Commit Graph

322 Commits

Author SHA1 Message Date
James Betker
f8108cfdb2 update environment and fix a bunch of deps 2022-07-24 23:43:25 -06:00
James Betker
45afefabed fix booboo 2022-07-24 18:00:14 -06:00
James Betker
cc62ba9cba few more tfd13 things 2022-07-24 17:39:33 -06:00
James Betker
76464ca063 some fixes to mdf to support new archs 2022-07-21 10:55:50 -06:00
James Betker
24a78bd7d1 update tfd14 too 2022-07-21 00:45:33 -06:00
James Betker
b92ff8de78 misc 2022-07-20 23:59:32 -06:00
James Betker
a1743d26aa Revert "Try to squeeze a bit more performance out of this arch"
This reverts commit 767f963392.
2022-07-20 23:57:56 -06:00
James Betker
767f963392 Try to squeeze a bit more performance out of this arch 2022-07-20 23:51:11 -06:00
James Betker
b9d0f7e6de simplify parameterization a bit 2022-07-20 23:41:54 -06:00
James Betker
ee8ceed6da rework tfd13 further
- use a gated activation layer for both attention & convs
- add a relativistic learned position bias. I believe this is similar to the T5 position encodings but it is simpler and learned
- get rid of prepending to the attention matrix - this doesn't really work that well. the model eventually learns to attend one of its heads to these blocks but why not just concat if it is doing that?
2022-07-20 23:28:29 -06:00
James Betker
40427de8e3 update tfd13 for inference 2022-07-20 21:51:25 -06:00
James Betker
dbebe18602 Fix ts=0 with new formulation 2022-07-20 12:12:33 -06:00
James Betker
82bd62019f diffuse the cascaded prior for continuous sr model 2022-07-20 11:54:09 -06:00
James Betker
b0e3be0a17 transition to nearest interpolation mode for downsampling 2022-07-20 10:56:17 -06:00
James Betker
7b3fc79737 iq checkin 2022-07-20 10:19:32 -06:00
James Betker
15decfdb98 misc 2022-07-20 10:19:02 -06:00
James Betker
c14bf6dfb2 fix conditioning free 2022-07-19 18:04:49 -06:00
James Betker
fc0b291b21 do masking up proper 2022-07-19 16:32:17 -06:00
James Betker
c00398e955 scope attention in tfd13 as well 2022-07-19 14:59:43 -06:00
James Betker
b157b28c7b tfd14
hopefully this helps address the positional dependencies of tfd12
2022-07-19 13:30:05 -06:00
James Betker
73d7211a4c fix script 2022-07-19 11:17:43 -06:00
James Betker
6b1cfe8e66 ugh 2022-07-19 11:14:20 -06:00
James Betker
da9e47ca0e new bounds for MEL normalization and multi-resolution SR in MDF 2022-07-19 11:11:46 -06:00
James Betker
eecb534e66 a few fixes to multiresolution sr 2022-07-19 11:11:15 -06:00
James Betker
eab7dc339d iq checkin
who knows where I'm going with this.. I don't even know sometimes..
2022-07-19 09:13:27 -06:00
James Betker
0824708dc7 iq checkin 2022-07-18 18:40:14 -06:00
James Betker
df27b98730 ddp doesnt like dropout on checkpointed values 2022-07-18 17:17:04 -06:00
James Betker
c959e530cb good ole ddp.. 2022-07-18 17:13:45 -06:00
James Betker
cf57c352c8 Another fix 2022-07-18 17:09:13 -06:00
James Betker
83a4ef4149 default to use input for conditioning & add preprocessed input to GDI 2022-07-18 17:01:19 -06:00
James Betker
1b4d9567f3 tfd13 for multi-resolution superscaling 2022-07-18 16:36:22 -06:00
James Betker
1b648abd7c iq2 2022-07-18 10:12:23 -06:00
James Betker
20ef9cc6b4 iq checkin
yeah - I'm at it again...
2022-07-17 18:24:33 -06:00
James Betker
e13b1adfdb :< 2022-07-14 21:52:23 -06:00
James Betker
51291ab070 Some additional context regularization in tfd 2022-07-14 21:49:47 -06:00
James Betker
fa352e2744 also some good assert text 2022-07-14 21:26:22 -06:00
James Betker
4d53c66602 simplify span selecting logic in tfdpc 2022-07-14 21:25:03 -06:00
James Betker
4d5688be47 fix compatibility 2022-07-13 21:28:20 -06:00
James Betker
def70cd444 Merge remote-tracking branch 'origin/master' 2022-07-13 21:26:59 -06:00
James Betker
711c53c1f0 music script 2022-07-13 21:26:55 -06:00
James Betker
15831b2576 some stuff 2022-07-13 21:26:25 -06:00
James Betker
e23c322089 uhh2.0 2022-07-12 22:48:46 -06:00
James Betker
ebfe72d502 fix obo 2022-07-12 22:28:20 -06:00
James Betker
f46d6645da tfdpcv5 updates 2022-07-12 21:48:18 -06:00
James Betker
7b4dcbf136 Support causal diffusion! 2022-07-08 12:30:05 -06:00
James Betker
28d5b6a80a optionally disable checkpointing in x_transformers (and make it so with the cond_encoder in tfdpc_v5) 2022-07-06 16:55:57 -06:00
James Betker
48270272e7 Use corner alignment for linear interpolation in TFDPC and TFD12
I noticed from experimentation that when this is not enabled, the interpolation edges are "sticky",
which is to say there is more variance in the center of the interpolation than at the edges.
2022-07-06 16:45:03 -06:00
James Betker
5816a4595e ugh 2022-07-05 11:14:09 -06:00
James Betker
7440e43531 Fix some bugs 2022-07-05 10:37:47 -06:00
James Betker
2b128730e7 Improve conditioning separation logic 2022-07-05 10:30:28 -06:00