Python* API Reference for Intel® Data Analytics Acceleration Library 2019
Parameters for the average 3D pooling layer. More...
Public Member Functions | |
| def | __init__ |
Public Member Functions inherited from Parameter | |
| def | __init__ |
Public Member Functions inherited from Parameter | |
| def | __init__ |
Public Member Functions inherited from Parameter | |
| def | __init__ |
| def | check |
Additional Inherited Members | |
Static Public Attributes inherited from Parameter | |
| strides = ... | |
| paddings = ... | |
| kernelSizes = ... | |
| indices = ... | |
Static Public Attributes inherited from Parameter | |
| weightsInitializer = ... | |
| biasesInitializer = ... | |
| predictionStage = ... | |
| propagateGradient = ... | |
| weightsAndBiasesInitialized = ... | |
| allowInplaceComputation = ... | |
| def __init__ | ( | self, | |
| firstIndex, | |||
| secondIndex, | |||
| thirdIndex, | |||
firstKernelSize = 2, |
|||
secondKernelSize = 2, |
|||
thirdKernelSize = 2, |
|||
firstStride = 2, |
|||
secondStride = 2, |
|||
thirdStride = 2, |
|||
firstPadding = 0, |
|||
secondPadding = 0, |
|||
thirdPadding = 0 |
|||
| ) |
Constructs the parameters of 3D pooling layer
| firstIndex | Index of the first of three dimensions on which the pooling is performed |
| secondIndex | Index of the second of three dimensions on which the pooling is performed |
| thirdIndex | Index of the third of three dimensions on which the pooling is performed |
| firstKernelSize | Size of the first dimension of 3D subtensor for which the average element is computed |
| secondKernelSize | Size of the second dimension of 3D subtensor for which the average element is computed |
| thirdKernelSize | Size of the third dimension of 3D subtensor for which the average element is computed |
| firstStride | Interval over the first dimension on which the pooling is performed |
| secondStride | Interval over the second dimension on which the pooling is performed |
| thirdStride | Interval over the third dimension on which the pooling is performed |
| firstPadding | Number of data elements to implicitly add to the the first dimension of the 3D subtensor on which the pooling is performed |
| secondPadding | Number of data elements to implicitly add to the the second dimension of the 3D subtensor on which the pooling is performed |
| thirdPadding | Number of data elements to implicitly add to the the third dimension of the 3D subtensor on which the pooling is performed |
For more complete information about compiler optimizations, see our Optimization Notice.