Commit Graph

601 Commits

Author SHA1 Message Date
Davis King
a1eea964b6 Added more comments 2017-05-05 05:42:13 -04:00
cclough
5fa4533b9a Update CMakeLists.txt (#566) 2017-04-30 20:48:51 -04:00
Davis King
df5a087b03 Made it more obvious that this file is a cmake tutorial. Also added a few more comments about how to use cmake. 2017-03-24 09:15:43 -04:00
Davis King
67db08f5a6 Made example cmake use dlib::dlib link name. Also made the installed
cmake config for dlib enable C++11.
2017-02-28 04:43:32 -05:00
Alain Vaucher
b41455fd26 Change minimum CMake version that supports the introduced features 2017-02-27 18:23:28 +01:00
Davis King
e4402cf575 Don't build face recognition example if GUI support isn't enabled. 2017-02-18 15:33:09 -05:00
Davis King
7747be8302 cleanup 2017-02-12 20:53:02 -05:00
Davis King
11016884ed Avoid crashing visual studio 2017-02-12 13:28:42 -05:00
Davis King
c5b29d985b Added try/catch block to main 2017-02-11 16:45:22 -05:00
Davis King
d7a6cd4960 fixed grammar in comment 2017-02-11 15:36:24 -05:00
Davis King
fe1a15f32a Added face recognition example 2017-02-11 14:52:47 -05:00
Davis King
45d047de80 Minor cleanup 2017-02-09 12:38:39 -05:00
Davis King
57ca3e5459 Made network smaller. 2017-02-08 22:53:55 -05:00
Davis King
6c6c25a344 merged 2017-01-22 11:32:27 -05:00
RangerUFO
0f60ba365b Fix comments typo in dnn_introduction2_ex (#405) 2017-01-22 10:36:40 -05:00
Davis King
3793e29e0e Added comments about test_one_step() 2017-01-22 10:25:29 -05:00
Davis King
bf36a846de Changed build order to see if it prevents travis from crashing. 2016-12-18 23:35:25 -05:00
Davis King
093f709a9a Minor improvement to example 2016-12-18 20:52:45 -05:00
Davis King
ab1575da20 more cleanup 2016-12-18 13:20:37 -05:00
Davis King
b87ecad51e Improved example 2016-12-18 13:10:13 -05:00
Davis King
fd13230486 Finished the more complex metric learning example and added some example data. 2016-12-17 20:41:36 -05:00
Davis King
f4b3c7ee0f Improved example 2016-12-17 16:46:39 -05:00
Davis King
f28d2f7329 Cleaned up example 2016-12-17 16:11:18 -05:00
Davis King
4d121e7e08 Added another metric learning example 2016-12-17 14:29:29 -05:00
Davis King
cb198afc3f Added metric learning example 2016-12-17 10:56:27 -05:00
Davis King
2787edc9bd Improved error messages about non-C++11 compilers and made the example cmake
file a little clearer on this issue.
2016-10-09 18:13:21 -04:00
Davis King
f5da9fe2b0 Changed cmake so it compiles most of the DNN examples when using visual studio. 2016-10-08 15:28:58 -04:00
Davis King
d4958e8a8e Evgeniy Fominov's changes that avoid compiler bugs in Visual Studio. 2016-10-08 14:27:34 -04:00
Davis King
fee64827b7 Made the upsampling conditional on the image not being huge already. 2016-10-07 22:07:13 -04:00
Davis King
b5c43a6efd Merge branch 'skip_gui_examples' of git://github.com/miscellanea/dlib into miscellanea-skip_gui_examples
Conflicts:
	examples/CMakeLists.txt
2016-10-02 17:52:39 -04:00
Davis King
56f4e19afa Added comments 2016-10-02 16:43:11 -04:00
Davis King
d53d49ebb8 Larger mustache :) 2016-10-02 14:33:22 -04:00
Davis King
67c1a79820 Added test image for dog mmod example program 2016-10-02 13:37:47 -04:00
Davis King
16cedfd92e Added more mmod examples. 2016-10-02 13:00:07 -04:00
Davis King
482b3a61b1 Simplified the network definition slightly 2016-10-02 12:54:14 -04:00
Xi Deng
ea20f5e2ca skip examples which need GUI when DLIB_NO_GUI_SUPPORT is defined 2016-10-01 18:49:57 -07:00
Davis King
05bbe4f4bb Fixed spelling error in comment 2016-09-30 23:09:03 -04:00
Davis King
4a408d5e07 Fixed example 2016-09-05 15:40:54 -04:00
Davis King
d5dc371ff8 Added random_cropper and DNN MMOD example programs. 2016-09-05 15:39:31 -04:00
Davis King
9e42f86cd3 Adjusted face boxes so they are a little bit more accurately placed. 2016-09-05 15:38:44 -04:00
Davis King
87efe17225 Added a call to set_all_bn_running_stats_window_sizes() to set this value to
what it was when this example was trained (since I just modified the default
value in dlib to something else).
