#include <LocalNeuralNetImp.hpp>
Inheritance diagram for geopm::LocalNeuralNetImp:
Collaboration diagram for geopm::LocalNeuralNetImp:
Public Member Functions | |
| LocalNeuralNetImp (const std::vector< std::shared_ptr< DenseLayer > > layers) | |
| Constructor input from a vector of DenseLayers. More... | |
| TensorOneD | forward (const TensorOneD &inp) const override |
| Perform inference using the instance weights and biases. More... | |
| size_t | get_input_dim () const override |
| Get the dimension required for the input TensorOneD. More... | |
| size_t | get_output_dim () const override |
| Get the dimension of the resulting TensorOneD. More... | |
 Public Member Functions inherited from geopm::LocalNeuralNet | |
| virtual | ~LocalNeuralNet ()=default |
| TensorOneD | operator() (const TensorOneD &input) const |
Additional Inherited Members | |
| Static Public Member Functions inherited from geopm::LocalNeuralNet | |
| static std::unique_ptr< LocalNeuralNet > | make_unique (std::vector< std::shared_ptr< DenseLayer > > layers) |
| Returns a unique_ptr to a concrete object constructed using the underlying implementation from a vector of DenseLayers. More... | |
Constructor & Destructor Documentation
◆ LocalNeuralNetImp()
| geopm::LocalNeuralNetImp::LocalNeuralNetImp | ( | const std::vector< std::shared_ptr< DenseLayer > > | layers | ) |
Constructor input from a vector of DenseLayers.
- Parameters
-
[in] input layers
- Exceptions
-
geopm::Exception if consecutive layer sizes are incompatible
Member Function Documentation
◆ forward()
|
overridevirtual |
Perform inference using the instance weights and biases.
- Parameters
-
[in] TensorOneD vector of input signals.
- Exceptions
-
geopm::Exception if input dimension is incompatible with network.
- Returns
- Returns a TensorOneD vector of output values.
Implements geopm::LocalNeuralNet.
◆ get_input_dim()
|
overridevirtual |
Get the dimension required for the input TensorOneD.
- Returns
- Returns a size_t equal to the number of columns of weights
Implements geopm::LocalNeuralNet.
◆ get_output_dim()
|
overridevirtual |
Get the dimension of the resulting TensorOneD.
- Returns
- Returns a size_t equal to the number of rows of weights
Implements geopm::LocalNeuralNet.
The documentation for this class was generated from the following files:
