Katsuya Hyodo's Projects
Implementation of UNet by Tensorflow Lite. Semantic segmentation without using GPU with RaspberryPi + Python. In order to maximize the learning efficiency of the model, this learns only the "Person" class of VOC2012. And Comparison with ENet.
TensorFlow models accelerated with NVIDIA TensorRT
Convert tflite to JSON and make it editable in the IDE. It also converts the edited JSON back to tflite binary.
Generate saved_model, tfjs, tf-trt, EdgeTPU, CoreML, quantized tflite, ONNX, OpenVINO, Myriad Inference Engine blob and .pb from .tflite. Support for building environments with Docker. It is possible to directly access the host PC GUI and the camera to verify the operation. NVIDIA GPU (dGPU) support. Intel iHD GPU (iGPU) support. Supports inverse quantization of INT8 quantization model.
GPU accelerated deep learning inference applications using TensorflowLite GPUDelegate / TensorRT
Challenge the marginal performance of YoloV2 + Neural Compute Stick + RaspberryPi YoloV2+Neural Compute Stick(NCS)+Raspberry Piの限界性能に挑戦
TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation, CVPR2022
Edge TPU Accelerator / Multi-TPU + MobileNet-SSD v2 + Python + Async + LattePandaAlpha/RaspberryPi3/LaptopPC
Edge TPU Accelerator / Multi-TPU / Multi-Model + Posenet/DeeplabV3/MobileNet-SSD + Python + Sync / Async + LaptopPC / RaspberryPi
Tensorflow implementation of CNN described in https://arxiv.org/abs/1806.09594
Official Pytorch Code for the paper TransWeather
TVM build and run test environment
PyTorch implementation for "A Wavelet-based Dual-stream Network for Underwater Image Enhancement", ICASSP, 2022.
Repository for URDF parsing code
URDF parser
Headers for URDF parsers
A ROS Driver for V4L USB Cameras
Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces. IJCV 2012
OpenCL implementation running on the VideoCore IV GPU of the Raspberry Pi models
A package to open video streams and publish them in ROS using the opencv videocapture mechanism
A Robust and Versatile Monocular Visual-Inertial State Estimator
The official repo for CVPR2021——ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search.
Tutorials related to using and extending RViz and interactive_markers.
Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos.
Configuration file to build the kernel to access the USB camera connected to the host PC using USBIP from inside the WSL2 Ubuntu 20.04/22.04.
A YAML parser and emitter in C++
Provides a conversion flow for YOLACT_Edge to models compatible with ONNX, TensorRT, OpenVINO and Myriad (OAK). My own implementation of post-processing allows for e2e inference. Support for Multi-Class NonMaximumSuppression, CombinedNonMaxSuppression.