PINTO0309

Deeplearning, Machinelearning, IoT

Annotation
Annotation
OnnxGraphQt - Practice ONNX editing operations with GUI
OnnxGraphQt - Practice ONNX editing operations with GUI
Stereo Depth HITNet, onnxruntime-gpu TensorRT 8.2.2.1 custom build
Stereo Depth HITNet, onnxruntime-gpu TensorRT 8.2.2.1 custom build
Person Attribute Recognition Sample, OpenVINO FP32 CPU only + 1280x720 + C++
Person Attribute Recognition Sample, OpenVINO FP32 CPU only + 1280x720 + C++
MobileNetV3 + DBFace + Fisheye USB Camera + OpenVINO FP16 + CPU only
MobileNetV3 + DBFace + Fisheye USB Camera + OpenVINO FP16 + CPU only
Jetson Nano + GPU (OpenGL ES3.2) + MediaPipe + FaceMesh + Python 3.6
Jetson Nano + GPU (OpenGL ES3.2) + MediaPipe + FaceMesh + Python 3.6
Jetson Nano + GPU (OpenGL ES3.2) + MediaPipe + FaceDetection + Python 3.6
Jetson Nano + GPU (OpenGL ES3.2) + MediaPipe + FaceDetection + Python 3.6
Jetson Nano + GPU (OpenGL ES3.2) + MediaPipe + Pose + Python 3.6
Jetson Nano + GPU (OpenGL ES3.2) + MediaPipe + Pose + Python 3.6
Jetson Nano + GPU (OpenGL ES3.2) + MediaPipe + Selfie Segmentation + Python 3.6
Jetson Nano + GPU (OpenGL ES3.2) + MediaPipe + Selfie Segmentation + Python 3.6
Jetson Nano + GPU (OpenGL ES3.2) + MediaPipe + HandPose + Python 3.6
Jetson Nano + GPU (OpenGL ES3.2) + MediaPipe + HandPose + Python 3.6
RaspberryPi4 CPU only + RaspberryPi OS 64bit + Python3.7 + MediaPipe Hand Detection, 9 FPS
RaspberryPi4 CPU only + RaspberryPi OS 64bit + Python3.7 + MediaPipe Hand Detection, 9 FPS
Head Pose Estimation - OpenCV
Head Pose Estimation - OpenCV
1 year GitHub commit history for PINTO0309 - 3D STL
1 year GitHub commit history for PINTO0309 - 3D STL
CenterNet MobileNetV2 FPN Keypoints 320x320 Float32 + TFLite 20 Threads
CenterNet MobileNetV2 FPN Keypoints 320x320 Float32 + TFLite 20 Threads
OpenVINO + Open3D + BlazePose 3D + USB Camera
OpenVINO + Open3D + BlazePose 3D + USB Camera
TensorSpace.js - YoloV2
TensorSpace.js - YoloV2
Generate saved_model,tfjs,tf-trt,TPU,CoreML,Qauntized tflite,ONNX,OpenVINO,blob and pb from .tflite.
Generate saved_model,tfjs,tf-trt,TPU,CoreML,Qauntized tflite,ONNX,OpenVINO,blob and pb from .tflite.
MODNet - WebCam-Based Portrait Video Matting Demo 512x672
MODNet - WebCam-Based Portrait Video Matting Demo 512x672
Santa Cypher - A silly encoder that converts (poorly) between text and Santa laughing.
Santa Cypher - A silly encoder that converts (poorly) between text and Santa laughing.
NanoDet
NanoDet "Super fast and lightweight anchor-free object detection model. Real-time on mobile devices"
3D Bounding Box Estimation for Autonomous Drinving
3D Bounding Box Estimation for Autonomous Drinving
Facial Cartoonization, 60FPS, OpenVINO FP16, Corei7 CPU only, without GPU
Facial Cartoonization, 60FPS, OpenVINO FP16, Corei7 CPU only, without GPU
3D Human Pose Estimation + Tensorflow.js + Browser + WebGL
3D Human Pose Estimation + Tensorflow.js + Browser + WebGL
BiSeNetV2 448x448 (Semantic Segmentation) + OpenVINO FP16 + Corei7 CPU only + USB Camera 640x480
BiSeNetV2 448x448 (Semantic Segmentation) + OpenVINO FP16 + Corei7 CPU only + USB Camera 640x480
Tensorflow Lite + DBFace INT8 Quantization 256x256 + RaspberryPi4 CPU 4 threads + USB Camera 640x480
Tensorflow Lite + DBFace INT8 Quantization 256x256 + RaspberryPi4 CPU 4 threads + USB Camera 640x480
OpenVINO + OpenCV Text Detection FP16 + NCS2 (MYRIAD) Reflects the rotation angle of the text
OpenVINO + OpenCV Text Detection FP16 + NCS2 (MYRIAD) Reflects the rotation angle of the text
OpenCV Text Detection (EAST text detector) 320x320 + EdgeTPU
OpenCV Text Detection (EAST text detector) 320x320 + EdgeTPU
OpenVINO + OpenCV Text Detection (EAST text detector) FP16 + NCS2 (MYRIAD)
OpenVINO + OpenCV Text Detection (EAST text detector) FP16 + NCS2 (MYRIAD)
OpenVINO + OpenCV Text Detection (EAST text detector) FP16 + x86 CPU only
OpenVINO + OpenCV Text Detection (EAST text detector) FP16 + x86 CPU only
OpenVINO + Mobile DeeplabV3-plus (MobileNetV3) FP16 + NCS2 (MYRIAD)
OpenVINO + Mobile DeeplabV3-plus (MobileNetV3) FP16 + NCS2 (MYRIAD)