https://docs.khadas.com/ 2026-04-06T15:07:58+00:00 https://docs.khadas.com/ https://docs.khadas.com/ttps://docs.khadas.com/lib/tpl/dokuwiki-new/images/favicon.ico text/html 2025-04-09T23:25:52+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/edge2/npu/demos/densenet-ctc?rev=1744255552&do=diff densenet npu edge2 rk3588 DenseNet CTC ONNX Keras Edge2 Demo - 3 Introduction Densenet_CTC is a text recognition model. It only can recognize single line text. Therefore usually, it needs to be used in conjunction with a text detection model. Recognition image and inference results on Edge2. text/html 2025-04-09T23:43:44+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/edge2/npu/demos/face-recognition?rev=1744256624&do=diff npu retinaface facenet edge2 Face Recognition Edge2 Demo - 7 Introduction Face Recognition Demo consists of two models, RetinaFace and FaceNet. It can detect face on image and recognize who it is. Here are two judgment indicators, cosine similarity and Euclidean distance. The closer the cosine similarity is to 1 and the closer the Euclidean distance is to 0, the more similar is between two faces. text/html 2025-04-09T23:38:17+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/edge2/npu/demos/facenet?rev=1744256297&do=diff npu facenet edge2 pytorch FaceNet PyTorch Edge2 Demo - 6 Introduction FaceNet is a face recognition model. It will convert a face image into a feature map. Compare the feature map between image and face database. Here are two judgment indicators, cosine similarity and Euclidean distance. The closer the cosine similarity is to 1 and the closer the Euclidean distance is to 0, the more similar is between two faces. text/html 2025-04-09T23:33:43+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/edge2/npu/demos/retinaface?rev=1744256023&do=diff npu retinaface edge2 pytorch RetinaFace PyTorch Edge2 Demo - 5 Introduction RetinaFace is a face detection model. It can draw five key points on each face, including two eyes, nose and two corners of mouth. Inference results on Edge2. Inference speed test: USB camera about text/html 2025-06-06T03:24:19+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/edge2/npu/demos/rknn-tflite?rev=1749194659&do=diff TFLite Edge2 Demo - 11 We can run TFLite models by converting them into RKNN format and running them on the onboard NPU. Get Source code Clone the examples sravansenthiln1/rknn_tflite. $ git clone https://github.com/sravansenthiln1/rknn_tflite $ cd rknn_tflite RKNN Conversion text/html 2025-04-09T23:30:37+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/edge2/npu/demos/vgg16?rev=1744255837&do=diff npu vgg16 edge2 tensorflow keras VGG16 TensorFlow Keras Edge2 Demo - 4 Introduction VGG16 is a classification model. It can assign a single label to an entire image. Image and inference results on Edge2. Train Model git clone https://github.com/Daipuwei/Mini-VGG-CIFAR10 text/html 2025-04-09T23:10:15+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/edge2/npu/demos/yolov7-tiny?rev=1744254615&do=diff yolo npu edge2 rk3588 YOLOv7-tiny Edge2 Demo - 1 Introduction YOLOv7-Tiny is an object detection model. It uses bounding boxes to precisely draw each object in image. Inference results on Edge2. Inference speed test: USB camera about 43ms per frame. MIPI camera about text/html 2025-06-06T03:24:37+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/edge2/npu/demos/yolov8n-pose?rev=1749194677&do=diff yolo npu edge2 rk3588 YOLOv8n-Pose OpenCV Edge2 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 2025-06-24T06:02:51+00:00 Anonymous (anonymous@undisclosed.example.com) https://docs.khadas.com/products/sbc/edge2/npu/demos/yolov8n?rev=1750759371&do=diff yolo npu edge2 rk3588 YOLOv8n OpenCV Edge2 Demo - 2 Introduction YOLOv8n is an object detection model. It uses bounding boxes to precisely draw each object in image. Inference results on Edge2. Inference speed test: USB camera about 52ms per frame. MIPI camera about