Hi,
I’m trying to run the PaddleOCR recognition model on a Raspberry Pi using the Hailo AI Accelerator. I would like to know the steps or procedures needed to:
Convert the PaddleOCR recognition model to be compatible with Hailo,
And perform inference on the Raspberry Pi using the Hailo device.
Could you guide me on the required tools, supported model formats, conversion pipeline, and inference setup? Any help or reference documentation would be appreciated.
I’d also like to know if there is any comprehensive documentation or guide that outlines the steps to convert and run any custom or pretrained model on the Hailo AI Accelerator in raspberry pi, including model conversion and inference.
If there’s a general workflow or resource that covers this process in detail, please share it.
The good news is that we do support PaddleOCR. It will still take a couple of releases for it to be in officially in the ModelZoo, but we will have it here very soon.