7812 Commits (71b303d883f6cea37d256caadeea1c46a0045df2)

 

All Branches   

Search

Author	SHA1	Message	Date
Davis King	71b303d883	Improve the error a user gets when trying to build the pyhton extention on windows but they didn't install visual C++.	4 years ago
Davis King	b9f4da5522	Make cuDNN test project failure print a message saying exactly why it failed.	4 years ago
Davis King	facefa0204	Fix random foreset regression not doing quite the right thing.	4 years ago
Davis King	fe803b566f	add support for cudnn 8.0	4 years ago
Davis King	f8887d8cbb	fix paths	4 years ago
Davis King	2a3cb83afc	Make dlib/__init__.py know the paths to cuda that cmake used. Use those ... paths instead of relying on CUDA_PATH to be set.	4 years ago
Davis King	1515adc744	work around a bug in nvcc	4 years ago
Davis King	7fe355e0ec	Oops, put import statements after path adjustment	4 years ago
Davis King	7fcb6c285d	Add an __init__.py file so we can add paths to CUDA libs on windows.	4 years ago
Davis King	53b6ea3bf5	Record last changeset and set PATCH version to 99	4 years ago
Davis King	5612caa169	Created release v19.20	4 years ago
Davis King	610aa6349a	updated docs	4 years ago
Davis King	3d738e1c2d	sanitize git logs for export to html	4 years ago
Davis King	883101477d	minor cleanup	4 years ago
stoperro	a83242014e	Corrected interpolate_bilinear for lab_pixel. (#2091) ... * * 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	4 years ago
Davis King	693aa0a719	fix build errors in cuda 10.2	4 years ago
Juha Reunanen	c7062aa363	Minor optimization: add shortcut to in-place image resize if size_scale is 1 (#2076)	4 years ago
Adrià Arrufat	64ba66e1c7	fix receptive field comment (#2070)	4 years ago
ncoder-1	8055b8d19a	Update dnn_introduction_ex.cpp (#2066) ... Changed C-style cast to static_cast.	4 years ago
Davis King	253745d29f	fix typo in comment	4 years ago
Davis King	a2e45f00b2	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.	4 years ago
Davis King	0e923cff93	A little bit of cleanup	4 years ago
Adrià Arrufat	55e9c890fd	Add cuda implementation for loss_mean_squared_per_channel_and_pixel (#2053) ... * 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>	4 years ago
Davis King	b42722a75d	Fix DLIB_ISO_CPP_ONLY not working	4 years ago
Davis King	fbb2db2188	fix example cmake script	5 years ago
Adrià Arrufat	b44d9465f6	Fix warning in dnn_trainer initialization list (#2049) ... The thread pool was initialized after the network, so it lead to a reorder warning in GCC 9.3.0	5 years ago
Adrià Arrufat	5a715fe24d	Remove outdated comment from DCGAN example (#2048) ... * Remove outdated comment That comment was there from when I was using a dnn_trainer to train the discriminator network. * Fix case	5 years ago
Davis King	237746fc13	disable in source builds	5 years ago
Adrià Arrufat	e9c56fb21a	Fix warnings while running the tests (#2046) ... * 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	5 years ago
Adrià Arrufat	d1d96e380c	remove branch from cuda kernel (#2045) ... * remove branch from cuda kernel * promote lambda to a global function	5 years ago
Adrià Arrufat	57bb5eb58d	use running stats to track losses (#2041)	5 years ago
Davis King	0057461a62	Promote some of the sub-network methods into the add_loss_layer interface so users don't have to write .subnet() so often.	5 years ago
Davis King	c79f64f52d	make update_parameters() a little more uniform	5 years ago
Davis King	fd0145345e	Fix Use of C++17 deprecated feature: std::iterator #2036	5 years ago
Adrià Arrufat	f42f100d0f	Add DCGAN example (#2035) ... * wip: dcgan-example * wip: dcgan-example * update example to use leaky_relu and remove bias from net * wip * it works! * add more comments * add visualization code * add example documentation * rename example * fix comment * better comment format * fix the noise generator seed * add message to hit enter for image generation * fix srand, too * add std::vector overload to update_parameters * improve training stability * better naming of variables make sure it is clear we update the generator with the discriminator's gradient using fake samples and true labels * fix comment: generator -> discriminator * update leaky_relu docs to match the relu ones * replace not with ! * add Davis' suggestions to make training more stable * use tensor instead of resizable_tensor * do not use dnn_trainer for discriminator	5 years ago
Adrià Arrufat	d610e56c2a	add leaky_relu activation layer (#2033) ... * add leaky_relu activation layer * add inplace case for leaky_relu and test_layer * make clear that alpha is not learned by leaky_relu * remove branch from cuda kernel	5 years ago
Juha Reunanen	74123841bb	To avoid a GPU memory leak, allow passing thread pools to dnn_trainer from outside (#2027) ... * Problem: The CUDA runtime allocates resources for each thread, and apparently those resources are not freed when the corresponding threads terminate. Therefore, each instantiation of dnn_trainer leaks a bit of GPU memory. Solution: Add possibility to pass thread pools from outside. This way, subsequent dnn_trainer instances can use the same threads, and there's no memory leak. * Add helpful comments	5 years ago
scott-vsi	6fc503d242	link against openblasp (#2028) ... openblasp is a parallel implementation of openblas with pthreads found on Centos/Fedora	5 years ago
Adrià Arrufat	1380e6b95f	add loss multiclass log weighted (#2022) ... * add loss_multiclass_log_weighted * fix class name in loss_abstract * add loss_multiclass_log_weighted test * rename test function to match class name * fix typo * reuse the weighted label struct across weighted losses * do not break compatibility with loss_multiclass_log_per_pixel_weighted * actually test the loss and fix docs * fix build with gcc 9	5 years ago
hwiesmann	9185a925ce	Integer conversions generating compiler warnings (#2024) ... * Prevention of compiler warning due to usage of int instead of a size type * Conversion of status type to long to prevent compiler warnings * The returned number of read items from a buffer is specified in numbers of type "streamsize" Co-authored-by: Hartwig <git@skywind.eu>	5 years ago
Facundo Galán	08aeada7d5	Replace result_of by invoke_result for C++17 and above (#2021) ... Co-authored-by: Facundo Galan <fgalan@danaide.com.ar>	5 years ago
scott-vsi	c8a175f569	effect -> affect (#2019)	5 years ago
Davis King	7b35d7b234	removed inappropriate assert	5 years ago
hwiesmann	e7087e5957	Prevention of compiler warning (#2015) ... Co-authored-by: Hartwig <git@skywind.eu>	5 years ago
Adrià Arrufat	c832d3b2fc	simplify resnet definition by reusing struct template parameter (#2010) ... * simplify definition by reusing struct template parameter * put resnet into its own namespace * fix infer names * rename struct impl to def	5 years ago
Davis King	3a53c78ad2	increment imglab version	5 years ago
Davis King	9a33669610	A little bit of cleanup and docs. Also added missing mutex lock.	5 years ago
martin	4ff365a530	imglab: chinese ("automatic") clustering, keyboard shortcuts for zooming (#2007) ... * imglab: add support for using chinese whispers for more automatic clustering * widgets: refactor out zooming from wheel handling * tools/imglab/src/metadata_editor.cpp imglab: add keyboard shortcuts for zooming	5 years ago
Davis King	fc6992ac04	A little bit of cleanup	5 years ago
Adrià Arrufat	10d7f119ca	Add dnn_introduction3_ex (#1991) ... * Add dnn_introduction3_ex	5 years ago