|
backend
|
handle state in training
|
2016-10-30 00:24:29 +01:00 |
|
compiler
|
consistent naming
|
2016-10-30 00:19:57 +01:00 |
|
dims
|
BatchSeq convenience alias
|
2016-10-26 12:37:48 +01:00 |
|
layers
|
this is no longer test code
|
2016-10-29 00:13:32 +01:00 |
|
activation.jl
|
basic convnet example working
|
2016-09-06 18:11:15 +01:00 |
|
cost.jl
|
revive basic train code
|
2016-09-06 18:10:20 +01:00 |
|
data.jl
|
length for iterators
|
2016-10-30 01:18:20 +01:00 |
|
Flux.jl
|
batched training for char-rnn
|
2016-10-29 23:36:39 +01:00 |
|
model.jl
|
use param object rather than named input
|
2016-10-25 17:57:20 +01:00 |
|
utils.jl
|
batched training for char-rnn
|
2016-10-29 23:36:39 +01:00 |
