- 09 Apr, 2016 6 commits
-
-
Davis King authored
-
Davis King authored
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.
-
Davis King authored
variable decorator.
-
Davis King authored
algorithms.
-
Davis King authored
--HG-- rename : dlib/test/corellation_tracker.cpp => dlib/test/correlation_tracker.cpp
-
Davis E. King authored
Corellation tracker options
-
- 08 Apr, 2016 13 commits
-
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
Fm authored
-
Fm authored
-
Davis King authored
-
Davis King authored
if they should be default constructed.
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
Davis King authored
statements when used inside a matlab mex file.
-
- 07 Apr, 2016 5 commits
-
-
Fm authored
-
Fm authored
-
Davis E. King authored
Regression test for corellation tracker
-
Fm authored
-
Evgeniy Fominov authored
-
- 05 Apr, 2016 6 commits
-
-
Davis E. King authored
Using float instead of double for FHOG computations
-
Jeffrey Byrne authored
-
Jeffrey Byrne authored
-
Jeffrey Byrne authored
-
Evgeniy Fominov authored
-
Fm authored
-
- 02 Apr, 2016 3 commits
-
-
Davis King authored
-
Davis King authored
-
Davis E. King authored
MSVC x64 SSE2 automatical support
-
- 01 Apr, 2016 7 commits
-
-
Davis King authored
-
Fm authored
-
Fm authored
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
Davis King authored
however, that doesn't really work if we need to compute the gradients with respect to the parameters which the layer attempted to do. So I made the layer's parameters non-learnable so it can continue to be inplace since the main usecase for this layer is to be a fast replacement for bn_ during testing.
-