It’s been three years since the RP2040 port of TensorFlow Lite for Microcontrollers. The work was done by Pete Warden, who at that point headed up the TensorFlow mobile team at Google. Since, the RP2040 port has been languishing. But a couple of weeks ago, that all changed. Raspberry Pi News reports:
Now at Useful Sensors, Pete has been doing some interesting things with RP2040. He has just upstreamed the last three years of changes — after all, as he puts it, “We all love pull requests with 1,129 changed files, right?” — and he’s taking on maintenance of the port on a best-effort basis.
The code now uses both cores of the RP2040 microcontroller.
The upshot? These updates and changes reduce the time for the person detection benchmark code from 824ms to 588ms. That’s a ×1.4 speed increase!
Read more on Raspberry Pi News here and see the pull request on GitHub.
No comments:
Post a Comment