Michael Pilosov, PhD
|
a9e772f34e
|
restrict experiment, add loop option + dropout
|
10 months ago |
Michael Pilosov
|
697030b7df
|
partial unsupervision
|
10 months ago |
Michael Pilosov, PhD
|
05dd4e29ce
|
sequential instead of loopback
|
10 months ago |
Michael Pilosov, PhD
|
d318480b7c
|
circle norm bad for supervise?
|
10 months ago |
Michael Pilosov, PhD
|
4342a54cc8
|
anchors and more train data, exp w batch
|
10 months ago |
Michael Pilosov, PhD
|
248d1a72f9
|
re-anchor, pretty meh results in-batch
|
10 months ago |
Michael Pilosov, PhD
|
865e7f5104
|
supervised questionable
|
10 months ago |
Michael Pilosov, PhD
|
b6d9f94d8e
|
tracked down the losses bug
|
10 months ago |
Michael Pilosov, PhD
|
953488be4c
|
remove modulo from 3-space
|
10 months ago |
Michael Pilosov, PhD
|
a49f166252
|
seems to learn (supervised) consistently now
|
10 months ago |
Michael Pilosov, PhD
|
b5d9e725b3
|
allow for mix of supervised and not with alpha
|
10 months ago |
Michael Pilosov, PhD
|
721993d9e5
|
switch to unsupervised
|
10 months ago |
Michael Pilosov, PhD
|
b9d334e49a
|
weird setup, but sometimes possible to learn labels
|
10 months ago |
Michael Pilosov, PhD
|
07b4e548e2
|
lets make sure this can learn via supervision first
|
10 months ago |
Michael Pilosov, PhD
|
1e818aa977
|
remove s loss entirely
|
10 months ago |
Michael Pilosov, PhD
|
e1ac3211b9
|
use lightning CLI everywhere
|
10 months ago |
Michael Pilosov, PhD
|
012c7b7c68
|
add validation step
|
10 months ago |
Michael Pilosov, PhD
|
88c8cde9f6
|
total overhaul of model
|
10 months ago |
Michael Pilosov
|
70ecd7d7db
|
another attempt
|
10 months ago |
Michael Pilosov
|
1f7d4c1890
|
use millions of colors
|
10 months ago |
Michael Pilosov
|
0934ca0aed
|
parameterize network width
|
10 months ago |
Michael Pilosov
|
a8b723f021
|
prep search for arch
|
10 months ago |
Michael Pilosov
|
06a05cdf65
|
slight refactors
|
10 months ago |
Michael Pilosov
|
4d8bcc8715
|
diff arch, optimizer
|
10 months ago |
Michael Pilosov
|
dfdcaab55a
|
updates
|
10 months ago |
Michael Pilosov
|
719597ce90
|
refactor loss functions
|
10 months ago |
mm
|
acb83adb27
|
more layers?
|
11 months ago |
mm
|
fa0ba0cee7
|
this looks good
|
11 months ago |
mm
|
64e18eb6cf
|
go back to simpler model
|
11 months ago |
Michael Pilosov
|
95af36221b
|
optimizations
|
11 months ago |
Michael Pilosov
|
d34a6b55d0
|
chkpt
|
11 months ago |
Michael Pilosov
|
9935640a81
|
initial commit
|
11 months ago |