index
:
nerv
bugfix-matrixfree
fastnn
gh-pages
master
rnn
tnn
wrapped-handles
Lua-based toolkit for high-performance deep learning
about
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
nerv
/
layer
/
affine.lua
Commit message (
Expand
)
Author
Age
*
clip on gradient now
Qi Liu
2016-05-09
*
fix bug in affine.lua
Qi Liu
2016-05-09
*
merge affine & lstm_gate & projection layer
Qi Liu
2016-05-09
*
Merge branch 'master' of ssh://speechlab.sjtu.edu.cn:8022/nerv-dev/nerv
beta-1
Determinant
2016-05-05
|
\
|
*
fix param_repo:add bug
Qi Liu
2016-05-05
*
|
make `bind_params` and `init` consistent in `affine.lua`,
Determinant
2016-05-05
|
/
*
add `no_update` attribute to `nerv.MatrixParam`; add corresponding
Determinant
2016-05-03
*
...
Determinant
2016-04-28
*
add doc
Determinant
2016-04-28
*
fix bug in passing err_input to network; gen zero vectors for bias
alpha-3.3
Determinant
2016-03-30
*
fix bug of momentum & update mse layer
Qi Liu
2016-03-29
*
major change: clearer param binding semantics; permit rebinding; enable
Determinant
2016-03-10
*
fixed some minor problem
txh18
2016-02-16
*
improve parameter auto-detection
Determinant
2016-02-16
*
move curand_gen out of the matrix layout
Determinant
2016-02-15
*
try a basic merge
Determinant
2016-02-15
*
changed auto-generating params, won not save in global_conf.param
txh18
2015-11-25
*
let affine supported multiple inputs
txh18
2015-11-24
*
small bug fix
txh18
2015-11-23
|
\
|
*
correct the use of self.gconf
Determinant
2015-11-23
*
|
merge in recent changes about param updates
txh18
2015-11-23
|
\
\
|
*
|
small bug fix
txh18
2015-11-23
|
|
/
|
*
use consistent update calc; clean up code; no need for `direct_update`
Determinant
2015-11-21
*
|
working on automatic parameter for layers
txh18
2015-11-20
|
/
*
added atomicAdd for select_linear update, however, the result still seems unr...
txh18
2015-11-17
*
change updateEI to update_by_err_input
txh18
2015-11-16
*
coding style changes
txh18
2015-11-16
*
unified param updates, now direct_update is the same speed with undirect_update
txh18
2015-11-16
*
used os.clock() for timer
txh18
2015-11-16
*
fixed direct update, did not know the result
txh18
2015-11-16
*
got good result when batch_size=1, strange!
txh18
2015-11-11
*
Merge pull request #6 from yimmon/master
Ted Yin
2015-10-12
|
\
|
*
kaldi mpe training support
Yimmon Zhuang
2015-09-18
*
|
enable user to set direct_update in gconf; use direct_update in the example
Determinant
2015-10-09
|
/
*
major change: use luarocks to manage project
Determinant
2015-06-22