Python* API Reference for Intel® Data Analytics Acceleration Library 2019
local contrast normalization layer parameters More...
Public Member Functions | |
| def | __init__ |
| def | check |
Public Member Functions inherited from Parameter | |
| def | __init__ |
Public Member Functions inherited from Parameter | |
| def | __init__ |
| def | check |
Static Public Attributes | |
| kernel = ... | |
| sumDimension = ... | |
| indices = ... | |
| sigmaDegenerateCasesThreshold = ... | |
Static Public Attributes inherited from Parameter | |
| weightsInitializer = ... | |
| biasesInitializer = ... | |
| predictionStage = ... | |
| propagateGradient = ... | |
| weightsAndBiasesInitialized = ... | |
| allowInplaceComputation = ... | |
| def __init__ | ( | self | ) |
Default constructor
| def check | ( | self | ) |
Checks the correctness of the parameter
|
static |
Data structure representing the dimension for local contrast normalization kernels. (2,3) is supported now
|
static |
Tensor with sizes m_1 x m_2 of the two-dimensional kernel
|
static |
The threshold to avoid degenerate cases when calculating 1/auxSigma
|
static |
Numeric table of size 1x1 that stores dimension f
For more complete information about compiler optimizations, see our Optimization Notice.