|
|
d7c5d57d93
|
Decreased blob-size a bit to make training faster
|
2021-09-22 12:10:17 +02:00 |
|
|
|
ca964732c5
|
Removed the slow blob-len growth
|
2021-09-22 11:50:03 +02:00 |
|
|
|
8608a89909
|
Train on bigger blobs (1KiB)
|
2021-09-22 11:46:22 +02:00 |
|
|
|
e4e2a18606
|
Tweaked training params
|
2021-09-22 11:09:15 +02:00 |
|
|
|
c95d5a2e8b
|
Merge branch 'master' of dominik.roth.ml:dodox/shark
|
2021-09-22 10:38:39 +02:00 |
|
|
|
483201c693
|
Increased layer count of model and refactored model into its own file
|
2021-09-22 10:38:09 +02:00 |
|
|
|
18ba954907
|
Increased layer count of model
|
2021-09-22 10:37:11 +02:00 |
|
|
|
1b4b6f1a2f
|
Updated README and better epoch-printing
|
2021-09-22 10:28:08 +02:00 |
|
|
|
5f0f9f1dce
|
Fixed a problem in model-training and renamed files
|
2021-09-22 09:14:23 +02:00 |
|
|
|
30cc846c6f
|
Sucessful discrimination; updated README
|
2021-09-21 16:00:43 +02:00 |
|
|
|
42ed2dd676
|
Fix: Encryption did not correctly increment iv
|
2021-09-21 15:54:29 +02:00 |
|
|
|
0c197e3e56
|
Higher lr; still wont work (gives false in 100% of tests)
|
2021-09-21 12:57:55 +02:00 |
|
|
|
054b4494d2
|
Even better loss tracking and more sparse checkpointing
|
2021-09-21 11:05:28 +02:00 |
|
|
|
5bd50e2b43
|
Better loss tracking and implemented saving of network-wheights
|
2021-09-21 09:49:27 +02:00 |
|
|
|
627bf370bc
|
Upped lr and dropout
|
2021-09-21 09:17:01 +02:00 |
|
|
|
f4444f3a9e
|
Started implementation of the PPT-Attacker
|
2021-09-21 09:14:31 +02:00 |
|
|
|
5f122e3cbf
|
The way markdown handles newlines is stupidwq
|
2021-09-20 11:35:29 +02:00 |
|
|
|
1eeeee57fe
|
small README
|
2021-09-20 11:34:57 +02:00 |
|
|
|
0dabde6dad
|
initial commit
|
2021-09-20 11:32:55 +02:00 |
|
