Scale layer
caffe源码中给出了scale层的作用,如下:
/**
* @brief Computes the elementwise product of two input Blobs, with the shape of
* the latter Blob "broadcast" to match the shape of the former.
* Equivalent to tiling the latter Blob, then computing the elementwise
* product. Note: for efficiency and convenience, this layer can
* additionally perform a "broadcast" sum too when `bias_term: true`
* is set.
*
* The latter, scale input may be omitted, in which case it's learned as
* parameter of the layer (as is the bias, if it is included).
*/
即,按元素计算连个输入的乘积。该过程以广播第二个输入来匹配第一个输入矩阵的大小。
也就是通过平铺第二个输入矩阵来计算按元素乘积(点乘)。
message ScaleParameter {
// The first axis of bottom[0] (the first input Blob) along which to apply
// bottom[1] (the second input Blob). May be negative to index from the end
// (e.g., -1 for the last axis).
//
// For example, if bottom[0] is 4D with shape 100x3x40x60, the output
// top[0] will have the same shape, and bottom[1] may have any of the
// following shapes (for the given value of axis):
// (axis == 0 == -4) 100; 100x3; 100x3x40; 100x3x40x60
// (axis == 1 == -3) 3; 3x40; 3x40x60
// (axis == 2 == -2) 40; 40x60
// (axis == 3 == -1) 60
// Furthermore, bottom[1] may have the empty shape (regardless of the value of
// "axis") -- a scalar multiplier.
optional int32 axis = 1 [default = 1]; //指定第二个输入的形状大小,默认为axis = 1,即如例子中所示可能有(3; 3x40; 3x40x60;)三种形状。
// (num_axes is ignored unless just one bottom is given and the scale is
// a learned parameter of the layer. Otherwise, num_axes is determined by the
// number of axes by the second bottom.) 除了只有一个输入bottom[0]外,num_axes都将被忽略.
// The number of axes of the input (bottom[0]) covered by the scale
// parameter, or -1 to cover all axes of bottom[0] starting from `axis`.
// Set num_axes := 0, to multiply with a zero-axis Blob: a scalar. //num_axes=-1,覆盖第一个输入的所有轴(维度);num_axes=0, 第一个输入与一个标量做点乘.
optional int32 num_axes = 2 [default = 1]; //第一个输入被覆盖轴的数量,默认为1.
// (filler is ignored unless just one bottom is given and the scale is
// a learned parameter of the layer.) 除了只有一个输入bottom[0]外,filler都将被忽略.
// The initialization for the learned scale parameter. 学习的scale参数的初始化.
// Default is the unit (1) initialization, resulting in the ScaleLayer
// initially performing the identity operation. 默认为单位初始化.
optional FillerParameter filler = 3;
// Whether to also learn a bias (equivalent to a ScaleLayer+BiasLayer, but
// may be more efficient). Initialized with bias_filler (defaults to 0).
optional bool bias_term = 4 [default = false]; //是否同时学习偏差bias,默认为否.
optional FillerParameter bias_filler = 5; //带有偏差填充的初始化,偏差bias_filler默认为0
}