Phil Wang
|
f5916111f8
|
0.6.3
0.6.3
|
2021-06-21 17:41:16 -07:00 |
|
Phil Wang
|
ad9e303ff3
|
fix channels
0.6.1
|
2021-06-11 15:28:36 -07:00 |
|
Phil Wang
|
ae42f48f6a
|
prepare so that unet can work with a channel of one, and also make it so image size is hard coded in diffusion class. preparing for training on protein distograms
0.6.0
|
2021-06-11 14:06:39 -07:00 |
|
Phil Wang
|
5989f4c77e
|
recommit sample
|
2020-10-13 09:32:56 -07:00 |
|
Phil Wang
|
2082046888
|
set higher num train steps, so non-practitioners do not think it is completed
|
2020-10-11 13:49:49 -07:00 |
|
Phil Wang
|
3c5b7e2d56
|
update readme
|
2020-10-10 10:37:44 -07:00 |
|
Phil Wang
|
d4ce9f6c38
|
save samples and models to ./results path
0.5.2
|
2020-10-09 21:50:23 -07:00 |
|
Phil Wang
|
ff451f697e
|
update with new and improved cosine noise scheduler
|
2020-10-09 21:21:02 -07:00 |
|
Phil Wang
|
3d96532c60
|
update citations in preparation to add improvements from a iclr 2021 paper
|
2020-10-05 17:15:28 -07:00 |
|
Phil Wang
|
ef2ca0b625
|
new paper suggests image linear attention is more effective without query normalization
0.4.0
|
2020-10-04 21:53:53 -07:00 |
|
Phil Wang
|
9f95a03c07
|
fix bug with rezero and linear attention
0.3.2
|
2020-09-21 20:11:34 -07:00 |
|
Phil Wang
|
a4c68d3569
|
fix bug
0.3.1
|
2020-09-15 15:57:39 -07:00 |
|
Phil Wang
|
b33a48e342
|
make sure when sampling, batch does not exceed training batch size
0.3.0
|
2020-09-15 15:15:10 -07:00 |
|
Phil Wang
|
8e5fb17063
|
add badge
|
2020-09-14 13:38:06 -07:00 |
|
Phil Wang
|
4bf28914bc
|
allow for mixed precision training with fp16 flag
0.2.4
|
2020-09-08 17:26:23 -07:00 |
|
Phil Wang
|
88f83d0ff2
|
fix loading checkpoint
0.2.2
|
2020-09-08 15:15:59 -07:00 |
|
Phil Wang
|
26b5cab6c8
|
update ema more frequently
0.2.1
|
2020-09-08 15:03:38 -07:00 |
|
Phil Wang
|
1307b3115d
|
add exponential moving average of model, also allow passing in custom noise schedule
0.2.0
|
2020-09-08 14:58:09 -07:00 |
|
Phil Wang
|
81fb2a0386
|
add sample
|
2020-09-08 10:17:48 -07:00 |
|
Phil Wang
|
698227ae13
|
fix small bug with gradient accumulation
0.1.4
|
2020-09-07 23:14:38 -07:00 |
|
Phil Wang
|
c479adf960
|
add interpolation
0.1.3
|
2020-09-07 22:38:59 -07:00 |
|
Phil Wang
|
d70fb08f8a
|
small helper fn to make sampling more clear
|
2020-09-07 16:40:36 -07:00 |
|
Phil Wang
|
e700a7c6de
|
add image back
|
2020-09-07 10:37:58 -07:00 |
|
Phil Wang
|
9c758662a3
|
fix another stray bug
0.1.2
|
2020-09-06 23:25:30 -07:00 |
|
Phil Wang
|
1f1e42e9f9
|
update readme
0.1.1
|
2020-09-06 22:35:37 -07:00 |
|
Phil Wang
|
e1800c1a8d
|
remove wip, seems to be working
|
2020-09-06 14:26:23 -07:00 |
|
Phil Wang
|
11f27032ba
|
offer training class to easily train model off an image directory
0.1.0
|
2020-09-06 14:22:44 -07:00 |
|
Phil Wang
|
d8472a6220
|
update readme
|
2020-09-06 03:44:25 -07:00 |
|
Phil Wang
|
d59d8b05f6
|
fix a small bug
0.0.2
|
2020-09-06 01:50:59 -07:00 |
|
Phil Wang
|
365ce0c335
|
update readme
|
2020-09-06 01:44:05 -07:00 |
|
Phil Wang
|
0cc4aecfd5
|
first alpha release
0.0.1
|
2020-09-06 01:40:57 -07:00 |
|
Phil Wang
|
79e0765675
|
make sampling work
|
2020-09-06 01:24:44 -07:00 |
|
Phil Wang
|
ee76497b83
|
complete training, sans sampling
|
2020-09-05 23:41:02 -07:00 |
|
Phil Wang
|
e496bba350
|
more cleanup
|
2020-09-05 14:11:32 -07:00 |
|
Phil Wang
|
1b05546b47
|
cleanup
|
2020-09-05 13:57:44 -07:00 |
|
Phil Wang
|
c9855c8c74
|
complete model portion
|
2020-09-05 13:55:17 -07:00 |
|
Phil Wang
|
73dc91e9f0
|
Create python-publish.yml
|
2020-08-31 12:47:17 -07:00 |
|
Phil Wang
|
dda425dc61
|
add scaffold
|
2020-08-31 12:45:27 -07:00 |
|
Phil Wang
|
df94747c0c
|
Update README.md
|
2020-08-25 19:24:13 -07:00 |
|
Phil Wang
|
f94876c6fb
|
Update README.md
|
2020-08-25 19:23:06 -07:00 |
|
Phil Wang
|
602421c714
|
Initial commit
|
2020-08-25 19:22:11 -07:00 |
|