Katsuya Hyodo

PINTO_model_zoo. A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

onnx2tf. A tool for converting ONNX files to LiteRT/TFLite/TensorFlow, PyTorch native code (nn.Module), TorchScript (.pt), state_dict (.pt), Exported Program (.pt2), and Dynamo ONNX. It also supports direct conversion from LiteRT to PyTorch.

OpenVINO-YoloV3. YoloV3/tiny-YoloV3+RaspberryPi3/Ubuntu LaptopPC+NCS/NCS2+USB Camera+Python+OpenVINO

Tensorflow-bin. Prebuilt binary with Tensorflow Lite enabled. For RaspberryPi / Jetson Nano. Support for custom operations in MediaPipe. XNNPACK, XNNPACK Multi-Threads, FlexDelegate.

MobileNet-SSD-RealSense. [High Performance / MAX 30 FPS] RaspberryPi3(RaspberryPi/Raspbian Stretch) or Ubuntu + Multi Neural Compute Stick(NCS/NCS2) + RealSense D435(or USB Camera or PiCamera) + MobileNet-SSD(MobileNetSSD) + Background Multi-transparent(Simple multi-class segmentation) + FaceDetection + MultiGraph + MultiProcessing + MultiClustering

openvino2tensorflow. This script converts the ONNX/OpenVINO IR model to Tensorflow's saved_model, tflite, h5, tfjs, tftrt(TensorRT), CoreML, EdgeTPU, ONNX and pb. PyTorch (NCHW) -> ONNX (NCHW) -> OpenVINO (NCHW) -> openvino2tensorflow -> Tensorflow/Keras (NHWC/NCHW) -> TFLite (NHWC/NCHW). And the conversion from .pb to saved_model and from saved_model to .pb and from .pb to .tflite and saved_model to .tflite and saved_model to onnx. 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.

simple-onnx-processing-tools. A set of simple tools for splitting, merging, OP deletion, size compression, rewriting attributes and constants, OP generation, change opset, change to the specified input order, addition of OP, RGB to BGR conversion, change batch size, batch rename of OP, and JSON convertion for ONNX models.

tflite2tensorflow. 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.

TensorflowLite-bin. Prebuilt binary for TensorFlowLite's standalone installer. For RaspberryPi. A very lightweight installer. I provide a FlexDelegate, MediaPipe Custom OP and XNNPACK enabled binary.

wsl2_linux_kernel_usbcam_enable_conf. 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.

mediapipe-bin. MediaPipe Python Wheel installer for RaspberryPi OS aarch64, Ubuntu aarch64, Debian aarch64 and Jetson Nano.

Keras-OneClassAnomalyDetection. [5 FPS - 150 FPS] Learning Deep Features for One-Class Classification (AnomalyDetection). Corresponds RaspberryPi3. Convert to Tensorflow, ONNX, Caffe, PyTorch. Implementation by Python + OpenVINO/Tensorflow Lite.

whisper-onnx-cpu. ONNX implementation of Whisper. PyTorch free.

MobileNetV2-PoseEstimation. Tensorflow based Fast Pose estimation. OpenVINO, Tensorflow Lite, NCS, NCS2 + Python.

MobileNet-SSD. MobileNet-SSD(MobileNetSSD) + Neural Compute Stick(NCS) Faster than YoloV2 + Explosion speed by RaspberryPi · Multiple moving object detection with high accuracy.

hand-gesture-recognition-using-onnx. This is a hand gesture recognition program that replaces the entire MediaPipe process with ONNX. Simultaneous detection of multiple palms and a simple tracker are additionally implemented. In addition, a simple MLP can learn and recognize gestures.

TensorflowLite-UNet. 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.

TPU-MobilenetSSD. Edge TPU Accelerator / Multi-TPU + MobileNet-SSD v2 + Python + Async + LattePandaAlpha/RaspberryPi3/LaptopPC

DMHead. Dual model head pose estimation. Fusion of SOTA models. 360° 6D HeadPose detection. All pre-processing and post-processing are fused together, allowing end-to-end processing in a single inference.

HeadPoseEstimation-WHENet-yolov4-onnx-openvino. WHENet - ONNX, OpenVINO, TFLite, TensorRT, EdgeTPU, CoreML, TFJS, YOLOv4/YOLOv4-tiny-3L

whisper-onnx-tensorrt. ONNX and TensorRT implementation of Whisper

OpenVINO-EmotionRecognition. OpenVINO+NCS2/NCS+MutiModel(FaceDetection, EmotionRecognition)+MultiStick+MultiProcess+MultiThread+USB Camera/PiCamera. RaspberryPi 3 compatible. Async.

scs4onnx. A very simple tool that compresses the overall size of the ONNX model by aggregating duplicate constant values as much as possible.

facemesh_onnx_tensorrt. Verify that the post-processing merged into FaceMesh works correctly. The object detection model can be anything other than BlazeFace. YOLOv4 and FaceMesh committed to this repository have modified post-processing.

