 Falko Victor Habel
|
81eaebac5b
|
Merge pull request 'overall_performance_improvement' (#3) from overall_performance_improvement into develop
Reviewed-on: #3
|
2025-02-26 12:14:27 +00:00 |
|
Falko Victor Habel
|
5321eee803
|
Merge pull request 'added aiunn inference' (#2) from add_use_class into develop
Reviewed-on: #2
|
2025-02-26 12:13:59 +00:00 |
|
Falko Victor Habel
|
930f3a4885
|
Merge pull request 'finetune_class' (#1) from finetune_class into develop
Reviewed-on: #1
|
2025-02-26 12:13:08 +00:00 |
|
Falko Victor Habel
|
ed80b0b068
|
improved quality
|
2025-02-26 12:33:25 +01:00 |
|
Falko Victor Habel
|
7fd2af6f12
|
improved early stoppping
|
2025-02-25 19:47:18 +01:00 |
|
Falko Victor Habel
|
2e1556d306
|
added aiunn inference
|
2025-02-25 19:36:58 +01:00 |
|
Falko Victor Habel
|
6aad1a38f5
|
increased trainingset amount
|
2025-02-25 15:47:50 +01:00 |
|
Falko Victor Habel
|
fcebc103b8
|
fixed paths
|
2025-02-25 15:47:21 +01:00 |
|
Falko Victor Habel
|
09f196294c
|
new upsampler scripts
|
2025-02-25 15:47:10 +01:00 |
|
Falko Victor Habel
|
0611a26564
|
updated project info
|
2025-02-25 15:04:38 +01:00 |
|
Falko Victor Habel
|
79e0aeb269
|
downsized batchsize increased images
|
2025-02-24 16:39:25 +01:00 |
|
Falko Victor Habel
|
153ead15b7
|
downsized image amount
|
2025-02-24 16:32:23 +01:00 |
|
Falko Victor Habel
|
ecb2694415
|
update color channels
|
2025-02-24 16:28:18 +01:00 |
|
Falko Victor Habel
|
64fb7a199d
|
antialisaing not available
|
2025-02-24 16:23:57 +01:00 |
|
Falko Victor Habel
|
2360e23cc7
|
downsized imageset
|
2025-02-24 16:20:45 +01:00 |
|
Falko Victor Habel
|
443b9f5589
|
use cpu
|
2025-02-24 15:44:28 +01:00 |
|
Falko Victor Habel
|
0fa14c4a6f
|
added gpu support
|
2025-02-24 15:22:41 +01:00 |
|
Falko Victor Habel
|
b89670ad6c
|
loaded with bf16
|
2025-02-24 15:21:08 +01:00 |
|
Falko Victor Habel
|
33a3626b74
|
fixed config
|
2025-02-24 15:16:05 +01:00 |
|
Falko Victor Habel
|
8935fa5e13
|
doubled config
|
2025-02-24 14:57:55 +01:00 |
|
Falko Victor Habel
|
e114023cbc
|
go to cpu
|
2025-02-23 23:21:31 +01:00 |
|
Falko Victor Habel
|
fde8bdcb6f
|
test
|
2025-02-23 23:13:27 +01:00 |
|
Falko Victor Habel
|
a51300c77c
|
base model fix
|
2025-02-23 22:50:17 +01:00 |
|
Falko Victor Habel
|
c88961aee7
|
convert back to images
|
2025-02-23 22:42:36 +01:00 |
|
Falko Victor Habel
|
86664b10a6
|
improved vram usage?
