Michael Pilosov, PhD
|
04ff370bbb
|
wip
|
9 months ago |
|
Michael Pilosov, PhD
|
90f08a5edb
|
paths
|
9 months ago |
|
Michael Pilosov, PhD
|
831f17a9b4
|
tweaks + path changes
|
10 months ago |
|
Michael Pilosov, PhD
|
698f6f1b51
|
seeds
|
10 months ago |
|
Michael Pilosov, PhD
|
13dd754ba6
|
nice set of params
|
10 months ago |
|
Michael Pilosov, PhD
|
a97055f282
|
GNU parallel
|
10 months ago |
|
Michael Pilosov, PhD
|
d1b963e05d
|
minimal requirements.
|
10 months ago |
|
Michael Pilosov, PhD
|
f3bc1e90d3
|
ignore npy
|
10 months ago |
|
Michael Pilosov, PhD
|
b95cb8df3d
|
cuda libs
|
10 months ago |
|
Michael Pilosov, PhD
|
527cc285f3
|
drop in cuml
|
10 months ago |
|
Michael Pilosov, PhD
|
95a6adac91
|
lint
|
10 months ago |
|
Michael Pilosov, PhD
|
447b773d03
|
no annotate, update target
|
10 months ago |
|
Michael Pilosov, PhD
|
00cba285c8
|
minor tweaks, check annotations
|
10 months ago |
|
Michael Pilosov, PhD
|
9953327d30
|
copy over color files, use new plotting
|
10 months ago |
|
Michael Pilosov, PhD
|
0ae8414481
|
syntax, no diff
|
10 months ago |
|
Michael Pilosov, PhD
|
2af491c324
|
tweak metric
|
10 months ago |
|
Michael Pilosov, PhD
|
5687f30818
|
back to "correct" metric
|
10 months ago |
|
Michael Pilosov, PhD
|
5def982f12
|
recreate iris looking result. weird though.
|
10 months ago |
|
Michael Pilosov, PhD
|
a9e772f34e
|
restrict experiment, add loop option + dropout
|
10 months ago |
|
Michael Pilosov
|
697030b7df
|
partial unsupervision
|
10 months ago |
|
Michael Pilosov
|
f450611ce3
|
pin requirements
|
10 months ago |
|
Michael Pilosov, PhD
|
0c4990e98c
|
remove depth = 8 and switch to relu
|
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
|
1c116f3f12
|
benchmark supervised again
|
10 months ago |
|
Michael Pilosov, PhD
|
c7ffd09fb4
|
lr scheduler
|
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
|
9e4861a272
|
try unsupervised again, but with 10k random samples
|
10 months ago |
|
Michael Pilosov, PhD
|
e5b6f287a3
|
xkcd colors may be too few to learn from. need 10x
|
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
|
0e561aae4c
|
big batch
|
10 months ago |
|
Michael Pilosov, PhD
|
30470f13bc
|
unsupervised results looking stunning
|
10 months ago |
|
Michael Pilosov, PhD
|
70f56ff9f0
|
cleanup temp files from interrupts
|
10 months ago |
|
Michael Pilosov, PhD
|
3adcc9779a
|
type hint, rename vars
|
10 months ago |
|
Michael Pilosov, PhD
|
a49f166252
|
seems to learn (supervised) consistently now
|
10 months ago |
|
Michael Pilosov, PhD
|
a44580a15b
|
depth of 1 led to consistently bad learning
|
10 months ago |
|
Michael Pilosov, PhD
|
eee8a8b0ba
|
update page
|
10 months ago |
|
Michael Pilosov, PhD
|
6260e7fdd3
|
restrict optimizers
|
10 months ago |
|
Michael Pilosov, PhD
|
467b3f7e57
|
entirely supervised
|
10 months ago |
|
Michael Pilosov, PhD
|
1da8d3194a
|
first one w weighted alpha
|
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
|
948bc31861
|
cull experimental range
|
10 months ago |
|
Michael Pilosov, PhD
|
fff2b88fa1
|
job updates
|
10 months ago |
|
Michael Pilosov, PhD
|
49e6260346
|
experiment loggin setup
|
10 months ago |
