Class representing the model of neural network.
More...
- Deprecated:
- This item will be removed in a future release.
def __init__ |
( |
|
self, |
|
|
|
args |
|
) |
| |
- Variant 1
- Variant 2
- Copy constructor
def allocate_{Float64|Float32} |
( |
|
self, |
|
|
|
args |
|
) |
| |
- Variant 1
Allocates the buffers needed for the training using neural network
- Parameters
-
sampleSize | Dimensionality of the batch for the input to the first layer |
parameter | Parameters of the training |
- Returns
- Status of computations
- Deprecated:
- This item will be removed in a future release.
- Variant 2
Allocates the buffers needed for the training using neural network
- Parameters
-
sampleSize | Dimensionality of the batch for the input to the first layer |
parameter | Parameters of the training |
- Returns
- Status of computations
- Deprecated:
- This item will be removed in a future release.
- Full Names
allocate_Float64
is for float64
allocate_Float32
is for float32
def create |
( |
|
stat = None | ) |
|
create(Status stat=None) -> daal.services.SharedPtr< daal.algorithms.neural_networks.training.Model >
def getBackwardLayer |
( |
|
self, |
|
|
|
index |
|
) |
| |
Returns the backward stage of a layer with certain index in the network
- Parameters
-
index | Index of the layer in the network |
- Returns
- Backward stage of a layer with certain index in the network
- Deprecated:
- This item will be removed in a future release.
def getBackwardLayers |
( |
|
self | ) |
|
Returns list of backward layers
- Returns
- List of backward layers
- Deprecated:
- This item will be removed in a future release.
def getForwardLayer |
( |
|
self, |
|
|
|
index |
|
) |
| |
Returns the forward stage of a layer with certain index in the network
- Parameters
-
index | Index of the layer in the network |
- Returns
- Forward stage of a layer with certain index in the network
- Deprecated:
- This item will be removed in a future release.
def getForwardLayers |
( |
|
self | ) |
|
Returns list of forward layers
- Returns
- List of forward layers
- Deprecated:
- This item will be removed in a future release.
def getPredictionModel_{Float64|Float32} |
( |
|
self | ) |
|
Returns list of forward layers and their parameters organised in the prediction.Model
- Returns
- List of forward layers and their parameters organised in the prediction.Model
- Deprecated:
- This item will be removed in a future release.
- Full Names
getPredictionModel_Float64
is for float64
getPredictionModel_Float32
is for float32
def getSerializationTag |
( |
|
self | ) |
|
getSerializationTag(Model self) -> int
def getSolverOptionalArgument |
( |
|
self, |
|
|
|
index |
|
) |
| |
Return the OptionalArgument from the neural netowrk model that stores intermediate status of solver between epochs by index
- Parameters
-
- Returns
- the OptionalArgument from the neural netowrk model that stores intermediate status of solver between epochs
- Deprecated:
- This item will be removed in a future release.
def getSolverOptionalArgumentCollection |
( |
|
self | ) |
|
Return the OptionalArgument from the neural netowrk model that stores intermediate status of solver between epochs
- Returns
- the OptionalArgument from the neural netowrk model that stores intermediate status of solver between epochs
- Deprecated:
- This item will be removed in a future release.
def getWeightsAndBiases |
( |
|
self, |
|
|
|
args |
|
) |
| |
- Variant 1
Returns table containing all neural network weights and biases
- Returns
- Table containing all neural network weights and biases
- Deprecated:
- This item will be removed in a future release.
- Variant 2
Returns the weights and biases of the forward layer of neural network as numeric table
- Parameters
-
idx | Index of the backward layer |
- Returns
- Weights and biases derivatives container
- Deprecated:
- This item will be removed in a future release.
def getWeightsAndBiasesDerivatives |
( |
|
self, |
|
|
|
args |
|
) |
| |
- Variant 1
Returns the weights and biases derivatives of all backward layers of neural network as numeric table
- Returns
- Weights and biases derivatives container
- Deprecated:
- This item will be removed in a future release.
- Variant 2
Returns the weights and biases derivatives of the backward layer of neural network as numeric table
- Parameters
-
idx | Index of the backward layer |
- Returns
- Weights and biases derivatives container
- Deprecated:
- This item will be removed in a future release.
def getWeightsAndBiasesStorageStatus |
( |
|
self | ) |
|
Returns weights and biases storage status
- Returns
- Weights and biases storage status. True if weights and biases of all layers stored in one numeric table. False otherwise.
- Deprecated:
- This item will be removed in a future release.
def initialize_{Float64|Float32} |
( |
|
self, |
|
|
|
args |
|
) |
| |
- Variant 1
Initializes neural network
- Parameters
-
sampleSize | Dimensionality of the batch for the input to the first layer |
topology | Collection of LayerDescriptor of every inserted layer |
parameter | Parameters of the training |
- Returns
- Status of computations
- Deprecated:
- This item will be removed in a future release.
- Variant 2
Initializes neural network
- Parameters
-
sampleSize | Dimensionality of the batch for the input to the first layer |
topology | Collection of LayerDescriptor of every inserted layer |
parameter | Parameters of the training |
- Returns
- Status of computations
- Deprecated:
- This item will be removed in a future release.
- Full Names
initialize_Float64
is for float64
initialize_Float32
is for float32
def setErrors |
( |
|
self, |
|
|
|
errors |
|
) |
| |
Sets the error collection to the Model
- Parameters
-
errors | Collection of errors |
- Deprecated:
- This item will be removed in a future release.
- Returns
- Status of computations
- Deprecated:
- This item will be removed in a future release.
def setSolverOptionalArgument |
( |
|
self, |
|
|
|
solverOptionalArgument, |
|
|
|
index |
|
) |
| |
Sets the OptionalArgument to neural netowrk model to store intermediate status of solver between epochs
- Parameters
-
solverOptionalArgument | OptionalArgumentPtr to set in collection |
index | Index in collection of required OptionalArgument |
- Returns
- Status of computations
- Deprecated:
- This item will be removed in a future release.
def setSolverOptionalArgumentCollection |
( |
|
self, |
|
|
|
solverOptionalArgumentCollection |
|
) |
| |
Sets the OptionalArgument to neural netowrk model to store intermediate status of solver between epochs
- Parameters
-
solverOptionalArgumentCollection | Structure to store intermediate status of solver |
- Returns
- Status of computations
- Deprecated:
- This item will be removed in a future release.
def setWeightsAndBiases |
( |
|
self, |
|
|
|
args |
|
) |
| |
- Variant 1
Sets table containing all neural network weights and biases
- Parameters
-
weightsAndBiases | Table containing all neural network weights and biases |
- Returns
- Status of computations
- Deprecated:
- This item will be removed in a future release.
- Variant 2
Sets table containing weights and biases of one forward layer of neural network
- Parameters
-
idx | Index of the forward layer |
table | Table containing weights and biases of one forward layer of neural network |
- Returns
- Status of computations
- Deprecated:
- This item will be removed in a future release.
The documentation for this class was generated from the following file:
- neural_networks/training.py