9 commits

Author	SHA1	Message	Date
Jean-Marc Valin	c76756e18a	Adding sparse training for GRU B inputs	2021-07-18 02:24:21 -04:00
Jean-Marc Valin	3e223e6015	Fixes Python inference for the binary probability tree	2021-07-10 01:59:49 -04:00
Jean-Marc Valin	d332100808	Representing output pdf as binary probability tree ... Saves on the MDense/softmax computation since we only need to compute 8 values instead of 256.	2021-07-10 01:59:49 -04:00
Jean-Marc Valin	d61f7e00f8	Fix missing transpose in the sparity code ... CuDNNGRU and GRU don't use the same weight format	2021-06-25 13:43:37 -04:00
Jean-Marc Valin	c7ba313a67	Adding extra constraint to avoid saturation for SSE/AVX2 ... When implementing using SSSE3 or AVX2, our dot products can saturate if two adjacent weights sum to more than 127.	2021-06-18 17:39:35 -04:00
Jean-Marc Valin	237245f815	Support for multi-GPU training ... Not sure why CuDNNGRU doesn't get used by default, but we need to explicitly use it to get things to run fast.	2021-06-18 13:20:43 -04:00
Jean-Marc Valin	1657bae024	WIP: Adding a constraint	2021-01-16 02:11:19 -05:00
Jean-Marc Valin	cc28518699	wip 8x4 sparseness	2021-01-16 02:11:19 -05:00
Jean-Marc Valin	90fec91b12	Convert training code to Tensorflow 2	2020-08-19 14:27:07 -04:00