Edge Impulse logo
Blog Post

MLPerf Tiny Inference Is a New Benchmarking Suite for tinyML Devices

TinyML, Embedded DevicesTo support developers who wish to explore and submit MLPerf Tiny benchmarks, Edge Impulse has worked with MLCommons to produce a set of reference projects.

Nick Bild

June 18, 2021

    When you’re optimizing a neural network for on-device efficiency, how can you be sure which changes you make will move your model in the right direction? And if you’re trying to select embedded hardware for your machine learning application, how do you know which devices are best suited to your workload? Making the right choices can be crucial for tinyML, where each byte and milliwatt is of critical importance.

    Until recently, with no available benchmarks, the only way to inform these decisions was through systematic evaluation of all the options available for your application—which, given the diversity of available technologies, can be a herculean feat.

    Fortunately, with the release of MLPerf Tiny Inference by MLCommons, an open engineering consortium, the landscape has now changed. MLPerf Tiny Inference was designed from the ground up to help engineers assess the performance of neural networks running on extremely low-power embedded devices.

    This release comes as embedded machine learning is experiencing a boom in popularity as compute resources capable of running machine learning algorithms have grown smaller and less expensive. These tiny neural networks can process audio, video, and other sensor data to provide rapid inference times without the privacy implications of sending that data to the cloud for processing.

    The modular components of a MLPerf Tiny reference implementation. (Image: C. Banbury et al.)

    The MLPerf Tiny Inference benchmarking suite offers reporting and also comparisons of tinyML devices, systems, and software. In particular, the benchmark measures four tasks that represent key tasks in embedded machine learning: Keyword spotting, visual wake words, image classification, and anomaly detection.

    To support developers and hardware manufacturers who wish to explore and submit MLPerf Tiny benchmarks, Edge Impulse has worked with the MLCommons team to produce a set of Edge Impulse reference projects that contain the datasets and models used in three of the scenarios:

    The energy and latency results of the reference implementations, which were run on an STMicroelectronics NUCLEO-L4R5ZI. (Image: C. Banbury et al.)

    MLPerf Tiny Inference was developed in collaboration with over 50 partners in industry and academia; it reflects the needs of the community at large. It looks to be an important tool to add to our ML toolboxes that will help us to add intelligence to everyday items, from wearables to thermostats and cameras.

    You can get involved with the MLPerf Tiny effort by joining the working group. To get started exploring the benchmarks, check out the Visual Wake Words project on Edge Impulse.



    Are you interested in bringing machine learning intelligence to your devices? We're happy to help.

    Subscribe to our newsletter