Uses of Class
org.deeplearning4j.eval.ROC

Packages that use ROC

Package	Description
org.deeplearning4j.eval
org.deeplearning4j.eval.serde
org.deeplearning4j.nn.graph
org.deeplearning4j.nn.multilayer

Uses of ROC in org.deeplearning4j.eval

Methods in org.deeplearning4j.eval with parameters of type ROC

Modifier and Type	Method and Description
void	ROC.merge(ROC other) Merge this ROC instance with another.

Uses of ROC in org.deeplearning4j.eval.serde

Methods in org.deeplearning4j.eval.serde with parameters of type ROC

Modifier and Type	Method and Description
void	ROCArraySerializer.serialize(ROC[] rocs, org.nd4j.shade.jackson.core.JsonGenerator jsonGenerator, org.nd4j.shade.jackson.databind.SerializerProvider serializerProvider)
void	ROCSerializer.serialize(ROC roc, org.nd4j.shade.jackson.core.JsonGenerator jsonGenerator, org.nd4j.shade.jackson.databind.SerializerProvider serializerProvider)
void	ROCSerializer.serializeWithType(ROC value, org.nd4j.shade.jackson.core.JsonGenerator gen, org.nd4j.shade.jackson.databind.SerializerProvider serializers, org.nd4j.shade.jackson.databind.jsontype.TypeSerializer typeSer)

Uses of ROC in org.deeplearning4j.nn.graph

Methods in org.deeplearning4j.nn.graph that return ROC

Modifier and Type	Method and Description
ROC	ComputationGraph.evaluateROC(org.nd4j.linalg.dataset.api.iterator.DataSetIterator iterator, int rocThresholdSteps) Evaluate the network (must be a binary classifier) on the specified data, using the ROC class
ROC	ComputationGraph.evaluateROC(org.nd4j.linalg.dataset.api.iterator.MultiDataSetIterator iterator, int rocThresholdSteps) Evaluate the network (must be a binary classifier) on the specified data, using the ROC class

Uses of ROC in org.deeplearning4j.nn.multilayer

Methods in org.deeplearning4j.nn.multilayer that return ROC

Modifier and Type	Method and Description
ROC	MultiLayerNetwork.evaluateROC(org.nd4j.linalg.dataset.api.iterator.DataSetIterator iterator, int rocThresholdSteps) Evaluate the network (must be a binary classifier) on the specified data, using the ROC class