dlib C++ Library News

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

See http://dlib.net/release_notes.html for release details.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

See http://dlib.net/release_notes.html for release details.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

See http://dlib.net/release_notes.html for release details.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

See http://dlib.net/release_notes.html for release details.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

See http://dlib.net/release_notes.html for release details.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

See http://dlib.net/release_notes.html for release details.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

See http://dlib.net/release_notes.html for release details.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

See http://dlib.net/release_notes.html for release details.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

See http://dlib.net/release_notes.html for release details.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This is a bugfix release. See http://dlib.net/release_notes.html for details.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release adds a bunch of new routines to the Python API. It also includes an auto-ML tool for training RBF-SVMs and various other usability improvements and bug fixes.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release adds about 50 new functions and classes to dlib's Python API. It also simplifies building a little and fixed some bugs.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release fixes a bug introduced in v19.11 which prevented grayscale images from being used via dlib's Python interface.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release adds a bunch of new image processing routines as well as many minor usability improvements and bug fixes.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release removes the need for Boost.Python when using dlib via Python. This makes compiling the Python interface to dlib much easier as there are now no external dependencies.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release includes a lot of bug fixes, usability enhancements, and speedups. It also includes a new global optimization algorithm as well as new examples showing how to do semantic segmentation using dlib's deep learning tooling.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release upgrades dlib's CNN+MMOD object detector to support creating multi-class detectors. It also includes significant speed improvements, allowing the detector to run at 98fps when executed on a NVIDIA 1080ti GPU. This release also adds a new
5 point face landmarking model that is over 10x smaller than the 68 point model, runs faster, and works with both HOG and CNN generated face detections. It is now the recommended landmarking model to use for face alignment.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release brings a lot of new features to dlib. There is a dlib to caffe converter, a bunch of new deep learning layer types, cuDNN v6 and v7 support, and a bunch of optimizations that make things run faster in different situations, like ARM NEON support, which makes HOG based detectors run a lot faster on mobile devices. However, the coolest new feature is an upgrade to the CNN+MMOD object detector to support detecting objects with varying aspect ratios.... read more

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This is a bug-fix release which fixes a slow resource leak that could occur when using cuDNN.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release adds a number of new features, most notably new deep learning tools including a state-of-the-art face recognition example using dlib's deep learning API. See http://dlib.net/dnn_face_recognition_ex.cpp.html for an introduction.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release adds a number of new features, most important of which is a deep convolutional neural network version of the max-margin object detection algorithm. This tool makes it very easy to create high quality object detectors. See http://dlib.net/dnn_mmod_ex.cpp.html for an introduction.... read more

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release adds support for cuDNN 5.1 as well as a number of minor bug fixes and usability improvements.

The latest release of the library can be downloaded from http://dlib.net

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release adds a deep learning toolkit to dlib that has a clean and fully documented C++11 API. It also includes CPU and GPU support, binds to cuDNN, can train on multiple GPUs at a time, and comes with a pretrained imagenet model based on ResNet34.

The release also adds a number of other improvements such as new elastic net regularized solvers and QP solvers, improved MATLAB binding tools, and other usability tweaks and optimizations.... read more

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release has focused on build system improvements, both for the Python API and C++ builds using CMake. This includes adding a setup.py script for installing the dlib Python API as well as a make install target for installing a C++ shared library for non-Python use.... read more

Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

This release adds new clustering tools as well as upgrades the shape_predictor to allow training on datasets with missing landmarks. It also includes bug fixes and minor usability improvements.

The latest release of the library can be downloaded from http://dlib.net