Uses of Package
org.deeplearning4j.eval

Packages that use org.deeplearning4j.eval

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

Classes in org.deeplearning4j.eval used by org.deeplearning4j.eval

Class and Description
BaseEvaluation BaseEvaluation implement common evaluation functionality (for time series, etc) for Evaluation, RegressionEvaluation, ROC, ROCMultiClass etc.
ConfusionMatrix
Evaluation Evaluation metrics: precision, recall, f1
IEvaluation A general purpose interface for evaluating neural networks - methods are shared by implemetations such as Evaluation, RegressionEvaluation, ROC, ROCMultiClass
RegressionEvaluation Evaluation method for the evaluation of regression algorithms. Provides the following metrics, for each column: - MSE: mean squared error - MAE: mean absolute error - RMSE: root mean squared error - RSE: relative squared error - correlation coefficient See for example: http://www.saedsayad.com/model_evaluation_r.htm For classification, see Evaluation
ROC ROC (Receiver Operating Characteristic) for binary classifiers, using the specified number of threshold steps.
ROC.CountsForThreshold
ROC.PrecisionRecallPoint
ROC.ROCValue
ROCMultiClass ROC (Receiver Operating Characteristic) for multi-class classifiers, using the specified number of threshold steps.

Classes in org.deeplearning4j.eval used by org.deeplearning4j.nn.graph

Class and Description
Evaluation Evaluation metrics: precision, recall, f1

Classes in org.deeplearning4j.eval used by org.deeplearning4j.nn.multilayer

Class and Description
Evaluation Evaluation metrics: precision, recall, f1
IEvaluation A general purpose interface for evaluating neural networks - methods are shared by implemetations such as Evaluation, RegressionEvaluation, ROC, ROCMultiClass
RegressionEvaluation Evaluation method for the evaluation of regression algorithms. Provides the following metrics, for each column: - MSE: mean squared error - MAE: mean absolute error - RMSE: root mean squared error - RSE: relative squared error - correlation coefficient See for example: http://www.saedsayad.com/model_evaluation_r.htm For classification, see Evaluation
ROC ROC (Receiver Operating Characteristic) for binary classifiers, using the specified number of threshold steps.
ROCMultiClass ROC (Receiver Operating Characteristic) for multi-class classifiers, using the specified number of threshold steps.