padding width (2D only)
  optional uint32 kernel_h = 11; // The kernel height (2D only)
  optional uint32 kernel_w = 12; // The kernel width (2D only)
  optional uint32 stride_h = 13; // The stride height (2D only)
  optional uint32 stride_w = 14; // The stride width (2D only)

  // 将输入通道和输出通道数分组
  optional uint32 group = 5 [default = 1]; // The group size for group conv

  optional FillerParameter weight_filler = 7; // The filler for the weight
  optional FillerParameter bias_filler = 8; // The filler for the bias
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 15 [default = DEFAULT];

  // The axis to interpret as "channels" when performing convolution.
  // Preceding dimensions are treated as independent inputs;
  // succeeding dimensions are treated as "spatial".
  // With (N, C, H, W) inputs, and axis == 1 (the default), we perform
  // N independent 2D convolutions, sliding C-channel (or (C/g)-channels, for
  // groups g>1) filters across the spatial axes (H, W) of the input.
  // With (N, C, D, H, W) inputs, and axis == 1, we perform
  // N independent 3D convolutions, sliding (C/g)-channels
  // filters across the spatial axes (D, H, W) of the input.
  optional int32 axis = 16 [default = 1];

  // Whether to force use of the general ND convolution, even if a specific
  // implementation for blobs of the appropriate number of spatial dimensions
  // is available. (Currently, there is only a 2D-specific convolution
  // implementation; for input blobs with num_axes != 2, this option is
  // ignored and the ND implementation will be used.)
  optional bool force_nd_im2col = 17 [default = false];
}