-
Notifications
You must be signed in to change notification settings - Fork 99
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Please update this port of TensorFlow Lite Micro library changes from latest upstream LiteRT for Microcontrollers? #20
Comments
Just to manage expectations, I don't work for Raspberry Pi anymore, and @petewarden was supporting this port on a very much "best efforts" basis. |
Any chance @lurch @kilograham @peterharperuk @Wren6991 @will-v-pi could run it up the flagpole to the Raspberry Pi team? |
The team will already have seen this I believe. They are all very busy though and may not be able to spend much time on it. |
FYI; @sean-lawless did submit a pull request a few weeks ago which @lurch made some comments on but it is not merged yet: |
@Hedda Have you tested Sean's PR to see if it works and gets you want you need? |
I've now updated this port to the latest TFLM upstream, and confirmed it works on the RP2350. See dfea53b |
Please consider updating this pico-tflmicro port of TensorFlow Lite Micro library with all the latest changes from upstream TensorFlow Lite (LiteRT) to enable better suppport for RP2040 and RP2350 microcontrollers from Raspberry Pi, ok?
https://github.com/tensorflow/tflite-micro
https://ai.google.dev/edge/litert/microcontrollers/overview
RP2040 support for TensorFlow Lite Micro was announced on the blog in January of 2024 but then no updates since March:
Would also really like to see native support for the new RP2350 SoC/MCU with both Cortex-M and/or RISC-V cores in it:
PS: Would in addition be awesome to see a demo on microWakeWord running natively on both RP2350 or RP2040 platforms:
The text was updated successfully, but these errors were encountered: