C++ API Reference for Intel® Data Analytics Acceleration Library 2020 Update 1
Class representing the parameters of neural network prediction. More...
|
inline |
Constructs the parameters of neural network prediction algorithm
[in] | batchSize_ | Size of the batch to be processed by the neural network |
[in] | allocateWeightsAndBiases_ | Flag that idicates if weights and biases are allocated or not |
size_t batchSize |
Size of the batch to be processed by the neural network.
For more complete information about compiler optimizations, see our Optimization Notice.