[Embench] Candidate for ML for future Embench

David PATTERSON pattrsn at cs.berkeley.edu
Tue Apr 21 18:30:14 CEST 2020

MLPerf's TinyML benchmark effort is considering using this model for visual
wake words. The NN model is 250 KB and they are use TensorFlow Lite.

Is this size plausible for future benchmarks?

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.librecores.org/pipermail/embench/attachments/20200421/28c70af6/attachment.htm>

More information about the Embench mailing list