Description Deploying YOLOv8 on Wildfire RK3588, we will use yolov8s.pt (downloaded from the YOLOv8 official website) as an example. 1. pt->onnx Do not use the official YOLOv8 code; instead, use the Rockchip YOLOv8 code available at the following address: https://github.com/airockchip/ultralytics_yolov8 After downloading the code, execute the model conversion with the following code: from ultralytics import … Read more
★ Embedded AI Series – Converting YOLOv3 Model Using RKNN Toolkit ” 1 Introduction Since my development work is primarily focused on AI applications in machine vision, the commonly used model is the YOLO model. Therefore, I will demonstrate the conversion of the YOLOv3 model using the example code from the RKNN toolkit in the … Read more
Overview In this project, we encountered a need for Optical Character Recognition (OCR). However, the best-performing <span>PaddleOCR</span> can only run on Baidu’s <span>PaddlePaddle</span> framework. In common projects, the more widely used Pytorch framework is often preferred. Installing PaddlePaddle separately not only makes the project overly bulky but may also lead to conflicts. In the previous … Read more
Requires the following versionRKLLM https://github.com/airockchip/rknn-llm/tree/release-v1.2.1b1 Install theRKLLM-Toolkit for this version, otherwise the model conversion may fail. Download the model file, taking Qwen3-0.6B as an example https://www.modelscope.cn/models/Qwen/Qwen3-0.6B Modify rknn-llm/examples/DeepSeek-R1-Distill-Qwen-1.5B_Demo/export/export_rkllm.py Changemodelpath to the downloadedQwen3 directory modelpath = ‘/home/andy/rkllm/Qwen3-0.6B’ Executepython export_rkllm.py to convert to therkllm supported model format. INFO: rkllm-toolkit version: 1.2.1b1WARNING: Cuda device not available! switch to … Read more
Bookmark + Pin to master cutting-edge technology news in embedded AIoTLike + Follow to become even better together! Description of Software and Hardware Devices in the Development Environment PC Host: Windows 11 (32GB RAM, 1TB SSD) Virtual Machine: Ubuntu 22.04 (allocated 16GB RAM, 512GB disk) Development Board: ELF2 (RK3588 4G+32G), running Ubuntu 22.04 Desktop system … Read more
In the previous introduction, we discussed how to develop AI inference applications based on Orange Pi AIpro, and learned that before inference, the original network model (which could be PyTorch/TensorFlow/Caffe, etc.) needs to be converted into an .om model. Only then can we call the Ascend aclmdlExecute and other model execution interfaces for model inference … Read more