Dlib. Clean C++11 Deep Learning API

	Dlib. 개요
	특징.- 알고리듬 및 기능. Machine Learning Algorithms Deep Learning Conventional SMO based Support Vector Machines for classification and regression Reduced-rank methods for large-scale classification and regression Relevance vector machines for classification and regression General purpose multiclass classification tools A Multiclass SVM A tool for solving the optimization problem associated with structural support vector machines. Structural SVM tools for sequence labeling Structural SVM tools for solving assignment problems Structural SVM tools for object detection in images Structural SVM tools for labeling nodes in graphs A large-scale SVM-Rank implementation An online kernel RLS regression algorithm An online SVM classification algorithm Semidefinite Metric Learning An online kernelized centroid estimator/novelty detector and offline support vector one-class classification Clustering algorithms: linear or kernel k-means, Chinese Whispers, and Newman clustering. Radial Basis Function Networks Multi layer perceptrons Numerical Algorithms A fast matrix object implemented using the expression templates technique and capable of using BLAS and LAPACK libraries when available. Numerous linear algebra and mathematical operations are defined for the matrix object such as the singular value decomposition, transpose, trig functions, etc. General purpose unconstrained non-linear optimization algorithms using the conjugate gradient, BFGS, and L-BFGS techniques Levenberg-Marquardt for solving non-linear least squares problems Box-constrained derivative-free optimization via the BOBYQA algorithm An implementation of the Optimized Cutting Plane Algorithm Several quadratic program solvers Combinatorial optimization tools for solving optimal assignment and min cut/max flow problems as well as the CKY algorithm for finding the most probable parse tree A big integer object A random number object Graphical Model Inference Algorithms Join tree algorithm for exact inference in a Bayesian network. Gibbs sampler markov chain monte carlo algorithm for approximate inference in a Bayesian network. Routines for performing MAP inference in chain-structured, Potts, or general factor graphs. Image Processing Routines for reading and writing common image formats. Automatic color space conversion between various pixel types Common image operations such as edge finding and morphological operations Implementations of the SURF, HOG, and FHOG feature extraction algorithms. Tools for detecting objects in images including frontal face detection and object pose estimation. Threading The library provides a portable and simple threading API A message passing pipe for inter-thread and inter-process communication A timer object capable of generating events that are regularly spaced in time Threaded objects Threaded functions Parallel for loops A thread_pool with support for futures Networking The library provides a portable and simple TCP sockets API An object to help you make TCP based servers iostream and streambuf objects that enables TCP sockets to interoperate with the C++ iostreams library A simple HTTP server object you can use to embed a web server into your applications A message passing pipe for inter-thread and inter-process communication A tool used to implement algorithms using the Bulk Synchronous Parallel (BSP) computing model Graphical User Interfaces The library provides a portable and simple core GUI API Implemented on top of the core GUI API are numerous widgets Unlike many other GUI toolkits, the entire dlib GUI toolkit is threadsafe Data Compression and Integrity Algorithms A CRC 32 object MD5 functions Various abstracted objects representing parts of data compression algorithms. Many forms of the PPM algorithm are included. Testing A thread safe logger object styled after the popular Java logger log4j A modular unit testing framework Various assert macros useful for testing preconditions General Utilities A type-safe object to convert between big and little endian byte orderings A command line parser with the ability to parse and validate command lines with various types of arguments and options An XML parser An object that can perform base64 conversions Many container classes Serialization support Many memory manager objects that implement different memory pooling strategies A tool that lets you easily call C++ from MATLAB 전산 특징. - C++11 - 타 솔루션 종속성 : cuDNN 을 설치하면 GPU연산가능, cuDNN 설치하지 않은 경우엔 CPU에서도 구동가능.   메인 사이트 : http://dlib.net/ 위사이트 블로그 내용중 일부 : http://blog.dlib.net/2016/06/a-clean-c11-deep-learning-api.html

 

///940.