OrgLion-ML
/
dlib
mirror of https://github.com/davisking/dlib.git
1
0
Fork 0
Code Issues Releases Wiki Activity
6,589 Commits 4 Branches 61 Tags 140 MiB
Commit Graph

6589 Commits

Author SHA1 Message Date
Davis King 420eba0e6a Added note about logging training parameters. 2017-08-06 11:34:07 -04:00
Davis King 0f2753b754 Changed how we print the network hash. 2017-08-06 08:54:10 -04:00
Davis King 7b26b2d1ff Made dnn_trainer print the network size when logged to an iostream. 2017-08-05 15:24:47 -04:00
Davis King 8b21c89efd Improved how the relaxed mmod overlap settings are determined. 2017-08-04 22:46:46 -04:00
Davis King ed683785ce Added get_synchronization_file() and get_test_one_step_calls() to dnn_trainer. 
Also added an operator<< for dnn_trainer that prints the parameters it's using.

These changes also break backwards compatibility with the previous
serialization format for dnn_trainer objects.
 2017-08-03 15:55:57 -04:00
Davis King 9540ca23ec Added operator<< for the DNN solvers. 2017-08-03 15:47:08 -04:00
Davis King aafde20607 Added operator<< for random_cropper. 2017-08-03 15:40:51 -04:00
Davis King a7d1dc474b Filled out the options for loss_mmod's operator<<. 2017-08-03 15:28:26 -04:00
Davis King 562d1b7519 Clarified spec 2017-08-03 09:36:51 -04:00
Davis King a1f94e167f Fixed spelling error in comment. 2017-08-03 09:14:36 -04:00
Davis King 29db3ee566 Added missing input validation to loss_mmod_. Specifically, the loss layer now 
checks if the user is giving truth boxes that can't be detected because the
non-max suppression settings would prevent them from being output at the same
time.  If this happens then we print a warning message and set one of the
offending boxes to "ignore".
 2017-07-31 19:49:46 -04:00
Davis King bf55c4e8e1 Clarified spec 2017-07-31 19:43:49 -04:00
Davis King 99d5702f03 Gave test_object_detection_function() an option to set how ignore box overlap is tested. 2017-07-30 20:55:04 -04:00
Davis King cb42b8fbe8 merged 2017-07-29 05:52:55 -04:00
Davis King afcd4d8f49 merged 2017-07-29 05:52:32 -04:00
Davis King 3faaa0b865 Minor adjustments to avoid false alarms in cca test. 2017-07-29 05:51:59 -04:00
ᴚ∀W∀ᴎ b4ec8d3d14 differential std::clamp from c++17 with dlib:: prefix to clamp() (#734) 2017-07-29 05:42:42 -04:00
Leo 1c96db9ef6 Fix strange dash in Box-Muller (#732) 2017-07-28 19:03:41 -04:00
Davis King 69d6f7c709 updated ignore file 2017-07-25 15:43:04 -04:00
Davis King 83171f8c5e Updated cmake required version 2017-07-25 15:42:13 -04:00
Davis King 0866d03ade Added cmake scripts and some related tooling that makes it easy to call C++ 
code from java.
 2017-07-25 15:41:30 -04:00
Davis King 968818748a Fixed tabbing 2017-07-24 10:01:30 -04:00
Davis King b4853ce449 Fixed grammar 2017-07-24 10:01:23 -04:00
Davis King 999306e161 Improved errors from libpng when users link against a different version of 
libpng than they built against.
 2017-07-22 11:41:48 -04:00
Davis King 1f5335c1ad Made tensor_conv hold references to the cuda_data_void_ptr work buffers in the 
member area of the class.  This way, we avoid a potential error where the
buffers are reallocated while cuDNN is still using them in the background.
 2017-07-22 07:50:52 -04:00
Evgeniy Fominov 863702f059 cuDNN convolution algorithms shared workspace (#695) 
* added shared workspace

