https://docs.khadas.com/ 2026-05-29T22:10:40+00:00 https://docs.khadas.com/ https://docs.khadas.com/ttps://docs.khadas.com/lib/tpl/dokuwiki-new/images/favicon.ico text/html 2026-04-02T02:48:19+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/vim4/npu/ksnn/demo/ppocr?rev=1775112499&do=diff npu ppocr ksnn vim4 Doc for version ddk-3.4.7.7 PPOCR KSNN Demo - 10 Introduction PPOCR is a state-of-the-art, highly efficient, open-source Optical Character Recognition system. It's designed to be ​​practical​​, ​​lightweight​​, and incredibly ​​fast​​, making it ideal for deploying OCR capabilities directly on mobile or edge devices with limited computational resources (like smartphones or IoT devices), as well as high-volume cloud-based processing. text/html 2026-04-02T02:48:07+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/vim4/npu/ksnn/demo/yolov8n-pose?rev=1775112487&do=diff npu yolo ksnn vim4 Doc for version ddk-3.4.7.7 YOLOv8n-Pose KSNN Demo - 8 Introduction YOLOv8n-Pose inherits the powerful object detection backbone and neck architecture of YOLOv8n. It extends the standard YOLOv8n object detection model by integrating dedicated pose estimation layers onto its head. This allows it to not only detect people (bboxes) but also simultaneously predict the spatial positions (keypoints) of their anatomical joints (e.g., shoulders, elbows, knees, ankles). text/html 2026-04-02T02:47:57+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/vim4/npu/ksnn/demo/yolov8n?rev=1775112477&do=diff npu yolo ksnn vim4 Doc for version ddk-3.4.7.7 YOLOv8n KSNN Demo - 2 Introduction YOLOv8n is an object detection model. It uses bounding boxes to precisely draw each object in image. Inference results on VIM4. Inference speed test: USB camera about 190ms per frame. MIPI camera about