![]() |
Neuron Net
|
Describes the gradient calculation process for the Neuron of pooling layer. More...
Macros | |
#define | def_k_CalcInputGradientProof 6 |
Index of the kernel of the Pooling neuron to transfer gradient to previous layer (CalcInputGradientProof) More... | |
#define | def_k_cigp_matrix_i 0 |
Inputs tesor. More... | |
#define | def_k_cigp_matrix_g 1 |
Tensor of gradients at current layer. More... | |
#define | def_k_cigp_matrix_o 2 |
Output tensor. More... | |
#define | def_k_cigp_matrix_ig 3 |
Tensor of gradients at previous layer. More... | |
#define | def_k_cigp_outputs 4 |
Number of outputs. More... | |
#define | def_k_cigp_window 5 |
Size of input window. More... | |
#define | def_k_cigp_step 6 |
Step size. More... | |
Functions | |
__kernel void | CalcInputGradientProof (__global double *matrix_i, __global double *matrix_g, __global double *matrix_o, __global double *matrix_ig, int outputs, int window, int step) |
Kernel of the Pooling neuron to transfer gradient to previous layer (CNeuronProofOCL) More... | |
Describes the gradient calculation process for the Neuron of pooling layer.
#define def_k_CalcInputGradientProof 6 |
Index of the kernel of the Pooling neuron to transfer gradient to previous layer (CalcInputGradientProof)
Definition at line 159 of file NeuroNet.mqh.
#define def_k_cigp_matrix_g 1 |
Tensor of gradients at current layer.
Definition at line 161 of file NeuroNet.mqh.
#define def_k_cigp_matrix_i 0 |
Inputs tesor.
Definition at line 160 of file NeuroNet.mqh.
#define def_k_cigp_matrix_ig 3 |
Tensor of gradients at previous layer.
Definition at line 163 of file NeuroNet.mqh.
#define def_k_cigp_matrix_o 2 |
Output tensor.
Definition at line 162 of file NeuroNet.mqh.
#define def_k_cigp_outputs 4 |
Number of outputs.
Definition at line 164 of file NeuroNet.mqh.
#define def_k_cigp_step 6 |
Step size.
Definition at line 166 of file NeuroNet.mqh.
#define def_k_cigp_window 5 |
Size of input window.
Definition at line 165 of file NeuroNet.mqh.
__kernel void CalcInputGradientProof | ( | __global double * | matrix_i, |
__global double * | matrix_g, | ||
__global double * | matrix_o, | ||
__global double * | matrix_ig, | ||
int | outputs, | ||
int | window, | ||
int | step | ||
) |
Kernel of the Pooling neuron to transfer gradient to previous layer (CNeuronProofOCL)
[in] | matrix_i | Inputs tesor |
[in] | matrix_g | Tensor of gradients at current layer |
[in] | matrix_o | Output tensor |
[out] | matrix_ig | Tensor of gradients at previous layer |
outputs | Number of outputs | |
window | Size of input window | |
step | Step size |
Definition at line 299 of file NeuroNet.cl.