Caffe：常用层的参数设置

InnerProduct

Also known as a “fully-connected” layer, computes an inner product with a set of learned weights, and (optionally) adds biases.

Parameters:

int 	M_
 
int 	K_
 
int 	N_
 
bool 	bias_term_
 
Blob< Dtype > 	bias_multiplier_
 
bool 	transpose_  if true, assume transposed weights 

Tile

Parameters:

unsigned int 	axis_
 
unsigned int 	tiles_
 
unsigned int 	outer_dim_
 
unsigned int 	inner_dim_

Reshape

vector< int > 	copy_axes_
 	vector of axes indices whose dimensions we'll copy from the bottom
 
int 	inferred_axis_
 	the index of the axis whose dimension we infer, or -1 if none
 
int 	constant_count_
 	the product of the "constant" output dimensions 

参考地址：
1.http://caffe.berkeleyvision.org/doxygen/annotated.html