org.deeplearning4j.scalnet.models
Sequential
Related Docs:
object Sequential
| package models
Build model configuration from optimizer and seed.
Build model configuration from optimizer and seed.
optimization algorithm to use in model
seed to use
NeuralNetConfiguration.Builder
Make last layer of architecture an output layer using the provided loss function.
Make last layer of architecture an output layer using the provided loss function.
loss function to use
Compile neural net architecture.
Compile neural net architecture. Call immediately before training.
loss function to use
optimization algorithm to use
Evaluate model against an iterator over data set
Evaluate model against an iterator over data set
data set
output size
Evaluation instance
Evaluate model against an iterator over data set
Evaluate model against an iterator over data set
data set
Evaluation instance
Evaluate model against an iterator over data set
Evaluate model against an iterator over data set
iterator over data set
output size
Evaluation instance
Evaluate model against an iterator over data set
Evaluate model against an iterator over data set
iterator over data set
Evaluation instance
Fit neural net to data.
Fit neural net to data.
data set
number of epochs to train
callbacks for monitoring training
Fit neural net to data.
Fit neural net to data.
iterator over data set
number of epochs to train
callbacks for monitoring training
Use neural net to make prediction on input x.
Use neural net to make prediction on input x
Class for keras-style simple sequential neural net architectures with one input node and one output node for each node in computational graph.
Wraps DL4J MultiLayerNetwork. Enforces keras model construction pattern: preprocessing (reshaping) layers should be explicitly provided by the user, while last layer is treated implicitly as an output layer.