Mike J Innes
|
ee623f2ed2
|
logloss is exported
|
2017-05-01 12:30:43 +01:00 |
|
Mike J Innes
|
4dc3fa6bd2
|
don't need mxnet here
|
2017-05-01 12:30:37 +01:00 |
|
Mike J Innes
|
f50688e75c
|
update char-rnn
|
2017-04-28 17:14:35 +01:00 |
|
Mike J Innes
|
1edabe6052
|
fix up char-rnn
|
2017-04-27 17:28:32 +01:00 |
|
Michael Krabbe Borregaard
|
a0b8d11f2e
|
add semicolon after readstring
|
2017-03-15 14:56:00 +01:00 |
|
Mike J Innes
|
4d4979b401
|
better alternative to basemodel
|
2017-02-28 16:42:48 +00:00 |
|
Mike J Innes
|
05d988dd74
|
split basemodel/model
|
2017-02-28 15:53:33 +00:00 |
|
Mike J Innes
|
3fa8a55e41
|
this is pointless
|
2017-01-28 22:35:10 +05:30 |
|
Mike J Innes
|
d3e0f455c2
|
magic constants
|
2016-12-15 21:07:07 +00:00 |
|
Mike J Innes
|
a63cd826c2
|
char-rnn temperature
|
2016-12-13 12:27:50 +00:00 |
|
Mike J Innes
|
bdd05157e2
|
dense -> affine
|
2016-11-14 22:16:00 +00:00 |
|
Mike J Innes
|
5b50d58381
|
char-rnn updates
|
2016-11-08 19:22:10 +00:00 |
|
Mike J Innes
|
7cd94b4a5d
|
well, that was easy 😎
|
2016-10-31 11:01:19 +00:00 |
|
Mike J Innes
|
e35380940b
|
finally producing something recognisable
|
2016-10-30 18:32:16 +00:00 |
|
Mike J Innes
|
4517e41226
|
sampling + tweaks
|
2016-10-30 16:07:29 +00:00 |
|
Mike J Innes
|
8db7df3f51
|
api tweaks
|
2016-10-30 14:12:32 +00:00 |
|
Mike J Innes
|
81d9743836
|
export recurrent
|
2016-10-30 11:41:52 +00:00 |
|
Mike J Innes
|
ce0cde0d2b
|
tweaks
|
2016-10-30 00:34:44 +01:00 |
|
Mike J Innes
|
73ff5b4201
|
batched training for char-rnn
|
2016-10-29 23:36:39 +01:00 |
|
Mike J Innes
|
f0779fc77c
|
beginning of char-rnn example
|
2016-10-29 00:16:39 +01:00 |
|