Shifting Capsule Networks from the Cloud to the Deep Edge

1 code implementation • 6 Oct 2021 • Miguel Costa, Diogo Costa, Tiago Gomes, Sandro Pinto

In terms of throughput, our Arm Cortex-M API enables the execution of primary capsule and capsule layers with medium-sized kernels in just 119. 94 and 90. 60 milliseconds (ms), respectively (STM32H755ZIT6U, Cortex-M7 @ 480 MHz).

Quantization