# 0.9.1

**Deeplearning4J**

* Fixed issue with incorrect version dependencies in 0.9.0
* Added EmnistDataSetIterator [Link](https://github.com/eclipse/deeplearning4j/blob/master/deeplearning4j/deeplearning4j-data/deeplearning4j-datasets/src/main/java/org/deeplearning4j/datasets/iterator/impl/EmnistDataSetIterator.java#L32)
* Numerical stability improvements to LossMCXENT / LossNegativeLogLikelihood with softmax (should reduce NaNs with very large activations)

**ND4J**

* Added runtime version checking for ND4J, DL4J, RL4J, Arbiter, DataVec [Link](https://github.com/eclipse/deeplearning4j/blob/master/nd4j/nd4j-backends/nd4j-api-parent/nd4j-api/src/main/java/org/nd4j/versioncheck/VersionCheck.java)

**Known Issues**

* Deeplearning4j: Use of Evaluation class no-arg constructor (i.e., new Evaluation()) can result in accuracy/stats being reported as 0.0. Other Evaluation class constructors, and ComputationGraph/MultiLayerNetwork.evaluate(DataSetIterator) methods work as expected.
  * This also impacts Spark (distributed) evaluation: workaround is to replace `sparkNet.evaluate(testData);` with `sparkNet.doEvaluation(testData, 64, new Evaluation(10))[0];`, where 10 is the number of classes and 64 in the evaluation minibatch size to use.
* SequenceRecordReaderDataSetIterator applies preprocessors (such as normalization) twice to each DataSet (possible workaround: use RecordReaderMultiDataSetIterator + MultiDataSetWrapperIterator)
* TransferLearning: ComputationGraph may incorrectly apply l1/l2 regularization (defined in FinetuneConfiguration) to frozen layers. Workaround: set 0.0 l1/l2 on FineTuneConfiguration, and required l1/l2 on new/non-frozen layers directly. Note that MultiLayerNetwork with TransferLearning appears to be unaffected.