Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • master default protected
  • neural-network
  • neural-network-google-colab
  • v0.0.5
  • v0.0.4
  • v0.0.3
  • v0.0.2
  • v0.0.1
8 results
Created with Raphaël 2.2.06Jan19Dec181727Nov2012876431Oct302928211898743216Sep13129654330Aug2827262322211914138726Jun117623May2221103230Apr253229Mar27262120191287127Feb26242120191815Modify output of runKFold to log AUC and AUC-PRModify output of runKFold to log AUC and AUC-PRModification to include correctly new version of java-rocCOrrection tests since change in java-roc new versionCorrection of some things since update java-rocCorrect axis title in p-r curve generationUpdate pom.xmlUpdate main function to save results in txt file + update pom.xml to use the last veersion of java-rocChange parameter for batchsizeAdd epoch number as parametersCorrect typo in filename curvesCorrection in name file for ROC and PR curvesChange getPrCurve to getPrecisionRecallCurveAdd P-R Curve generation in modelEvaluation for NeuralNetworkAdd Curve generation in modelEvaluation for NeuralNetworkTest for generation Roc curve and save in pngComparison ROC computation with different settingsPrint thresholdSteps value for checkingAdd new datafile for testCode added (in comment) to generate aggragation of dataset after a classical learning. Result will be used to validate P-R curve generationChange in pom.xml to try to avoid dependencies errorsRemove listenerRemove dependencies commentsAdd DL4J cuda in pomSolve issues triggered by maven verifyCorrect issue in average auc computationChange logger to println because logger is not always desplayed in RunnerSet epoch number to 500Fix merge conflictsChange sysout in main to logChange sysout in main to logChange some logs to display Average AUC for WT and execution time in runKFold methodChange log to display Average AUC and exectution time for runKFoldRemove seed in learning methodRemove dependency in double in pom + add line to force to use all GPU availableUpdate code to solve issues due to the version change (0.9.1 to 1.0.0-beta5)Change all version of ND4J and DL4J to 1.0.0-beta5. All dependencies must have the same version numberChange dependency cudo to use Cuda 1Change DL4J backend to use GPUSet pom.xml as before change for Google Colob