Commit Graph

6611 Commits

Author SHA1 Message Date
Davis King
96619c859f merged 2017-08-15 09:32:26 -04:00
Davis King
4541a1b90a Fixed grammar 2017-08-14 21:36:18 -04:00
Davis King
d6a1e273c0 Updated solvers to correctly pull in cont_'s bias parameter multipliers. 2017-08-14 14:04:16 -04:00
Davis King
9043c7415e Added extract_ layer 2017-08-14 13:50:47 -04:00
Davis King
525cfc71af Added more tests for copy_tensor() 2017-08-14 12:48:37 -04:00
Davis King
7078cfaff5 Added an "add_to" option to tt:copy_tensor(). There was also a bug in the
concat layer's backward() method.  It was assigning the gradient to previous
layers instead of adding the gradient, as required by the layer interface
specification.  This change also noticeably speeds up concat layers since only
one CUDA kernel launch now happens per concat operation, rather than one
kernel launch for each sample in a tensor.
2017-08-14 12:28:26 -04:00
Davis King
89c9267e46 Made copy_tensor() use cudaMemcpyAsync() rather than cudaMemcpy(). 2017-08-14 09:52:53 -04:00
Davis King
aafa411672 Added mult_prev layer. 2017-08-11 17:47:19 -04:00
Davis King
f7310f4bbc Added multiply_zero_padded() 2017-08-11 16:39:00 -04:00
Davis King
46a02d9447 Made swig always run when you rebuild to avoid stale swig outputs. 2017-08-10 17:05:35 -04:00
Davis King
4ab360e439 Added DLIB_NO_ABORT_ON_2ND_FATAL_ERROR for dlib::fatal_error as a generic
switch for use in plugin environments.
2017-08-10 16:07:42 -04:00
Davis King
2630029cb4 Fixed missing java:: qualifiers. 2017-08-10 16:07:12 -04:00
Davis King
e99d47cc7c Removed exit call on load library failure. 2017-08-10 15:31:02 -04:00
Davis King
44a62b19d0 A bit of path cleanup 2017-08-10 15:16:21 -04:00
Davis King
8f3249a438 merged 2017-08-10 14:38:59 -04:00
Davis King
ae13ad800e Added more options for controlling the install folder paths. 2017-08-10 14:38:41 -04:00
Davis King
af88b0d56f merged 2017-08-09 21:42:29 -04:00
Davis King
d9f93548dd Fixed a bug in the warning message about NMS overlap where it would sometimes false alarm. 2017-08-09 21:42:14 -04:00
Davis King
d62c5a7c8e merged 2017-08-09 12:20:06 -04:00
Davis King
cf24f02507 Added an object that lets you hold a copyable reference to a java array. Also
renamed the objects and generally improved documentation.
2017-08-09 12:19:41 -04:00
Davis King
fa5c666b6e Added an overload of mat() that takes a row stride value. 2017-08-08 15:10:17 -04:00
Davis King
594df9a66d Relaxes test to avoid false alarms. 2017-08-08 15:00:38 -04:00
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