aboutsummaryrefslogtreecommitdiff
Commit message (Expand)AuthorAge
* used os.clock() for timertxh182015-11-16
* fixed direct update, did not know the resulttxh182015-11-16
* added timertxh182015-11-15
* merge lr schedule changetxh182015-11-15
|\
| * got good PPL for H400...cloudygoose2015-11-15
* | added msr_sc settxh182015-11-15
|/
* small bug: lr_halftxh182015-11-13
* ...txh182015-11-13
* added random seedtxh182015-11-13
* added loadstringtxh182015-11-13
* saving param file for every itertxh182015-11-13
* change ppl_net to ppl_alltxh182015-11-13
* added wcost for select_linear layertxh182015-11-12
* cleaning files...txh182015-11-12
* get good PPL for h300, see m-tests/LOG-tnn-h300txh182015-11-12
* added a little debug info in readertxh182015-11-11
* got good result when batch_size=1, strange!txh182015-11-11
* bug fix : changed zero-filling across borderstxh182015-11-10
* small bug in lmseqreadertxh182015-11-09
* small bug about zeroing errortxh182015-11-09
* another bit error bug foundtxh182015-11-09
* serious bug about bit operation in tnntxh182015-11-08
* switched to softmax_ce_ttxh182015-11-08
* ih[0] nolonger zerotxh182015-11-08
* trying to test softmax_ce_ttxh182015-11-08
* meet a bug, don not know whytxh182015-11-07
* ready to test on ptbtxh182015-11-07
* writing the schedulertxh182015-11-06
* added cross-border flushtxh182015-11-06
* first small tnn test seems to worktxh182015-11-06
* working on TNN:net_propagatetxh182015-11-03
* still working on TNNtxh182015-11-03
* ...txh182015-11-02
* ...txh182015-11-02
* still working on the tdag layertxh182015-11-01
* start implementing tdag_layertxh182015-10-30
* finished a simple version of lmseqreadertxh182015-10-30
* still working in lmseqreadertxh182015-10-30
* doingtxh182015-10-28
* TODO:implement lmseqreadertxh182015-10-28
* changed copy_rows_fromd_by_idx a bit to make it clearertxh182015-10-28
* added update_select_rows to doctxh182015-10-28
* added update_select_rows for select_linear:update speed-uptxh182015-10-27
* using copy_rows_fromd for select-liner:propagate, TODO:speed up select-linear...txh182015-10-26
* discovered a copy_rows_fromd_by_idx that can be usedtxh182015-10-26
* simple doc changetxh182015-10-25
|\
| * changed doc pointer in the main markdowntxh182015-10-25
* | added timer for profilingtxh182015-10-25
* | lmptb can be run after merge from mastertxh182015-10-23
* | Just come back, let's merge the new mastertxh182015-10-23
|\|