Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Explore how deep learning compilers optimize TinyML models in this technical conference talk from the tinyML Summit 2023, presented by OctoML Software Engineer Gavin Uberti. Dive into the inner workings of Apache TVM as it compiles a MobileNetV1 model for Cortex-M microcontrollers, examining the intermediate representations and their transformations during optimization. Learn about the process of tailoring convolution kernels for specific devices, folding quantization parameters into subsequent operators, and implementing on-the-fly layout rewrites to enhance model performance.
