| Package | Description |
|---|---|
| org.deeplearning4j.models.sequencevectors.graph.walkers.impl |
| Modifier and Type | Class and Description |
|---|---|
static class |
PopularityWalker.Builder<T extends SequenceElement> |
static class |
WeightedWalker.Builder<T extends SequenceElement> |
| Modifier and Type | Method and Description |
|---|---|
RandomWalker.Builder<T> |
RandomWalker.Builder.setNoEdgeHandling(NoEdgeHandling handling)
This method defines walker behavior when it gets to node which has no next nodes available
Default value: RESTART_ON_DISCONNECTED
|
RandomWalker.Builder<T> |
WeightedWalker.Builder.setRestartProbability(double alpha)
This method defines a chance for walk restart
Good value would be somewhere between 0.03-0.07
|
RandomWalker.Builder<T> |
RandomWalker.Builder.setRestartProbability(double alpha)
This method defines a chance for walk restart
Good value would be somewhere between 0.03-0.07
|
RandomWalker.Builder<T> |
RandomWalker.Builder.setSeed(long seed)
This method specifies random seed.
|
RandomWalker.Builder<T> |
RandomWalker.Builder.setWalkDirection(WalkDirection direction)
This method defines next hop selection within walk
|
RandomWalker.Builder<T> |
RandomWalker.Builder.setWalkLength(int walkLength)
This method specifies output sequence (walk) length
|
Copyright © 2020. All rights reserved.