From the DeepGate blog.
Research notes, product updates, and the engineering behind ultra-efficient edge AI.
Automating model design for edge AI.
DeepGate's model search and compiler produce models that run up to 45× faster and use up to 11× less RAM than reference models on the same microcontroller.
Our edge AI compiler outperforms Google and vendor toolchains.
DeepGate compiler produces static binaries that use up to 3× less RAM and run up to 2× faster than Google's TFLM on Arm Cortex-M, across silicon vendors.