OrgLion-ML
/
dlib
mirror of https://github.com/davisking/dlib.git
1
0
Fork 0
Code Issues Releases Wiki Activity
5,801 Commits 4 Branches 61 Tags 140 MiB
Commit Graph

5801 Commits

Author SHA1 Message Date
Davis King feb81e1f4f Made fc<> always use a bias and added an fc_no_bias<> for the other case. 2016-04-10 12:10:56 -04:00
Davis King 6acddf99de Just renamed variables to reflect the new meaning of the batch normalization 
running variance output.
 2016-04-10 11:31:24 -04:00
Davis King 538de238fa merged 2016-04-10 10:54:49 -04:00
Davis King f9cb3150d0 upgraded to cudnn v5. Also changed the affine_ layer to not be templated but 
to automatically select the right mode.  The serialization format for bn_
layers has also changed, but the code will still be able to deserialize older
bn_ objects.
 2016-04-10 10:52:40 -04:00
Davis King 5dad959a02 Made the cuda test include some header files to make it a little more 
realistic.
 2016-04-09 23:10:27 -04:00
Davis King c81825c3c2 Made unit test more robust 2016-04-09 19:54:59 -04:00
Davis King 9cd103e545 Minor changes to avoid warnings and a bug in clang. 2016-04-09 12:53:12 -04:00
Davis King b509a16943 Made tests more robust. 2016-04-09 10:07:33 -04:00
Davis King 5fecb30c99 Fixed c++11 test program. 2016-04-09 09:21:17 -04:00
Davis King 945c62bf93 Adjusted test threshold to avoid false test failure. 2016-04-09 09:17:55 -04:00
Davis King b47ab37b24 Improved C++11 detection. 2016-04-09 09:16:57 -04:00
Davis King 6e9ee89ef6 merged 2016-04-08 23:13:48 -04:00
Davis King fe168596a2 Moved most of the layer parameters from runtime variables set in constructors 
to template arguments.  This way, the type of a network specifies the entire
network architecture and most of the time the user doesn't even need to do
anything with layer constructors.
 2016-04-08 23:12:53 -04:00
Davis King 001bca78e3 Improved the add_layer forwarding constructor. Also added repeat_group() 
variable decorator.
 2016-04-08 22:37:28 -04:00
Davis King 0a1464b697 Added global functions for telling cuDNN to prefer fast or memory efficient 
algorithms.
 2016-04-08 19:59:32 -04:00
Davis King eb25bf44a8 fixed spelling error 
--HG--
rename : dlib/test/corellation_tracker.cpp => dlib/test/correlation_tracker.cpp
 2016-04-08 17:31:49 -04:00
Davis E. King a73155e6d0 Merge pull request #98 from e-fominov/corellation-tracker-options 
Corellation tracker options
 2016-04-08 17:28:41 -04:00
Davis King 2cfbd02c2b Fixed bug in mex binding API. 2016-04-08 09:38:23 -04:00
Davis King 03995313c2 Minor change to avoid compiler warnings. 2016-04-08 08:59:06 -04:00
Davis King 545fe6c981 Fixed another compiler error that could happen with the forwarding constructor. 2016-04-08 07:18:15 -04:00
Davis King c5af788e7a merged 2016-04-08 06:41:16 -04:00
Fm f9962fd784 Fixed corellation_tracker abstract docs 2016-04-08 09:43:16 +03:00
Fm 0f1e9f9982 Changed corellation_tracker constructor 2016-04-08 09:39:15 +03:00
Davis King f06dbfd562 Fixed compile time bug in the constructor I just added. 2016-04-07 23:16:17 -04:00
Davis King 9482271ea9 Made it so you can skip giving layer detail objects to a network's constructor 
if they should be default constructed.
 2016-04-07 22:55:17 -04:00
Davis King 3f54286154 merged 2016-04-07 21:24:05 -04:00
Davis King 95182765b6 merged 2016-04-07 21:23:22 -04:00
Davis King 6afc923307 clarified spec 2016-04-07 21:20:36 -04:00
Davis King e378be9c79 merged 2016-04-07 13:02:13 -04:00
Davis King 1ca9c0cc2f Fixed a bug that caused the matrix to throw an error during some assignment 
statements when used inside a matlab mex file.
 2016-04-07 13:01:37 -04:00
Fm d1efcd9487 Added options for corellation tracker 2016-04-07 18:54:07 +03:00
Fm 71af6f4802 Added options for corellation tracker 2016-04-07 18:34:47 +03:00
Davis E. King 05f92e165f Merge pull request #97 from e-fominov/test-corellation-tracker 
Regression test for corellation tracker
 2016-04-07 06:50:52 -04:00
Fm bdfb7b0eb0 Added regression test for corellation_tracker 2016-04-07 13:08:38 +03:00
Evgeniy Fominov 13ea9e581c Added regression test for corellation_tracker 2016-04-07 12:26:37 +03:00
Fm 22ae802385 Added simd8 usage on FHOG features computation 2016-04-05 12:43:54 +03:00
Davis E. King cfe718ea09 Merge pull request #93 from e-fominov/fhog-float 
Using float instead of double for FHOG computations
 2016-04-04 20:09:54 -04:00
Jeffrey Byrne a649591e4a updated aknowledgement 2016-04-04 15:43:12 -04:00
Jeffrey Byrne eef9477514 updated aknowledgement 2016-04-04 15:41:28 -04:00
Jeffrey Byrne 698dbd42ac updated aknowledgement 2016-04-04 15:39:26 -04:00
Evgeniy Fominov 091d95f3af Changed fhog calculations from double to float 2016-04-04 19:57:46 +03:00
Fm ec750ffe7a Changed fhog calculations from double to float 2016-04-04 19:17:45 +03:00
Davis King 5dd1c056c1 merged 2016-04-02 09:35:00 -04:00
Davis King 7fdcfb0bb0 Added input_rgb_image. 2016-04-02 09:34:01 -04:00
Davis E. King b8203b2e54 Merge pull request #91 from e-fominov/msvcx64-sse2-support 
MSVC x64 SSE2 automatical support
 2016-04-01 18:24:42 -04:00
Davis King 4f367471ae Added a member function to get the line intercept from running_gradient. 2016-04-01 11:38:16 -04:00
Fm bb0ac566db MSVC SSE2 automatical support for x64 2016-04-01 14:48:20 +03:00
Fm d3fb8c5f31 MSVC SSE2 automatical support for x64 2016-04-01 14:46:44 +03:00
Davis King 3165ff2892 minor cleanup 2016-03-31 21:11:11 -04:00
Davis King 65f60203ab Added unit test for prelu layer. 2016-03-31 21:10:56 -04:00