Susan Eraly

I can add this as part of the example review.

Added. Was a little tricky since it's downloading a file from a google drive link programatically and that is annoying and tricky..

Hi @rafal-perkowski Thank you for taking such a close look at this. We are discussing a fix for the rank=1 case. You can follow it [here](https://github.com/KonduitAI/deeplearning4j/pull/155#partial-pull-merging) The other two issues...

We can close this. Issues are fixed.

Also adding note on reworking example to better align to best practices

The reason it predicts only one class is because it needs tuning. Keeping issue open for reworking to better align with best practices.

Hi @dkunzinfa Thank you for filing this issue. The test data labels are incorrect...They are all incorrectly marked. If you look at the print outs of the loss you will...

Sure thing. We *are* working on updating things and redoing/reorganizing docs examples etc.

@carlosorrego For now as a workaround you can set the IDropout to null before [this line.](https://github.com/eclipse/deeplearning4j-examples/blob/master/dl4j-examples/src/main/java/org/deeplearning4j/examples/styletransfer/NeuralStyleTransfer.java#L291) There isn't any dropout in the net here. Looks like the forward pass somehow...

I wonder how the traffic on the nd4j site compares to the dl4j. In any case, I agree with Justin. We should integrate them all onto one site. As of...