Commit graph

13 commits

Author SHA1 Message Date
Jean-Marc Valin
b0620c0bf9
Using sparse GRUs in DRED decoder
Saves ~270 kB of weights in the decoder
2023-11-15 04:08:50 -05:00
Jean-Marc Valin
77594bf158
Dumping RDOVAE stats from XML 2023-11-08 17:32:43 -05:00
Jean-Marc Valin
222662dac8
DRED: quantize scale and dead zone to 8 bits 2023-11-07 18:10:50 -05:00
Jean-Marc Valin
0ab0640d4a
Split stats in two and remove useless dimensions 2023-11-07 00:07:14 -05:00
Jean-Marc Valin
544b3e576c
DRED: quantize r and p0 parameters with 8 bits
Only code non-degenerate symbols, which makes the encoder faster
2023-11-06 03:16:43 -05:00
Jan Buethe
1accd2472e
finalized quantization option in export_rdovae_weights.py 2023-10-20 14:14:31 +02:00
Jean-Marc Valin
d720955d61
Marking RDOVAE layers to quantize 2023-10-19 16:06:52 -04:00
Jan Buethe
60ac1c6c99
prepared quantization implementation for DRED 2023-10-19 21:54:39 +02:00
Jean-Marc Valin
27663d3641
Using a DenseNet for DRED 2023-10-02 01:43:44 -04:00
Jan Buethe
eb72d29a15
Support for dumping LinearLayer in weight-exchange 2023-07-27 19:55:17 -04:00
Marcus Asteborg
f36685fc97
Remove trailing whitespace in dnn 2023-06-22 13:58:37 -07:00
jbuethe
aa474553b5 updated torch framework to include quantization 2023-01-13 11:48:04 +00:00
jbuethe
fdb04d0eef added pytorch implementation of RDOVAE 2022-11-23 11:02:29 +00:00