Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Adam ¶
type Adam struct {
// contains filtered or unexported fields
}
Adam is an Adam solver
type BatchTrainer ¶
type BatchTrainer struct {
// contains filtered or unexported fields
}
BatchTrainer implements parallelized batch training
func NewBatchTrainer ¶
func NewBatchTrainer(solver Solver, verbosity, batchSize, parallelism int) *BatchTrainer
NewBatchTrainer returns a BatchTrainer
type OnlineTrainer ¶
type OnlineTrainer struct {
// contains filtered or unexported fields
}
OnlineTrainer is a basic, online network trainer
func NewTrainer ¶
func NewTrainer(solver Solver, verbosity int) *OnlineTrainer
NewTrainer creates a new trainer
type SGD ¶
type SGD struct {
// contains filtered or unexported fields
}
SGD is stochastic gradient descent with nesterov/momentum
type Samples ¶
type Samples []Sample
Samples is a set of input-output pairs
type Solver ¶
type Solver interface {
Init(size int)
Update(value, gradient float64, iteration, idx int) float64
}
Solver implements an update rule for training a NN
type StatsPrinter ¶
type StatsPrinter struct {
// contains filtered or unexported fields
}
StatsPrinter prints training progress
func (*StatsPrinter) PrintProgress ¶
func (p *StatsPrinter) PrintProgress(n *nn.Neural, validation Samples, elapsed time.Duration, iteration int)
PrintProgress prints the current state of training
Source Files
Click to show internal directories.
Click to hide internal directories.