Python* API Reference for Intel® Data Analytics Acceleration Library 2019
2D convolution layer parameters More...
Public Member Functions | |
| def | __init__ |
Public Member Functions inherited from Parameter | |
| def | __init__ |
Public Member Functions inherited from Parameter | |
| def | __init__ |
| def | check |
Static Public Attributes | |
| indices = ... | |
| groupDimension = ... | |
| kernelSizes = ... | |
| strides = ... | |
| paddings = ... | |
| nKernels = ... | |
| nGroups = ... | |
Static Public Attributes inherited from Parameter | |
| weightsInitializer = ... | |
| biasesInitializer = ... | |
| predictionStage = ... | |
| propagateGradient = ... | |
| weightsAndBiasesInitialized = ... | |
| allowInplaceComputation = ... | |
| def __init__ | ( | self | ) |
Default constructor
|
static |
Dimension for which the grouping is applied. groupDimension=1 is supported now
|
static |
Data structure representing the dimension for convolution kernels. (2,3) is supported now
|
static |
Data structure representing the sizes of the two-dimensional kernel subtensor
|
static |
Number of groups which the input data is split in groupDimension dimension
|
static |
Number of kernels applied to the input layer data
|
static |
Data structure representing the number of data to be implicitly added to the subtensor
|
static |
Data structure representing the intervals on which the kernel should be applied to the input
For more complete information about compiler optimizations, see our Optimization Notice.