PinnedMark PorathNREL prize do-overThanks to NREL and the American Made program for hosting a contest worth $175,000. Thanks to Google for releasing tensorflow-gnn to the…Aug 301Aug 301
PinnedMark PorathData augmentation on TPUModel training is an iterative process, but it doesn’t have to be slow. With a tf.data pipeline, TFRecords → TPU, work that lasted hours on…May 12, 2021May 12, 2021