High Performance Open Source Deep Learning Server

Deep Detect Versatile Machine Learning

My personal blog http://blog.omeryavuz.gen.tr

Templates for the best neural architectures

Deep neural networks with a proven track record are included as templates. These include Googlenet, Alexnet, ResNet, character-based nets for image and text classification.

Range of model quality assessment measures

Assessing your model quality made easy. From F1-score to multiclass log loss, measures and their history can be accessed during the learning phase.

Collection of input connectors

Handle large repositories of images with extreme ease. Massage and pre-process data from CSV files directly from the API prior to learning a statistical model.

Get state of the art results with no code involved

Classify images, detect objects, deal with text and numerical data from your application or the command line by series of simple calls to the deep learning server. 

Seamless switch between development and production 

Use one or more deep learning servers for development and production, test, move and reuse models, it has never been easier to bring the full machine learning cycle into production! 

Easy API and flexible template output formats 

A simple yet powerful and generic API for use of Machine Learning. It is simple to setup, test, and plug into your existing application.

DeepDetect is a deep learning API and server written in C++11. It makes state of the art deep learning easy to work with and integrate into existing applications. It has support for backend machine learning libraries Caffe, Tensorflow and XGBoost.

DeepDetect boasts the following features:

General

• High level & generic API for machine learning & deep learning
• JSON communication format
• Remote Python client library
• Embedded server with support for asynchronous training calls
• High performance, benefits from multicore CPU and GPU
• Flexible input / output connectors for text, images, raw data (CSV, SVM)
• Flexible template output format to simplify connection to external applications (e.g. Elastic search, …)
• No database dependency and sync, everything is organized on the filesystem

Machine Learning / Deep Learning

• Support for state of the art Deep Learning via Caffe and Tensorflow libraries, and decision trees via XGBoost
• Templates for the most useful neural architectures (e.g. Googlenet, Alexnet, NiN, mlp, convnet, logistic regression, ResNets, …)
• Range of pre-trained state of the art models for text and images
• Range of built-in model assessment measures (e.g. F1, multi class log loss, …)
• Support for multiple Machine Learning services, training and prediction calls in parallel
• Makes the most out of CPUs and GPUs
• Supervised learning, regression and prediction over images and other numerical and textual data, auto encoders, object detection, …

Data

• Built-in input connectors to ease the setup of a machine learning pipeline
• Easy management large datasets of images
• Easy management and preprocessing of CSV data files
• Connector to handle large collections of images with on-the-fly data augmentation (e.g. rotations, mirroring, …)
• Connector to handle CSV files with preprocessing capabilities
• Connector to handle sparse data in SVM format
• Connector to handle text files
• Output connectors for various external applications can be setup through templates via the API, without code (e.g. for Elastic search, XML, SQL, …)

Machine learning frameworks and algorithms supported by the server

• Caffe, one of the most powerful deep neural network frameworks. Caffe has support for many neural architectures, including logistic regression, multi-layer perceptron, convolutional networks, recurrent nets, etc…
  
• XGBoost one of the most regarded machine learning frameworks for a wide range of applications. Gradient boosted trees are a form of decision trees.