2016-09-05 15:00:52 -04:00
Davis King
91150823eb Simplified example to show only the C++11 version of the code. 2016-08-30 14:58:38 -04:00
Davis King
4ee1f6644d Made thread_pool and parallel_for propagate exceptions from task threads to
calling code.
2016-08-30 14:44:46 -04:00
Davis King
02d8ebc903 fixed typo in example 2016-08-24 06:56:35 -04:00
Davis King
4f0c2ba092 Fixed typo in network definition. 2016-08-22 14:53:26 -04:00
Davis King
bdbc8e418b Renamed something to avoid name clash with standard library. 2016-07-22 16:22:57 -04:00
Evgeniy Fominov
bbeac285d1 Shape predictor trainer optimizations (#126)
* Shape predictor trainer optimizations

* Fixed performance leak in single thread mode & made VS2010 support
2016-07-22 09:11:13 -04:00
Davis King
5e550a261e Added some more comments 2016-06-25 18:31:21 -04:00
Davis King
15f4081cdf fixed compiler warning 2016-06-25 13:03:12 -04:00
Davis King
a9343acc51 Changed code so the validation listing file doesn't have to be in the imagenet
root folder.
2016-06-25 12:31:59 -04:00
Davis King
efcdc871e4 fixed compiler warnings 2016-06-25 11:17:07 -04:00
Davis King
f88f784a4e Minor formatting cleanup 2016-06-25 09:47:36 -04:00
Davis King
2469352e95 fixed typo 2016-06-25 09:42:22 -04:00
Davis King
fcf7ab6daa Updated examples to refer to the correct file names. 2016-06-25 09:40:11 -04:00
Davis King
a76b642a4e renamed examples
--HG--
rename : examples/dnn_mnist_advanced_ex.cpp => examples/dnn_introduction2_ex.cpp
rename : examples/dnn_mnist_ex.cpp => examples/dnn_introduction_ex.cpp
2016-06-25 09:34:53 -04:00
Davis King
541ce716b9 Added the program that made the resnet model. 2016-06-25 09:26:51 -04:00
Davis King
1123eaa134 Changed the message that cmake displays when opencv isn't found so users don't get confused. 2016-06-24 01:28:52 -04:00
Davis King
87493f4971 Added some comments 2016-06-22 22:30:45 -04:00
Davis King
f453b03f39 Added an example showing how to classify imagenet images. 2016-06-22 22:26:48 -04:00
Fm
cc38772715 #pragma warning moved to dnn.h 2016-06-22 18:09:26 +03:00
Fm
2e741703ef removed wrong empty line 2016-06-22 17:54:28 +03:00
Fm
9930d3279e removed comment form net printing 2016-06-22 17:53:37 +03:00
Fm
f3b0159ef1 #pragma warning for C4503 and /bigobj 2016-06-22 17:51:06 +03:00
Fm
63c2465f32 Added compiler flags for VS compiling DNN samples without warnings 2016-06-22 17:22:43 +03:00
Davis King
1c01eaec1d updated example comments 2016-06-11 11:54:44 -04:00
Davis King
6e0f13ba06 minor cleanup 2016-05-30 13:14:04 -04:00
Davis King
53e9c15811 Clarified some parts of the example. 2016-05-30 08:50:28 -04:00
Fm
d32bcdfa3d Changed concat syntax into concat1, concat2..., made dtest more readable:: 2016-05-27 09:56:00 +03:00
Fm
2f7d3578d2 Added layer access and printing examples to inception sample 2016-05-26 19:40:10 +03:00
Fm
1f0318e222 depth_group replaced with concat layer 2016-05-26 17:43:54 +03:00
Fm
93e786db6c Merge branch 'master' of https://github.com/davisking/dlib into dnn_group_layer 2016-05-26 17:15:56 +03:00
Davis King
b9332698fe updated example 2016-05-23 22:01:47 -04:00
Davis King
5e70b7a2c6 Cleaned up code a little and made the example use a better version of the architecture. 2016-05-22 13:17:10 -04:00
Davis King
0cd76f899b Added an error message if a camera isn't available. 2016-05-18 22:22:56 -04:00
Fm
28c4a48281 Grouping layer added 2016-05-17 13:07:04 +03:00
Davis King
ee2a0070db Added comment to show how to deserialize a network. 2016-05-15 14:52:33 -04:00
Davis King
ba0f7c5c53 Added a function to dnn_trainer that lets you query the "steps without
progress" estimate.  I also renamed the get/set functions for the shrink amount
to have a consistent name and use the word "factor" instead of "amount".