|
2025-02-23 22:26:48 +01:00 |
|
Falko Victor Habel
|
7603ce8851
|
massivly downsized data
|
2025-02-23 20:09:28 +01:00 |
|
Falko Victor Habel
|
ad27ea2fa2
|
fixed to load kwargs
|
2025-02-23 20:04:44 +01:00 |
|
Falko Victor Habel
|
74c4adbff0
|
debug print
|
2025-02-23 20:02:31 +01:00 |
|
Falko Victor Habel
|
86bb74835d
|
updated Upsampler config
|
2025-02-23 19:59:18 +01:00 |
|
Falko Victor Habel
|
048a8d9861
|
added extra config
|
2025-02-23 19:56:17 +01:00 |
|
Falko Victor Habel
|
b740819757
|
fixed paths
|
2025-02-23 19:27:34 +01:00 |
|
Falko Victor Habel
|
e52a2a4b81
|
fixed spelling
|
2025-02-23 19:26:55 +01:00 |
|
Falko Victor Habel
|
2883e67e1c
|
temporary commit for lowercase fix
|
2025-02-23 19:26:36 +01:00 |
|
Falko Victor Habel
|
736886021c
|
updated finetuning script to work with Upsamler and added Early Stopping
|
2025-02-22 17:53:06 +01:00 |
|
Falko Victor Habel
|
2aba93caea
|
updated upsampler
|
2025-02-22 17:52:37 +01:00 |
|
Falko Victor Habel
|
933238a530
|
added extra psampling layer [not working]
|
2025-02-22 17:24:02 +01:00 |
|
Falko Victor Habel
|
90bcdd346a
|
even more downsized
|
2025-02-22 10:45:30 +01:00 |
|
Falko Victor Habel
|
f576a0d789
|
fixed autocast
|
2025-02-22 10:43:10 +01:00 |
|
Falko Victor Habel
|
81ceddff3b
|
addded device gpu and fixed autocast
|
2025-02-21 22:01:54 +01:00 |
|
Falko Victor Habel
|
742a3e6f70
|
fiexd script
|
2025-02-21 21:59:16 +01:00 |
|
Falko Victor Habel
|
4af12873f2
|
cpu training
|
2025-02-21 21:54:33 +01:00 |
|
Falko Victor Habel
|
992bc0eb7f
|
downsized two 8k samples
|
2025-02-21 21:51:48 +01:00 |
|
Falko Victor Habel
|
0166d8feeb
|
single batch
|
2025-02-21 21:49:16 +01:00 |
|
Falko Victor Habel
|
b06dad23af
|
downsized samples to max of 10k
|
2025-02-21 21:47:06 +01:00 |
|
Falko Victor Habel
|
6a31e8fa7f
|
downsized to 2
|
2025-02-21 21:43:01 +01:00 |
|
Falko Victor Habel
|
d66b167b85
|
downsized abtchsize to 8
|
2025-02-21 21:17:40 +01:00 |
|
Falko Victor Habel
|
fca74fb8d2
|
new loading
|
2025-02-21 21:12:14 +01:00 |
|
Falko Victor Habel
|
2583d2f01f
|
bugfix
|
2025-02-21 21:05:48 +01:00 |
|
Falko Victor Habel
|
2f12fcb863
|
updated loading
|
2025-02-21 21:03:37 +01:00 |
|
Falko Victor Habel
|
6a9b4afd91
|
use correct model loading
|
2025-02-21 20:58:35 +01:00 |
|
Falko Victor Habel
|
eacef6af65
|
added tqdm
|
2025-02-21 20:57:11 +01:00 |
|
Falko Victor Habel
|
36f9b30666
|
new saving
|
2025-02-21 20:55:46 +01:00 |
|
Falko Victor Habel
|
0c0372794e
|
new alternative version
|
2025-02-21 20:54:30 +01:00 |
|
Falko Victor Habel
|
40f1a65006
|
fix
|
2025-02-17 16:31:12 +01:00 |
|
Falko Victor Habel
|
bba5e2179d
|
setted up correct amp
|
2025-02-17 16:26:54 +01:00 |
|
Falko Victor Habel
|
e28fd3d330
|
added paths
|
2025-02-17 16:24:14 +01:00 |
|
Falko Victor Habel
|
704ad6106d
|
updated inference class and test image
|
2025-02-17 16:22:47 +01:00 |
|
Falko Victor Habel
|
62825e9731
|
increased image size
|
2025-02-15 13:29:50 +01:00 |
|
Falko Victor Habel
|
4c84086932
|
updated script
|
2025-02-15 13:27:30 +01:00 |
|
Falko Victor Habel
|
619e17c32c
|
going with batchsize 1
|
2025-02-15 13:17:17 +01:00 |
|
Falko Victor Habel
|
e69d0e90ec
|
fixed checkpoints tensors
|
2025-02-15 13:08:09 +01:00 |
|
Falko Victor Habel
|
75be3291d3
|
added custom upscaler model
|
2025-02-14 22:39:20 +01:00 |
|
Falko Victor Habel
|
1234fc5beb
|
added device type to autocast
|
2025-02-14 22:27:19 +01:00 |
|
Falko Victor Habel
|
ca29ee748b
|
fixed rsults
|
2025-02-14 22:23:38 +01:00 |
|
