GitLab

* Add example of semantic segmentation using the PASCAL VOC2012 dataset

* Add note about Debug Information Format when using MSVC

* Make the upsampling layers residual as well

* Fix declaration order

* Use a wider net

* trainer.set_iterations_without_progress_threshold(5000); // (was 20000)

* Add residual_up

* Process entire directories of images (just easier to use)

* Simplify network structure so that builds finish even on Visual Studio (faster, or at all)

* Remove the training example from CMakeLists, because it's too much for the 32-bit MSVC++ compiler to handle

* Remove the probably-now-unnecessary set_dnn_prefer_smallest_algorithms call

* Review fix: remove the batch normalization layer from right before the loss

* Review fix: point out that only the Visual C++ compiler has problems.
Also expand the instructions how to run MSBuild.exe to circumvent the problems.

* Review fix: use dlib::match_endings

* Review fix: use dlib::join_rows. Also add some comments, and instructions where to download the pre-trained net from.

* Review fix: make formatting comply with dlib style conventions.

* Review fix: output training parameters.

* Review fix: remove #ifndef __INTELLISENSE__

* Review fix: use std::string instead of char*

* Review fix: update interpolation_abstract.h to say that extract_image_chips can now take the interpolation method as a parameter

* Fix whitespace formatting

* Add more comments

* Fix finding image files for inference

* Resize inference test output to the size of the input; add clarifying remarks

* Resize net output even in calculate_accuracy

* After all crop the net output instead of resizing it by interpolation

* For clarity, add an empty line in the console output

included in the edge graph.  If it isn't then the output labels from
chinese_whispers would be missing faces in this degenerate case.

dimensions in the same format as the mmod_options object (i.e. two lengths
measured in pixels).  This should make defining random_cropping strategies that
are consistent with MMOD settings much more straightforward since you can just
take the mmod_options settings and give them to the random_cropper and it will
do the right thing.

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.

the API for the mmod_options struct slightly.

min and max object height, it's now min and max object size.  This way, if you
have objects that are short and wide (i.e. objects where the relevant dimension
is width rather than height) you will get sensible behavior out of the random
cropper.

* Convert unique_ptr

* Fix passing unique_ptr as copy by value

* Remove scoped_ptr implementation

* Fix missed files

* Move bool cast into tester macro

* Reexport scoped_ptr alias from sockets

* Replace shared_ptr/weak_ptr with stdlib counterparts

* Fix ptr usage through tests compilation

* Bring back dlib smart ptrs as legacy

* Include scoped_ptr directly

* Add explanation about smart_ptr deprecation

the example restarts correctly.