2016-05-15 14:48:06 -04:00
Davis King
13cc545da3 clarified comments. 2016-05-15 14:31:06 -04:00
Davis King
66166c674d Changed the solver interface to take the learning rate and the layer details
object as an input.  This allows the solvers to exhibit a more complex behavior
that depends on the specific layer.  It also removes the learning rate from the
solver's parameter set and pushes it entirely into the core training code.
This also removes the need for the separate "step size" which previously was
multiplied with the output of the solvers.

Most of the code is still the same, and in the core and trainer the step_size
variables have just been renamed to learning_rate.  The dnn_trainer's relevant
member functions have also been renamed.

The examples have been updated to reflect these API changes.  I also cleaned up
the resnet definition and added better downsampling.
2016-05-14 20:30:45 -04:00
Davis King
1e70c721a4 Made example use the "everything" version of avg pooling. 2016-05-07 14:30:42 -04:00
Davis King
4a7633056c Fixed avg pooling filter sizes to avoid errors with the new rules about
non-one based strides.
2016-05-04 21:40:29 -04:00
Davis King
1f0705ae92 clarified example 2016-04-28 19:41:27 -04:00
Davis King
d31723ff45 Fixed typo in example 2016-04-19 06:44:31 -04:00
Davis King
b16cc99e8f Added comments about using multiple GPUs 2016-04-18 22:48:07 -04:00
Davis King
603d474352 - Renamed network_type::num_layers to network_type::num_computational_layers.
- Made layer() recurse into repeat objects so that the index given to layer()
  does what you would expect.
- Added an operator<< for network objects that prints the network architecture.
2016-04-16 10:50:15 -04:00
Davis King
61591b13e2 Seeded random number generator with the clock since that's generally a good
thing to do for this kind of training.
2016-04-11 23:11:18 -04:00
Davis King
02c27ff916 fixed formatting 2016-04-11 23:06:32 -04:00
Davis King
423cd85594 renamed a file
--HG--
rename : examples/dnn_mnist_resnet_ex.cpp => examples/dnn_mnist_advanced_ex.cpp
2016-04-11 22:57:11 -04:00
Davis King
902a2beeaf Fleshed out these examples more. 2016-04-11 22:55:49 -04:00
Davis King
02b844ea5c Fixed grammar and clarified a few things. 2016-04-11 21:18:14 -04:00
Davis King
7d7c932f29 Added a narrative to this example. 2016-04-10 17:30:45 -04:00
Davis King
67a81c1c51 Made examples work with new fc<> template. 2016-04-10 12:11:19 -04:00
Davis King
f9cb3150d0 upgraded to cudnn v5. Also changed the affine_ layer to not be templated but
to automatically select the right mode.  The serialization format for bn_
layers has also changed, but the code will still be able to deserialize older
bn_ objects.
2016-04-10 10:52:40 -04:00
Davis King
fe168596a2 Moved most of the layer parameters from runtime variables set in constructors
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.
2016-04-08 23:12:53 -04:00
Davis King
030f5a0a76 A bit more cleanup 2016-03-27 10:50:52 -04:00
Davis King
47bdf95fbe added more stuff to example 2016-03-27 10:29:30 -04:00
Davis King
8f0bda5f82 Changed this example to be another mnist example so it runs in a non-insane
amount of time.

--HG--
rename : examples/dnn_mit67_ex.cpp => examples/dnn_mnist_resnet_ex.cpp
2016-03-26 23:16:43 -04:00
Davis King
8d3ec0f9d3 Removed cruft 2016-03-26 23:07:38 -04:00
Davis King
517858adf5 changed to run on image net 2016-02-27 09:23:18 -05:00
Davis King
0ecff0e6a4 Removed gif filtering 2016-02-08 09:13:02 -05:00
Davis King
d1b307a8ee Added some dnn examples. 2016-02-06 22:39:43 -05:00
Davis King
ab4920a4cb added missing #include 2015-08-11 06:51:35 -04:00
Davis King
0c561f2b89 Switched more URLs to dlib.net rather than sourceforge.net. 2015-07-24 08:15:40 -04:00
Davis King
1294d6d398 fleshed out this example with comments 2015-06-02 17:47:46 -04:00
Fabio Perez
5fb4c584bd Revise help message 2015-05-30 22:00:36 -03:00
Davis King
52f3e558a4 Added initial version of model predictive control example program. 2015-05-30 19:04:50 -04:00
Davis King
0d6830a48d added comments about using imglab 2015-03-29 16:47:37 -04:00
Davis King
a80553612a cleaned up examples 2015-03-22 19:33:17 -04:00
