C++ API Reference for Intel® Data Analytics Acceleration Library 2020 Update 1
Provides methods for the maximum 1D pooling layer in the batch processing mode. More...
algorithmFPType | Data type to use in intermediate computations for the maximum 1D pooling layer, double or float |
method | Maximum 1D pooling layer method, Method |
|
inline |
Constructs the maximum 1D pooling layer
[in] | nDimensions | Number of dimensions in input gradient tensor |
Parameter parameter |
Maximum 1D pooling layer parameters
For more complete information about compiler optimizations, see our Optimization Notice.