nerv - Lua-based toolkit for high-performance deep learning

	Commit message (Collapse)	Author	Age
*	fix minor bugs in cumatrix; clean up part of code	Determinant	2015-06-07
\|
*	fix memory leak in profiling; other minor changes	Determinant	2015-06-07
\|
*	...	Determinant	2015-06-06
\|
*	add ASR DNN trainer	Determinant	2015-06-06
\|
*	add get_params to all layers	Determinant	2015-06-05
\|
*	add close method for ChunkFile, fix #18	Determinant	2015-06-05
\|
*	add profiling; add ce accurarcy; several other changes	Determinant	2015-06-05
\|
*	demo now works (without random shuffle)	Determinant	2015-06-03
\|
*	fix a bug: input[1] should be input[2] (since Lua arrays are 1-based)	Determinant	2015-06-02
\|
*	add ParamRepo, LayerRepo, DAGLayer	Determinant	2015-06-02
\|
*	add preprocessing layers and change layer constructor interface	Determinant	2015-06-02
\|
*	rename param file to chunk file (intend to generalize it)	Determinant	2015-05-30
\|
*	add softmax + ce layer; test_dnn_layers produces the same result as TNet	Determinant	2015-05-28
\|
*	add mul_elem and log_elem; add dimension checking in cumatrix methods	Determinant	2015-05-28
\|
*	Merge branch 'master' of https://github.com/cloudygoose/nerv into ↵	Determinant	2015-05-28
\|\ \| \| \| \| \| \| \| \| \| \| \| \|	cloudygoose-master Conflicts: examples/cumatrix_from_mmatrix.lua
\| *	modified copy_from(d/h), copy_to(d/h)	txh18	2015-05-27
\| \|
* \|	change softmax to in-place operation and fix memory leak	Determinant	2015-05-28
\|/
*	...	txh18	2015-05-26
\|
*	added nerv_matrix_(get_dataref_value) and tested in ↵	txh18	2015-05-26
\| \| \| \|	examples/mmatrix_example, however it is a little strange to return 101
*	correct the oop_example	Determinant	2015-05-26
\|
*	add "copy from/to cumatrix" functionality	Determinant	2015-05-25
\|
*	rewrite the oop example	Determinant	2015-05-25
\|
*	...	Determinant	2015-05-25
\|
*	move example files to a dedicated directory	Determinant	2015-05-25