* rewrite shared workspace code

* rename and device-based buffer allocation

* fix cudnn_device_buffer constructors
 2017-07-21 12:37:46 -04:00
Pavan kumar 3e471ade23 Just small typo (#716) 2017-07-19 09:08:28 -04:00
Davis King a621ffb2d9 merged 2017-07-18 22:19:52 -04:00
Davis King e7fe423bc4 Added --sort and also the ability to propagate boxes from one image to the 
next using dlib::correlation_tracker.
 2017-07-18 22:19:29 -04:00
Morosko 6525344fb8 Make http_client compile in C++11 and above (#714) 
* Make http_client compile in C++11 and above

* Optimize file reading
 2017-07-18 09:33:27 -04:00
Juha Reunanen fc92774687 Add per-pixel mean square loss (#690) 
* Add per-pixel mean square loss

* Add documentation of loss_mean_squared_per_pixel_

* Add test case for per-pixel mean square loss: a simple autoencoder

* Review fix: reorder params of function tensor_index, so that the order corresponds to the convention used in the rest of the dlib code base

* Review fix: add breaks as intended, and change the rest of the test accordingly

* Again a case where the tests already work locally for me, but not on AppVeyor/Travis - this commit is a blindfolded attempt to fix the problem
(and it also fixes a compiler warning)
 2017-07-16 07:23:59 -04:00
Davis King daedd9012d Hopefully improved compiler error diagnostic when using gcc and a user misconfigures their build environment. 2017-07-15 22:29:44 -04:00
Joost van Amersfoort 4a4fd91a26 remove linking to libpython on linux/OSX (#703) 
* remove linking to libpython on linux

* add OSX libpython free building

* add automatic discovery of include python dir back in

* make the libs non required for building on manylinux
 2017-07-14 21:12:00 -04:00
Davis King be8b5cd01b Trying another python build test. 2017-07-11 22:17:07 -04:00
Davis King 7a4babb401 Trying again... 2017-07-11 22:02:26 -04:00
Davis King c07a5ccbd1 Add cmake to path for travis 2017-07-11 20:46:29 -04:00
Davis King 4dd11beb2e More python build tests 2017-07-11 19:52:18 -04:00
Davis King 296358929a Try to get travis to give me new boost. 2017-07-11 19:35:56 -04:00
Davis King fb1ad2ef55 Tell travis to use newer boost. 2017-07-11 19:28:08 -04:00
Davis King 7692ea8405 More travis stuff 2017-07-11 18:18:45 -04:00
Davis King c10f43308c Fixing travis-ci config. 2017-07-11 18:16:15 -04:00
Davis King 6266b98773 Make travis-ci build the python api 2017-07-11 18:12:47 -04:00
MambaWong 373ca59369 Update webcam_face_pose_ex.cpp (#702) 
Test on a given video like this cv::VideoCapture cap("Sample.avi") may be broken when the video frames are not enough before the main window is closed by the user.
 2017-07-11 14:11:06 -04:00
Davis King 6081fea5fa Fixed typo in spec. 2017-07-09 12:20:21 -04:00
Davis King f00ec0cb1e Added Juha Reunanen serialize test case, but one with dlib:: in front and one 
without to make sure both types of lookup work.
 2017-07-08 16:53:29 -04:00
Davis King 29897305fd Work around funny name lookup rules for serialize() call. 2017-07-08 16:50:38 -04:00
Davis King 32fb83b3ad Fixed name lookup problem for calls to serialize() on network objects. 2017-07-08 15:56:40 -04:00
Davis King a6602c3717 Improved error message from the svmstruct object detector. 2017-07-07 10:42:29 -04:00
Davis King ebdc064c61 merged 2017-07-07 10:31:26 -04:00
Juha Reunanen 0ed1ce6153 Add new loss for weighted pixel inputs (#685) 
* Add new loss for weighted pixel inputs (may be useful e.g. to emphasize rare classes)

* Deduplicate method loss_multiclass_log_per_pixel_(weighted_)::to_label

* Add a simple test case for weighted inputs
(also, fix a typo in test_tensor_resize_bilienar's name)

* Add loss_multiclass_log_per_pixel_weighted_ to loss_abstract.h

* Decrease the amount of weighting

* There's no need to train for a very long time
 2017-07-07 10:26:29 -04:00