Use Openvino and / or ONNX in STM32MP1
Options
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
2021-09-23 2:05 AM
Is it possible to use AI frameworks like ONNX and / or Openvino (and related accelerators like movidius, GPU) on STM32MP1? I took a look but I found only examples with tensorflow lite and Coral devices (i.e. https://github.com/STMicroelectronics/meta-st-stm32mpu-ai)
Labels:
- Labels:
-
STM32MP15 Lines
This discussion is locked. Please start a new topic to ask your question.
1 REPLY 1
Options
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
2021-09-27 8:26 AM
Hi @EBelt.1,
ONNX framework is not yet implemented on STM32MP1.
Study to support this framework will start soon.
Regarding the OpenVino, this framework will not be supported on STM32MP1.
To accelerate NN processing, the Google Coral EdgeTPU is supported on STM32MP1.
BR
Vincent
In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.
In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.
