Adding a web interface to a C++ application
One thing that is always sort of a pain is setting up a graphical user interface. This is especially true if you are making an embedded application or something that functions more as a system service...
View ArticleClik here to view.
Dlib 18.6 released: Make your own object detector!
I just posted the next version of dlib, v18.6. There are a bunch of nice changes, but the most exciting addition is a tool for creating histogram-of-oriented-gradient (HOG) based object detectors....
View ArticleMITIE: A completely free and state-of-the-art information extraction tool
I work at a MIT lab and there are a lot of cool things about my job. In fact, I could go on all day about it, but in this post I want to talk about one thing in particular, which is that we recently...
View ArticleClik here to view.
Dlib 18.7 released: Make your own object detector in Python!
A while ago I boasted about how dlib's object detection tools are better than OpenCV's. However, one thing OpenCV had on dlib was a nice Python API, but no longer! The new version of dlib is out and...
View ArticleMITIE v0.2 Released: Now includes Python and C++ APIs for named entity...
A few months ago I posted about MITIE, the new DARPA funded information extraction tool being created by our team at MIT. At the time it only provided English named entity recognition and sported a...
View ArticleClik here to view.
Real-Time Face Pose Estimation
I just posted the next version of dlib, v18.10, and it includes a number of new minor features. The main addition in this release is an implementation of an excellent paper from this year's Computer...
View ArticleMITIE v0.3 Released: Now with Java and R APIs
We just made the next release of MITIE, a new DARPA funded information extraction tool being created by our team at MIT. This release is relatively minor and just adds APIs for Java and R. The project...
View ArticleDlib 18.11 released
The new version of dlib is out. This release contains mostly minor bug fixes and usability improvements, with the notable exception of new routines for extracting local-binary-pattern features from...
View ArticleDlib 18.12 released
I just released the next version of dlib. This time I added tools for computing 2D FFTs, Hough transforms, image skeletonizations, and also a simple and type safe API for calling C++ code from MATLAB....
View ArticlePython Stuff and Real-Time Video Object Tracking
The new version of dlib is out today. As promised, there is now a full Python API for using dlib's state-of-the-art object pose estimation and learning tools. You can see examples of this API here and...
View ArticleClik here to view.
Reinforcement Learning, Control, and 3D Visualization
Over the last few months I've spent a lot of time studying optimal control and reinforcement learning. Aside from reading, one of the best ways to learn about something is to do it yourself, which in...
View ArticleClik here to view.
A Clean C++11 Deep Learning API
Dlib 19.0 is out and it has a lot of new features, like new elastic net and quadratic program solvers. But the feature I'm most excited about is the new deep learning API. There are a lot of existing...
View ArticleDlib 19.1 Released
cuDNN 5.1 is out and it isn't completely backwards compatible with cuDNN 5.0 due to a bug in cuDNN 5.1. For the curious, in cuDNN 5.1 cudnnGetConvolutionBackwardFilterAlgorithm() will select the...
View ArticleClik here to view.
Hipsterize Your Dog With Deep Learning
I'm getting ready to make the next dlib release, which should be out in a few days, and I thought I would point out a humorous new example program. The dog hipsterizer!It uses dlib's new deep learning...
View ArticleClik here to view.
Easily Create High Quality Object Detectors with Deep Learning
A few years ago I added an implementation of the max-margin object-detection algorithm (MMOD) to dlib. This tool has since become quite popular as it frees the user from tedious tasks like hard...
View ArticleClik here to view.
High Quality Face Recognition with Deep Metric Learning
Since the last dlib release, I've been working on adding easy to use deep metric learning tooling to dlib. Deep metric learning is useful for a lot of things, but the most popular application is face...
View ArticleClik here to view.
Vehicle Detection with Dlib 19.5
Dlib v19.5 is out and there are a lot of new features. 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...
View ArticleClik here to view.
Fast Multiclass Object Detection in Dlib 19.7
The new version of dlib is out and the biggest new feature is the ability to train multiclass object detectors with dlib's convolutional neural network tooling. The previous version only allowed you...
View ArticleClik here to view.
Dlib 19.8 is Out
Dlib 19.8 is officially out. There are a lot of changes, but the two most interesting ones are probably the new global optimizer and semantic segmentation examples. The global optimizer is definitely...
View ArticleClik here to view.
A Global Optimization Algorithm Worth Using
Here is a common problem: you have some machine learning algorithm you want to use but it has these damn hyperparameters. These are numbers like weight decay magnitude, Gaussian kernel width, and so...
View ArticleClik here to view.
Correctly Mirroring Datasets
I get asked a lot of questions about dlib's landmarking tools. Some of the most common questions are about how to prepare a good training dataset. One of the most useful tricks for creating a dataset...
View ArticleClik here to view.
Automatic Learning Rate Scheduling That Really Works
Training deep learning models can be a pain. In particular, there is this perception that one of the reasons it's a pain is because you have to fiddle with learning rates. For example, arguably the...
View Article