Machine Learning for Mobile & IoT made easy.

We automate model optimization and management so you can focus on data and training.

ACCELERATION

Ship the fastest model implementation without additional development effort.

CROSS-PLATFORM

Support multiple hardware and software platforms from a single code base.

ANALYTICS

Get actionable insights for model speed, power and memory optimization.

Why numericcal?

Speed, memory and power are an afterthought in standard machine learning training. Why spend time training a perfectly accurate model just to discover it is too slow or too big for your application and target platform? We provide tools to help you reach your implementation goals quickly and effortlessly.

MODEL RESOURCE OPTIMIZATION

We automatically run multiple toolchains to give you the best speed, power and memory tradeoff on every model change.

CROSS-PLATFORM MODEL ANALYTICS

We measure on-device speed and power usage to help you evaluate and compare models across hardware platforms.

BOTTLENECK IDENTIFICATION

We help you pinpoint performance bottlenecks and focus your model optimization on layers that matter the most.

Model optimization

Focus on choosing and training the best Deep Learning model for your application knowing that we’ll do everything to find the best implementation of your network for every platform.


On the right we compare TensorFlow Mobile and Numericcal Runtime Engine on a Qualcomm SnapDragon 820 based Android phone. The network is NVidia DriveNet without any modifications such as quantization or pruning. In this case, leveraging the Adreno GPU and memory access optimizations results in 5x speedup.

Learn more

Analytics

Use numericcal to compare and select hardware platforms for your next product. We’ll make sure you can easily update and evolve your Machine Learning models across hardware revisions as your product matures.

MODEL ACTIVITY MONITORING

Model activity report shows user engagement over time. It can be used to analyze performance of different model versions and A/B testing of models.

FLEET LEVEL BENCHMARKING

Fleet analysis shows relative frequency of model use across different platforms. Detailed performance measurements can be shown for each platform.

MODEL/PLATFORM COMPARISON

Benchmark model ideas across all relevant platforms to pick the best one. Make sure that your model updates work across all relevant devices.

Contact us

Questions? Comments? Feature requests?

Bitnami