From 408eed9eda0a560dc4992b48285ae86744513449 Mon Sep 17 00:00:00 2001 From: Kazexiii Date: Tue, 17 Jul 2018 03:54:28 -0700 Subject: [PATCH 1/2] Update earlystopping.md --- earlystopping.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/earlystopping.md b/earlystopping.md index 36969a469..52d5792f0 100644 --- a/earlystopping.md +++ b/earlystopping.md @@ -27,7 +27,7 @@ The best model is the one saved at the time of the vertical dotted line - i.e., Using DL4J's early stopping functionality requires you to provide a number of configuration options: -* A score calculator, such as the *DataSetLossCalculator*([JavaDoc](https://deeplearning4j.org/doc/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculator.html), [Source Code](https://github.com/deeplearning4j/deeplearning4j/blob/c152293ef8d1094c281f5375ded61ff5f8eb6587/deeplearning4j-core/src/main/java/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculator.java)) for a Multi Layer Network, or *DataSetLossCalculatorCG* ([JavaDoc](https://deeplearning4j.org/doc/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculatorCG.html), [Source Code](https://github.com/deeplearning4j/deeplearning4j/blob/c152293ef8d1094c281f5375ded61ff5f8eb6587/deeplearning4j-core/src/main/java/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculatorCG.java)) for a Computation Graph. Is used to calculate at every epoch (for example: the loss function value on a test set, or the accuracy on the test set) +* A score calculator, such as the *DataSetLossCalculator*([JavaDoc](https://deeplearning4j.org/doc/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculator.html), [Source Code](https://github.com/deeplearning4j/deeplearning4j/blob/c152293ef8d1094c281f5375ded61ff5f8eb6587/deeplearning4j-core/src/main/java/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculator.java)) for a Multi Layer Network, or *DataSetLossCalculatorCG* ([JavaDoc](https://deeplearning4j.org/doc/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculatorCG.html), [Source Code](https://github.com/deeplearning4j/deeplearning4j/blob/c152293ef8d1094c281f5375ded61ff5f8eb6587/deeplearning4j-core/src/main/java/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculatorCG.java)) for a Computation Graph. These can be used to calculate the loss function value or the accuracy on a test set at every epoch. * How frequently we want to calculate the score function (default: every epoch) * One or more termination conditions, which tell the training process when to stop. There are two classes of termination conditions: * Epoch termination conditions: evaluated every N epochs From ba43bb1abe5cfe6512d6282b4f8b0577856ed75d Mon Sep 17 00:00:00 2001 From: Kazexiii Date: Tue, 17 Jul 2018 03:59:35 -0700 Subject: [PATCH 2/2] Update earlystopping.md --- earlystopping.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/earlystopping.md b/earlystopping.md index 52d5792f0..8a92367e5 100644 --- a/earlystopping.md +++ b/earlystopping.md @@ -27,7 +27,7 @@ The best model is the one saved at the time of the vertical dotted line - i.e., Using DL4J's early stopping functionality requires you to provide a number of configuration options: -* A score calculator, such as the *DataSetLossCalculator*([JavaDoc](https://deeplearning4j.org/doc/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculator.html), [Source Code](https://github.com/deeplearning4j/deeplearning4j/blob/c152293ef8d1094c281f5375ded61ff5f8eb6587/deeplearning4j-core/src/main/java/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculator.java)) for a Multi Layer Network, or *DataSetLossCalculatorCG* ([JavaDoc](https://deeplearning4j.org/doc/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculatorCG.html), [Source Code](https://github.com/deeplearning4j/deeplearning4j/blob/c152293ef8d1094c281f5375ded61ff5f8eb6587/deeplearning4j-core/src/main/java/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculatorCG.java)) for a Computation Graph. These can be used to calculate the loss function value or the accuracy on a test set at every epoch. +* A score calculator, such as the *DataSetLossCalculator*([JavaDoc](https://deeplearning4j.org/doc/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculator.html), [Source Code](https://github.com/deeplearning4j/deeplearning4j/blob/c152293ef8d1094c281f5375ded61ff5f8eb6587/deeplearning4j-core/src/main/java/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculator.java)) for a Multi Layer Network, or *DataSetLossCalculatorCG* ([JavaDoc](https://deeplearning4j.org/doc/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculatorCG.html), [Source Code](https://github.com/deeplearning4j/deeplearning4j/blob/c152293ef8d1094c281f5375ded61ff5f8eb6587/deeplearning4j-core/src/main/java/org/deeplearning4j/earlystopping/scorecalc/DataSetLossCalculatorCG.java)) for a Computation Graph. These can be used to calculate for example the loss function value or the accuracy on a test set at every epoch. * How frequently we want to calculate the score function (default: every epoch) * One or more termination conditions, which tell the training process when to stop. There are two classes of termination conditions: * Epoch termination conditions: evaluated every N epochs