AngelBottomless and GitHub
029d7c7543
Revert unresolved changes in Bias initialization
...
it should be zeros_ or parameterized in future properly.
2022-10-27 14:44:53 +09:00
guaneec and aria1th
cc56df996e
Fix dropout logic
2022-10-27 14:38:21 +09:00
AngelBottomless
85fcccc105
Squashed commit of fixing dropout silently
...
fix dropouts for future hypernetworks
add kwargs for Hypernetwork class
hypernet UI for gradio input
add recommended options
remove as options
revert adding options in ui
2022-10-27 14:38:21 +09:00
guaneec and GitHub
b6a8bb123b
Fix merge
2022-10-26 15:15:19 +08:00
guaneec and GitHub
91bb35b1e6
Merge fix
2022-10-26 15:00:03 +08:00
guaneec and GitHub
649d79a8ec
Merge branch 'master' into hn-activation
2022-10-26 14:58:04 +08:00
guaneec and GitHub
877d94f97c
Back compatibility
2022-10-26 14:50:58 +08:00
AngelBottomless and AUTOMATIC1111
7207e3bf49
remove duplicate keys and lowercase
2022-10-26 09:17:01 +03:00
AngelBottomless and AUTOMATIC1111
de096d0ce7
Weight initialization and More activation func
...
add weight init
add weight init option in create_hypernetwork
fstringify hypernet info
save weight initialization info for further debugging
fill bias with zero for He/Xavier
initialize LayerNorm with Normal
fix loading weight_init
2022-10-26 09:17:01 +03:00
guaneec and GitHub
c702d4d0df
Fix off-by-one
2022-10-26 13:43:04 +08:00
guaneec and GitHub
2f4c91894d
Remove activation from final layer of HNs
2022-10-26 12:10:30 +08:00
AngelBottomless and AUTOMATIC1111
e9a410b535
check length for variance
2022-10-24 09:07:39 +03:00
AngelBottomless and AUTOMATIC1111
0d2e1dac40
convert deque -> list
...
I don't feel this being efficient
2022-10-24 09:07:39 +03:00
AngelBottomless and AUTOMATIC1111
348f89c8d4
statistics for pbar
2022-10-24 09:07:39 +03:00
AngelBottomless and AUTOMATIC1111
40b56c9289
cleanup some code
2022-10-24 09:07:39 +03:00
AngelBottomless and AUTOMATIC1111
b297cc3324
Hypernetworks - fix KeyError in statistics caching
...
Statistics logging has changed to {filename : list[losses]}, so it has to use loss_info[key].pop()
2022-10-24 09:07:39 +03:00
DepFA and AUTOMATIC1111
1fbfc052eb
Update hypernetwork.py
2022-10-23 08:34:33 +03:00
AngelBottomless and AUTOMATIC1111
48dbf99e84
Allow tracking real-time loss
...
Someone had 6000 images in their dataset, and it was shown as 0, which was confusing.
This will allow tracking real time dataset-average loss for registered objects.
2022-10-22 22:24:19 +03:00
AngelBottomless and AUTOMATIC1111
24694e5983
Update hypernetwork.py
2022-10-22 20:25:32 +03:00
discus0434
6a4fa73a38
small fix
2022-10-22 13:44:39 +00:00
discus0434 and GitHub
97749b7c7d
Merge branch 'AUTOMATIC1111:master' into master
2022-10-22 22:00:59 +09:00
discus0434
7912acef72
small fix
2022-10-22 13:00:44 +00:00
discus0434
fccba4729d
add an option to avoid dying relu
2022-10-22 12:02:41 +00:00
AUTOMATIC
7fd90128eb
added a guard for hypernet training that will stop early if weights are getting no gradients
2022-10-22 14:48:43 +03:00
discus0434
dcb45dfecf
Merge branch 'master' of upstream
2022-10-22 11:14:46 +00:00
discus0434
0e8ca8e7af
add dropout
2022-10-22 11:07:00 +00:00
timntorres and AUTOMATIC1111
272fa527bb
Remove unused variable.
2022-10-21 16:52:24 +03:00
timntorres and AUTOMATIC1111
19818f023c
Match hypernet name with filename in all cases.
2022-10-21 16:52:24 +03:00
timntorres and AUTOMATIC1111
51e3dc9cca
Sanitize hypernet name input.
2022-10-21 16:52:24 +03:00
AUTOMATIC
03a1e288c4
turns out LayerNorm also has weight and bias and needs to be pre-multiplied and trained for hypernets
2022-10-21 10:13:24 +03:00
AUTOMATIC1111 and GitHub
0c5522ea21
Merge branch 'master' into training-help-text
2022-10-21 09:57:55 +03:00
timntorres and AUTOMATIC1111
4ff274e1e3
Revise comments.
2022-10-21 09:55:00 +03:00
timntorres and AUTOMATIC1111
5245c7a493
Issue #2921-Give PNG info to Hypernet previews.
2022-10-21 09:55:00 +03:00
AUTOMATIC
c23f666dba
a more strict check for activation type and a more reasonable check for type of layer in hypernets
2022-10-21 09:47:43 +03:00
aria1th
f89829ec3a
Revert "fix bugs and optimizations"
...
This reverts commit 108be15500
2022-10-21 01:37:11 +09:00
AngelBottomless and GitHub
108be15500
fix bugs and optimizations
2022-10-21 01:00:41 +09:00
AngelBottomless and GitHub
a71e021236
only linear
2022-10-20 23:48:52 +09:00
AngelBottomless and GitHub
d8acd34f66
generalized some functions and option for ignoring first layer
2022-10-20 23:43:03 +09:00
discus0434 and GitHub
6b38c2c19c
Merge branch 'AUTOMATIC1111:master' into master
2022-10-20 18:51:12 +09:00
AUTOMATIC
930b4c64f7
allow float sizes for hypernet's layer_structure
2022-10-20 08:18:02 +03:00
discus0434
6f98e89486
update
2022-10-20 00:10:45 +00:00
DepFA and GitHub
166be3919b
allow overwrite old hn
2022-10-20 00:09:40 +01:00
DepFA and GitHub
d6ea584137
change html output
2022-10-20 00:07:57 +01:00
discus0434
2ce52d32e4
fix for #3086 failing to load any previous hypernet
2022-10-19 16:31:12 +00:00
AUTOMATIC
c6e9fed500
fix for #3086 failing to load any previous hypernet
2022-10-19 19:21:16 +03:00
discus0434
3770b8d2fa
enable to write layer structure of hn himself
2022-10-19 15:28:42 +00:00
discus0434
42fbda83bb
layer options moves into create hnet ui
2022-10-19 14:30:33 +00:00
discus0434 and GitHub
7f8670c4ef
Merge branch 'master' into master
2022-10-19 15:18:45 +09:00
Silent and AUTOMATIC1111
da72becb13
Use training width/height when training hypernetworks.
2022-10-19 09:13:28 +03:00
discus0434
e40ba281f1
update
2022-10-19 01:03:58 +09:00
