SmartEngine
1.6.0
|
Trains a set of networks using gradient descent. Training with GradientDescentTrainer requires a Loss structure and thus the output of the network must be known. If only a relative loss about the network is known, a GeneticTrainer needs to be used. More...
Classes | |
class | CInfo |
GradientDescentTrainer constructor info More... | |
Public Member Functions | |
GradientDescentTrainer (CInfo cinfo) | |
void | SetTrainingInfo (GradientDescentTrainingInfo info) |
Overrides the training info from what was passed into the constructor More... | |
void | Train (int generationCount) |
Synchronously trains for the specified number of iterations More... | |
void | Reset () |
Resets the internal state of the trainer. More... | |
IEnumerator | TrainAsync (int generationCount) |
Asynchrounously trains for the specified number of iterations More... | |
Public Member Functions inherited from SmartEngine.NeuralNetworks.LossTrainer | |
unsafe void | SetTrainingMethod (SmartEngine.NeuralNetworks.LossTrainingMethodInfo info) |
Sets the training method and associated parameters More... | |
Public Member Functions inherited from SmartEngine.Resource | |
SerializationResult | Load (string appendName=null) |
Load this object from disk. More... | |
SerializationResult | Save (string appendName=null) |
Save this object to disk. More... | |
SerializationResult | Serialize (MemoryBuffer buffer) |
Write the contents of this object to a buffer. More... | |
SerializationResult | Serialize (out byte[] data) |
Write the contents of this object to a byte array. More... | |
SerializationResult | Deserialize (MemoryBuffer buffer) |
Fill this object with contents from a buffer. More... | |
SerializationResult | Deserialize (byte[] data) |
Fill this object with contents from a byte array. More... | |
Public Member Functions inherited from SmartEngine.Object | |
void | AddRef () |
Increments the internal reference count on this object. It is not common to use this method directly. More... | |
void | Release () |
Decrements the internal reference count on this object. It is not common to use this method directly. More... | |
Public Member Functions inherited from SmartEngine.Disposable | |
void | Dispose () |
Cleans up any internal state. It is not safe to use an object after it has been disposed. More... | |
Additional Inherited Members | |
Properties inherited from SmartEngine.NeuralNetworks.LossTrainer | |
uint | GenerationCount [get] |
Returns the number of generations we have been training for. More... | |
float | Loss [get] |
Returns the loss in the graph. More... | |
Properties inherited from SmartEngine.Resource | |
string | ResourceName [get] |
Returns the name of this resource passed to the constructor. More... | |
SerializationResult | LastLoadResult [get] |
Returns the result of the last call to Load(). Useful for checking loaded data state after creation. More... | |
Trains a set of networks using gradient descent. Training with GradientDescentTrainer requires a Loss structure and thus the output of the network must be known. If only a relative loss about the network is known, a GeneticTrainer needs to be used.
void SmartEngine.NeuralNetworks.GradientDescentTrainer.Reset | ( | ) |
Resets the internal state of the trainer.
void SmartEngine.NeuralNetworks.GradientDescentTrainer.SetTrainingInfo | ( | GradientDescentTrainingInfo | info | ) |
Overrides the training info from what was passed into the constructor
info |
void SmartEngine.NeuralNetworks.GradientDescentTrainer.Train | ( | int | generationCount | ) |
Synchronously trains for the specified number of iterations
generationCount |
IEnumerator SmartEngine.NeuralNetworks.GradientDescentTrainer.TrainAsync | ( | int | generationCount | ) |
Asynchrounously trains for the specified number of iterations
generationCount |