IBM Watson Machine Learning Accelerator vs. MatConvNet vs. Python vs. RT-LAB Comparison Chart

The VLFeat open source library implements popular computer vision algorithms specializing in image understanding and local features extraction and matching. Algorithms include Fisher Vector, VLAD, SIFT, MSER, k-means, hierarchical k-means, agglomerative information bottleneck, SLIC superpixels, quick shift superpixels, large scale SVM training, and many others. It is written in C for efficiency and compatibility, with interfaces in MATLAB for ease of use, and detailed documentation throughout. It supports Windows, Mac OS X, and Linux. MatConvNet is a MATLAB toolbox implementing Convolutional Neural Networks (CNNs) for computer vision applications. It is simple, efficient, and can run and learn state-of-the-art CNNs. Many pre-trained CNNs for image classification, segmentation, face recognition, and text detection are available.

RT-LAB is OPAL-RT’s real-time simulation software combining performance and enhanced user experience. Fully integrated with MATLAB/Simulink®, RT-LAB offers the most complex model-based design for interaction with real-world environments. It provides the flexibility and scalability to achieve the most complex real-time simulation applications in the automotive, aerospace, power electronics, and power systems industries. Since its first application nearly 20 years ago on the Canadian Space Agency’s Canada Arm, RT-LAB has revolutionized the world of systems engineering, whether in space, on the ground or at sea. RT-LAB enables engineers and scientists to accelerate the development of new prototypes and to meet the most rigorous testing required by new and innovative technologies. RT-LAB handles everything, including code generation, with an easy-to-use interface. With just a few clicks of the mouse, a Simulink® model becomes an interactive real-time simulation application.