Davis King
76230b9971 Added an example program for the new perspective_window object. 2015-03-22 19:22:07 -04:00
Davis King
5694fada70 Added spectral_cluster() example 2015-02-11 07:55:42 -05:00
Davis King
27510c8a09 Added comments 2015-02-03 15:33:11 -05:00
Davis King
35aba916d3 Added an example for the correlation_tracker 2015-02-03 14:01:37 -05:00
Davis King
4d223d4d54 Made example's CMakeLists.txt file a little more tutorial like. 2015-01-31 09:43:57 -05:00
Davis King
de37509455 added a SQLite example program 2015-01-29 20:53:01 -05:00
Davis King
a9c5c98d56 Added sqlite example. Needs comments 2015-01-27 23:40:53 -05:00
Davis King
7596c094a6 fixed spelling error in comment 2015-01-26 17:58:35 -05:00
Davis King
afa4fe0c23 Fixed some grammar and added a note about the bias term. 2015-01-05 17:39:37 -05:00
Davis King
773fe59a34 Fixed grammar 2014-12-27 15:05:25 -05:00
Davis King
f3da116159 Added an example for svm_c_trainer. 2014-12-09 18:13:45 -05:00
Davis King
ad99a6668e Added an example program for the new hough_transform object. 2014-12-09 17:40:19 -05:00
Davis King
bb673f4099 Added example of accessing individual pixels 2014-12-09 08:08:02 -05:00
Davis King
f00c7e0f42 Added max cost assignment example program 2014-12-07 12:11:13 -05:00
Davis King
664ea355f4 Another minor cmake change to avoid warnings 2014-12-06 08:34:19 -05:00
Davis King
ae826a408f Increased min required cmake version to avoid warnings
from OpenCV cmake scripts.
2014-11-15 12:10:31 -05:00
Davis King
dac39d2b95 Added an example showing how to use OpenCV's frame grabber
for face pose estimation.
2014-11-15 11:39:26 -05:00
Davis King
3eae0bcb00 Changed example to avoid tying a stream to itself since some iostream libraries
have a bug that causes them to crash when you do this.
2014-09-30 19:21:38 -04:00
Davis King
f4f395975e Added scope qualifiers to some mutex objects to avoid a name collision
in newer versions of clang.
2014-09-27 09:57:28 -04:00
Davis King
5c78a9c3a6 Updated style sheet so face parts aren't all smashed together when viewed in a
browser.
2014-09-17 20:37:26 -04:00
Davis King
bd4056346b Added code to show how to chip out the faces. 2014-09-06 15:44:09 -04:00
Davis King
5e4aaf2e53 improved examples 2014-08-24 10:37:19 -04:00
Davis King
b191400a00 Added initial version of shape training example 2014-08-21 22:42:48 -04:00
Davis King
5ae170c461 Added a face landmarking example program 2014-08-21 22:11:55 -04:00
Davis King
dd3bf1f2c5 Changed the example to recommend using something like the f1-score when using
BOBYQA for model selection.
2014-06-23 16:06:23 -04:00
Davis King
e3af40d5a5 Updated example to use evaluate_detectors() 2014-05-26 18:46:35 -04:00
Davis King
c6d778eaf9 Made the examples use the new simplified file serialization API. 2014-05-08 21:07:56 -04:00
Davis King
be7457770e Fixed minor typos 2014-04-26 19:56:18 -04:00
Davis King
d763696f68 Added an example program showing how to setup a logger hook 2014-04-26 17:32:06 -04:00
Davis King
2821926236 merged changes and updated abstract file. 2014-04-22 20:13:47 -04:00
Davis King
137b7f80c8 Simplified example program. 2014-04-05 16:56:48 -04:00
Csaba Kertesz
31078adee9 Add maximal iterations option for relevance vector machine trainer 2014-03-16 12:19:19 +01:00
Davis King
8e1e548a70 Updated this example to use the scan_fhog_pyramid version of the object
detector since it is much more user friendly.
2014-03-08 13:12:48 -05:00
Davis King
1e9a6297dc fixed grammar 2014-01-12 10:15:46 -05:00
Davis King
e66fa51ebe clarified examples 2014-01-11 22:40:43 -05:00
Davis King
4f8a93975f clarified example 2014-01-11 14:52:28 -05:00
Davis King
015727cd5f clarified example 2014-01-11 11:30:52 -05:00
Davis King
ba37c88fbf Clarified examples now that we have more object detectors in the library. 2014-01-11 10:40:39 -05:00
Davis King
20afefd79b clarified example 2014-01-09 23:23:04 -05:00
Davis King
c7346758d8 improved example program documentation 2014-01-09 23:19:44 -05:00
Davis King
f698db9cb5 Slightly improved example. Still needs a lot of work though. 2014-01-05 20:01:49 -05:00
Davis King
20dde81bd1 Added comments to this example program 2014-01-05 13:53:21 -05:00