PyVertical
PyVertical copied to clipboard
Development of SplitNN as a 2d array of Models.
This allows for generic logic which can be used to accomodate arbitrary input/ label tensor partitions.
Currently we treat the SplitNN as a 1d array of models. This allows us to perform horizontal splits in the model.
When this works, we should be able to use the same, standard class for any data/ label distribution
Hi @H4LL Can I work on this issue, please?
Sure! Lmk know if you'd like any pointers/ feedback
Thank you! This is my first issue on Openmined Could you point me to some articles/resources I can refer to learn more about this SplitNN project?
https://blog.openmined.org/split-neural-networks-on-pysyft/ https://blog.openmined.org/what-is-pyvertical/
hey @arunraja-hub, how is this going?
Apologies I haven't had time to work on this You can reassign it to someone else