SmartEngine
1.6.0
|
Public Attributes | |
LossTrainingMethod | Method = LossTrainingMethod.Stochastic |
The method to use while training More... | |
readonly List< long > | SessionIndices = new List<long>() |
Session indices divide the graph input into logical chunks. These are row indicies in the input buffer. More... | |
int | BatchSize = 32 |
The number of rows to train at a time. More... | |
int | SequenceLength = 1 |
How many sequences should be trained every step. Only applies to stepped trainable layers (such as LSTM). Effectively, this determines how long of a memory the layer (LSTM) has. More... | |
int SmartEngine.NeuralNetworks.LossTrainingMethodInfo.BatchSize = 32 |
The number of rows to train at a time.
LossTrainingMethod SmartEngine.NeuralNetworks.LossTrainingMethodInfo.Method = LossTrainingMethod.Stochastic |
The method to use while training
int SmartEngine.NeuralNetworks.LossTrainingMethodInfo.SequenceLength = 1 |
How many sequences should be trained every step. Only applies to stepped trainable layers (such as LSTM). Effectively, this determines how long of a memory the layer (LSTM) has.
readonly List<long> SmartEngine.NeuralNetworks.LossTrainingMethodInfo.SessionIndices = new List<long>() |
Session indices divide the graph input into logical chunks. These are row indicies in the input buffer.
When training an LSTM, sequence runs won't go past session lines. When training stochastically, one row from each session will be batched together.