- Production support for top-tier XGBoost machine learning library.
- Docker images for CPU and GPU machines, see instructions to get started in minutes.
- Out of the box image similarity search.
- Ready to go on AWS: AMI for instant image classification service with GoogleNet and ResNet.
- State of the art text classification API with Character-Based Deep Convolutional Nets!
- Seamless integration with Elasticsearch.
Instant Machine Learning for your Applications
Get state of the art results with no code involved
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.
No Compromise on Technology
Embeds the best deep learning technology
The deep learning server has full support for the state of the art Caffe and XGBoost libraries, with even more choice on the way. No compromise, the best image recognition and neural network technologies at your fingertips.
Makes the most out of your CPU and GPU
Multi-purpose deep learning server that supports multiple learning jobs and services in parallel. The full C++ stack is designed for genericity and the best performances.
Open Source with professional support
A full Open Source product that gives you freedom and control over your stack. The product is supported by Machine Learning experts and AI veterans, and they can help with your applications too.
Versatile Machine Learning
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.