The Microsoft Cognitive Toolkit, previously known as CNTK, allows developers to harness the intelligence within massive datasets through deep learning by providing scaling, speed and accuracy with commercial-grade quality and compatibility with the programming languages and algorithms they already use. Microsoft today announced the general availability of Cognitive Toolkit version 2.0 with some new features including Keras support, Java bindings and Spark support for model evaluation, and model compression to increase the speed to evaluating a trained model on CPUs. With the GA release, Cognitive Toolkit v2.0 is now enterprise-ready and can be used for production-grade AI. Read about the new improvements in detail below.
- Keras Support (public preview): The Keras API was designed for users to develop AI applications and is optimized for the user experience. Keras has opened deep learning to thousands of people with no prior machine learning experience. We are delighted to announce that many thousands of Keras users are now able to benefit from the performance of Cognitive Toolkit without any changes to their existing Keras recipes. Keras support is currently in public preview as we continue to refine this capability.
- Java Bindings and Spark Support: Now with the GA release, users can evaluate Cognitive toolkit models with a new Java API. This makes it ideal for users wishing to integrate deep learning models into their Java based applications or for evaluation at scale on platforms like Spark.
- Model Compression: Evaluating a trained model on lower end CPUs found in mobile products can make real time performance difficult to achieve. With the Cognitive Toolkit GA, we are including extensions that allow quantized implementations of several FP operations, which are several times faster compared to full precision counterparts. The speedup is great enough to enable evaluating Cognitive Toolkit models much faster on server and low-power embedded devices with little loss of evaluation accuracy.
Along with the above new features, Microsoft has also made some performance improvements making Cognitive Toolkit the fastest deep learning framework. You can read about all the changes that are part of this v2.0 update here. And you can download the Microsoft Cognitive Toolkit v2.0 here.