- Configure the threshold algorithm in SharedTrainingMaster:
TrainingMaster tm = new SharedTrainingMaster.Builder(voidConfiguration, minibatchSize)
.thresholdAlgorithm(new AdaptiveThresholdAlgorithm(gradientThreshold))
.build();
- Configure the residual vectors by calling residualPostProcessor():
TrainingMaster tm = new SharedTrainingMaster.Builder(voidConfiguration, minibatch)
.residualPostProcessor(new ResidualClippingPostProcessor(clipValue, frequency))
.build();
..................Content has been hidden....................
You can't read the all page of ebook, please click
here login for view all page.