- 01 Aug, 2020 3 commits
-
-
Davis King authored
error: calling a constexpr host function("log1p") from a device function("cuda_log1pexp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this. The error only happens with some versions of CUDA. -
Davis King authored
-
Davis King authored
-
- 26 Jul, 2020 3 commits
-
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
- 25 Jul, 2020 1 commit
-
-
Davis King authored
-
- 22 Jul, 2020 1 commit
-
-
jbfove authored
Previously they were restored to default values, which had the effect of negating the current setting of the calling code (whether set in the compiler options or by pragma previously)
-
- 12 Jul, 2020 1 commit
-
-
Davis King authored
-
- 28 Jun, 2020 2 commits
-
-
stoperro authored
-
Davis King authored
Improve the error a user gets when trying to build the pyhton extention on windows but they didn't install visual C++.
-
- 21 Jun, 2020 1 commit
-
-
Davis King authored
-
- 20 Jun, 2020 2 commits
-
-
Davis King authored
-
Davis King authored
-
- 18 Jun, 2020 2 commits
-
-
Davis King authored
-
Davis King authored
paths instead of relying on CUDA_PATH to be set.
-
- 10 Jun, 2020 1 commit
-
-
Davis King authored
-
- 07 Jun, 2020 2 commits
-
-
Davis King authored
-
Davis King authored
-
- 06 Jun, 2020 4 commits
-
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
- 01 Jun, 2020 2 commits
-
-
Davis King authored
-
stoperro authored
* * Corrected interpolate_bilinear for non-RGB images not to collapse into grayscale (#2089) * * interpolate_bilinear uses now pixel_to_vector for shorter code. * pixels now have operator!=. * * Explicitely float interpolation * Using C++11 static_assert() in interpolation. * * Corrected documentation for interpolate_bilinear, interpolate_quadratic * * Corrected formatting near interpolate_bilinear
-
- 15 May, 2020 1 commit
-
-
Davis King authored
-
- 05 May, 2020 1 commit
-
-
Juha Reunanen authored
-
- 27 Apr, 2020 1 commit
-
-
Adrià Arrufat authored
-
- 22 Apr, 2020 1 commit
-
-
ncoder-1 authored
Changed C-style cast to static_cast.
-
- 19 Apr, 2020 1 commit
-
-
Davis King authored
-
- 18 Apr, 2020 3 commits
-
-
Davis King authored
Reduce code duplication a bit and make equal_error_rate() give correct results when called on data where all detection scores are identical. Previously it would say the EER was 0, but really it should have said 1 in this case.
-
Davis King authored
-
Adrià Arrufat authored
* wip: attempt to use cuda for loss mse channel * wip: maybe this is a step in the right direction * Try to fix dereferencing the truth data (#1) * Try to fix dereferencing the truth data * Fix memory layout * fix loss scaling and update tests * rename temp1 to temp * readd lambda captures for output_width and output_height clangd was complaining about this, and suggested me to remove them in the first, place: ``` Lambda capture 'output_height' is not required to be captured for this use (fix available) Lambda capture 'output_width' is not required to be captured for this use (fix available) ``` * add a weighted_loss typedef to loss_multiclass_log_weighted_ for consistency * update docs for weighted losses * refactor multi channel loss and add cpu-cuda tests * make operator() const * make error relative to the loss value Co-authored-by:Juha Reunanen <juha.reunanen@tomaattinen.com>
-
- 14 Apr, 2020 1 commit
-
-
Davis King authored
-
- 04 Apr, 2020 1 commit
-
-
Davis King authored
-
- 03 Apr, 2020 1 commit
-
-
Adrià Arrufat authored
The thread pool was initialized after the network, so it lead to a reorder warning in GCC 9.3.0
-
- 02 Apr, 2020 1 commit
-
-
Adrià Arrufat authored
* Remove outdated comment That comment was there from when I was using a dnn_trainer to train the discriminator network. * Fix case
-
- 31 Mar, 2020 3 commits
-
-
Davis King authored
-
Adrià Arrufat authored
* fix some warnings when running tests * rever changes in CMakeLists.txt * update example make use of newly promoted method * update tests to make use of newly promoted methods
-
Adrià Arrufat authored
* remove branch from cuda kernel * promote lambda to a global function
-