Deep learning framework by BAIR
Created by
Yangqing Jia
Lead Developer
Evan Shelhamer
Convolution./include/caffe/layers/conv_layer.hpp ./src/caffe/layers/conv_layer.cpp ./src/caffe/layers/conv_layer.cu n * c_i * h_i * w_in * c_o * h_o * w_o, where h_o = (h_i + 2 * pad_h - kernel_h) / stride_h + 1 and w_o likewise.The Convolution layer convolves the input image with a set of learnable filters, each producing one feature map in the output image.
Sample (as seen in ./models/bvlc_reference_caffenet/train_val.prototxt):
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
}
}
}
ConvolutionParameter convolution_param)
num_output (c_o): the number of filterskernel_size (or kernel_h and kernel_w): specifies height and width of each filterweight_filler [default type: 'constant' value: 0]bias_term [default true]: specifies whether to learn and apply a set of additive biases to the filter outputspad (or pad_h and pad_w) [default 0]: specifies the number of pixels to (implicitly) add to each side of the inputstride (or stride_h and stride_w) [default 1]: specifies the intervals at which to apply the filters to the inputgroup (g) [default 1]: If g > 1, we restrict the connectivity of each filter to a subset of the input. Specifically, the input and output channels are separated into g groups, and the th output group channels will be only connected to the th input group channels../src/caffe/proto/caffe.proto):message ConvolutionParameter {
optional uint32 num_output = 1; // The number of outputs for the layer
optional bool bias_term = 2 [default = true]; // whether to have bias terms
// 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. (Kernel dilation is sometimes referred to by its use in the
// algorithme à trous from Holschneider et al. 1987.)
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)
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];
}