MobileNet-SSDLite-RealSense-TF. RaspberryPi3(Raspbian Stretch) + MobileNetv2-SSDLite(Tensorflow/MobileNetv2SSDLite) + RealSense D435 + Tensorflow1.11.0 + without Neural Compute Stick(NCS)

BoT-SORT-ONNX-TensorRT. BoT-SORT + YOLOX implemented using only onnxruntime, Numpy and scipy, without cython_bbox and PyTorch. Fast human tracker. OSNet is not used.

OpenVINO-DeeplabV3. [4-5 FPS / Core m3 CPU only] [11 FPS / Core i7 CPU only] OpenVINO+DeeplabV3+LattePandaAlpha/LaptopPC. CPU / GPU / NCS. RealTime semantic-segmentaion. Python3.5+Tensorflow v1.11.0+OpenCV3.4.3+PIL

YOLO. An MIT License of YOLOv9, YOLOv7, YOLO-RD

TPU-Posenet. Edge TPU Accelerator / Multi-TPU / Multi-Model + Posenet/DeeplabV3/MobileNet-SSD + Python + Sync / Async + LaptopPC / RaspberryPi

DEIMv2. [DEIMv2] Real Time Object Detection Meets DINOv3

faster-whisper-env. An environment where you can try out faster-whisper immediately.

yolo-depthanythingv2-merge. Merging YOLOv9 and DepthAnythingV2

onnx2json. Exports the ONNX file to a JSON file and JSON dict.

crowdhuman_hollywoodhead_yolo_convert. YOLOv7 training. Generates a head-only dataset in YOLO format. The labels included in the CrowdHuman dataset are Head and FullBody, but ignore FullBody.

tflite2json2tflite. Convert tflite to JSON and make it editable in the IDE. It also converts the edited JSON back to tflite binary.

LightGlue-ONNX. ONNX-compatible LightGlue: Local Feature Matching at Light Speed

yolact_edge_onnx_tensorrt_myriad. 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.

simple_fisheye_calibrator. Simple GUI-based correction of fisheye images. The correction parameters specified on the screen can be diverted to opencv's fisheye correction parameters. Supports execution via Docker.

sit4onnx. Tools for simple inference testing using TensorRT, CUDA and OpenVINO CPU/GPU and CPU providers. Simple Inference Test for ONNX.

scc4onnx. Very simple NCHW and NHWC conversion tool for ONNX. Change to the specified input order for each and every input OP. Also, change the channel order of RGB and BGR. Simple Channel Converter for ONNX.

zumo32u4. Zumo32u4(ATmega32u4) + RaspberryPi3(RaspberryPi) + SLAM(CartoGrapher/Gmapping) + RPLiDAR A1M8

Bazel_bin. Bazel's pre-built binaries for armv7l / aarch64 / x86_64.

mtomo. Multiple types of NN model optimization environments. It is possible to directly access the host PC GUI and the camera to verify the operation. Intel iHD GPU (iGPU) support. NVIDIA GPU (dGPU) support.

onnxruntime4raspberrypi. onnxruntime for RaspberryPi armv7l

human-instance-segmentation. ROI-based Instance Segmentation for Human Detection (CNN)

MobileNetv2-SSDLite. My proprietary procedure. Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.

20220228_intel_deeplearning_day_hitnet_demo. Special Presentation Demo at Intel IoT Planet 2021 DeepLearning Day / インテル IoT プラネット 2021 DeepLearning Dayの特別講演の発表資料 https://www.intel.co.jp/content/www/jp/ja/now/iot-planet/deep-learning-day.html

json2onnx. Converts a JSON file to an ONNX file.

pytorch4raspberrypi. Cross-compilation of PyTorch armv7l (32bit) for RaspberryPi OS

hand_landmark. HandLandmark Detection that can be performed only in onnxruntime. Pre-focusing by skeletal detection is not performed. This does not use MediaPipe.

spo4onnx. Simple tool for partial optimization of ONNX. Further optimize some models that cannot be optimized with onnx-optimizer and onnxsim by several tens of percent. In particular, models containing Einsum and OneHot.

TensorflowLite-flexdelegate. This is a repository for checking the operation of Flex Delegate of Tensorflow.

snc4onnx. Simple tool to combine(merge) onnx models. Simple Network Combine Tool for ONNX.

gazelle. Python

OpenVINO-ADAS. [1 FPS / CPU only] OpenVINO+ADAS+LattePandaAlpha. CPU / GPU / NCS. RealTime semantic-segmentaion. Python3.5+OpenCV3.4.3+PIL

jetson-tensorflow-pytorch-build. Provides an environment for compiling TensorFlow or PyTorch with CUDA for aarch64 on an x86 machine. This is for Jetson. If you build using an EC2 m6g.16xlarge (aarch64) instance, TensorFlow can be fully built in about 30 minutes. It can be used as a cross-compilation environment not only for TensorFlow and PyTorch, but also for various other packages and libraries.

Open3D-build. Provide Docker build sequences of Open3D for various environments.

onnx-aec. A playground for experimenting with acoustic echo cancellation using a microphone, speaker, and ONNX.

OpenVINO-bin. OpenVINO installer storage location (Full version)