The AIXPRT Community Preview is a pre-release build of AIXPRT, an AI benchmark tool that makes it easier to evaluate a system's machine learning inference performance by running common image-classification and object-detection workloads.
The preview build includes support for the Intel OpenVINO©, TensorFlow™, and TensorFlow with NVIDIA© TensorRT™ toolkits to run image-classification and object-detection workloads with ResNet-50 and SSD-MobileNet v1 networks. The test reports FP32, FP16, and INT8 levels of precision. Test systems must be running Ubuntu 16.04 LTS or Windows 10, and the minimum CPU and GPU requirements vary by toolkit. You can find more detail on hardware and software requirements in the installation instructions below. Additional instructions are located in the installation package's readme files.
The most current AIXPRT Community Preview build is hosted on the AIXPRT tab in the XPRT Members' Area, and in our GitHub repository. Normally, only BenchmarkXPRT Development Community members have access to community previews. However, because we're seeking broad input from experts in this field, we'll gladly make anyone interested in participating a member. Please contact us to request a membership and access to the AIXPRT repository.
The XPRT benchmarks are constantly evolving. Get the latest announcements about the XPRT family right here.
Principled Technologies brings its technical prowess to the XPRT family with these informative, fact-based white papers. Read them here.
We periodically hold Webinars to inform members about what's going on in the BenchmarkXPRT community. Visit our Webinars archive.