Falko Victor Habel
|
9645e1da23
|
fixed checkpoint
|
2025-02-14 22:14:09 +01:00 |
|
Falko Victor Habel
|
5a6680178a
|
try checkpoints
|
2025-02-14 22:10:07 +01:00 |
|
Falko Victor Habel
|
e7e7e96001
|
max gpu usage added
|
2025-02-14 22:03:04 +01:00 |
|
Falko Victor Habel
|
ca44dd8a77
|
added torch.amp support
|
2025-02-14 21:48:52 +01:00 |
|
Falko Victor Habel
|
b4dd550f8d
|
downsized params
|
2025-02-14 21:33:47 +01:00 |
|
Falko Victor Habel
|
19e5b72724
|
simplified code
|
2025-02-12 06:59:18 +01:00 |
|
Falko Victor Habel
|
8fafbebe45
|
fixed loading
|
2025-02-08 16:55:54 +01:00 |
|
Falko Victor Habel
|
20dd9f68ed
|
added tqdm to improve code
|
2025-02-08 12:52:48 +01:00 |
|
Falko Victor Habel
|
a48bad5a49
|
limit dataset
|
2025-02-07 15:26:57 +01:00 |
|
Falko Victor Habel
|
39efdff09e
|
updated datasets
|
2025-02-06 20:54:05 +01:00 |
|
Falko Victor Habel
|
bac4a9010a
|
updated dataset loading
|
2025-02-06 18:33:43 +01:00 |
|
Falko Victor Habel
|
72a5959bc1
|
updated batchsize and fixed key names
|
2025-02-05 22:32:39 +01:00 |
|
Falko Victor Habel
|
1a66169b37
|
updated keys
|
2025-02-05 21:33:33 +01:00 |
|
Falko Victor Habel
|
e298ac4c45
|
manually loading the correct modle again
|
2025-02-05 21:27:42 +01:00 |
|
Falko Victor Habel
|
de6a67cb4e
|
updated finetuning script
|
2025-02-05 16:16:31 +01:00 |
|
Falko Victor Habel
|
bb22d0a6da
|
added decoder models fits
|
2025-01-31 17:34:33 +01:00 |
|
Falko Victor Habel
|
be74658ceb
|
added decoeder model
|
2025-01-31 17:30:41 +01:00 |
|
Falko Victor Habel
|
9187ebe012
|
debug print
|
2025-01-31 17:14:28 +01:00 |
|
Falko Victor Habel
|
325faef9d5
|
push
|
2025-01-31 17:02:35 +01:00 |
|
Falko Victor Habel
|
50fa103579
|
printing
|
2025-01-31 16:57:13 +01:00 |
|
Falko Victor Habel
|
804882d7a2
|
corrected dataset paths
|
2025-01-31 16:11:21 +01:00 |
|
Falko Victor Habel
|
0b04ebab7a
|
corected path again
|
2025-01-31 16:06:12 +01:00 |
|
Falko Victor Habel
|
6b35463027
|
upgaeed path for base model
|
2025-01-31 16:04:54 +01:00 |
|
Falko Victor Habel
|
13fb2b76c1
|
updated finetuning
|
2025-01-31 16:03:28 +01:00 |
|
Falko Victor Habel
|
9ec563e86d
|
updated Finetuner to correctly log losses
|
2025-01-30 20:49:34 +01:00 |
|
Falko Victor Habel
|
8c49cc7e01
|
fixed tqdm in finetuning
|
2025-01-30 13:51:49 +01:00 |
|
Falko Victor Habel
|
0484ae01b1
|
added tqdm and removed doubles
|
2025-01-30 13:21:56 +01:00 |
|
Falko Victor Habel
|
34c547fb23
|
next try
|
2025-01-30 13:14:45 +01:00 |
|
Falko Victor Habel
|
9b7a182782
|
debug mode
|
2025-01-30 12:52:57 +01:00 |
|
Falko Victor Habel
|
4037a07764
|
updated process
|
2025-01-30 12:39:24 +01:00 |
|
Falko Victor Habel
|
be5bb53620
|
working transform
|
2025-01-30 11:56:17 +01:00 |
|
Falko Victor Habel
|
1f33f22bea
|
convert the bytes first
|
2025-01-30 10:45:18 +01:00 |
|
Falko Victor Habel
|
73d52f733c
|
updated config for updated model
|
2025-01-30 10:41:37 +01:00 |
|
Falko Victor Habel
|
2121316e3b
|
finetune improvement
|
2025-01-30 10:36:15 +01:00 |
|
Falko Victor Habel
|
4a60045320
|
first finetune try
|
2025-01-29 23:06:49 +01:00 |
|
Falko Victor Habel
|
914d002602
|
added new aiiun script with first draft for pip project
|
2025-01-29 22:30:57 +01:00 |
|
Falko Victor Habel
|
71da7ed2f1
|
removed old scripts
|
2025-01-29 22:30:35 +01:00 |
|
Falko Victor Habel
|
d85faadcc1
|
first finetune script
|
2025-01-29 19:26:32 +01:00 |
|
Falko Victor Habel
|
2f14301550
|
added init files for all different aiunn versions
|
2025-01-07 09:23:31 +01:00 |