James Betker
4509cfc705
track logperp for diffusion evals
2022-07-28 01:30:44 -06:00
James Betker
19eb939ccf
gd perplexity
...
# Conflicts:
# codes/trainer/eval/music_diffusion_fid.py
2022-07-28 00:25:05 -06:00
James Betker
a1bbde8a43
few things
2022-07-26 11:52:03 -06:00
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
f3d967dbf5
remove eta from mdf
2022-07-24 17:21:20 -06:00
James Betker
76464ca063
some fixes to mdf to support new archs
2022-07-21 10:55:50 -06:00
James Betker
13c263e9fb
go all in on m2wv3
2022-07-21 00:51:27 -06:00
James Betker
24a78bd7d1
update tfd14 too
2022-07-21 00:45:33 -06:00
James Betker
02ebda42f2
#yolo
2022-07-21 00:43:03 -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
9a37f3ba42
reminder to future self
2022-07-20 10:19:15 -06:00
James Betker
15decfdb98
misc
2022-07-20 10:19:02 -06:00
James Betker
2997a640b0
fix mdf
2022-07-19 19:39:29 -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
b203a7dc97
And remove unused parameters
2022-07-19 15:05:12 -06:00
James Betker
17a07b2e33
readd one mdf function
2022-07-19 15:04:36 -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
4597447178
add assertions to mel generator script
2022-07-19 11:23:54 -06:00
James Betker
1b6fe88bcb
spit out overages in GDI
2022-07-19 11:19:59 -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
2fb85526bc
mdf cleanup
2022-07-19 09:57:05 -06:00
James Betker
4aa840a494
be more stringent on min and max ranges in GDI.. this is gonna break somethings probably
2022-07-19 09:14:08 -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
625d7b6f38
music joiner checkin
2022-07-18 18:40:25 -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
8d7692c1e0
uh
2022-07-18 17:15:27 -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
7a10c3fed8
commit my own version of vq, with a fix for cosine similarity and support for masking
2022-07-18 10:12:17 -06:00
James Betker
4ce5c31705
music_joiner update for new big cosine model
2022-07-17 18:24:56 -06:00
