Hobby programmer. Intel Software Innovator Program member.
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.
Python - Released: 11 Dec 2019 - 3,348
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.
Python - Released: 27 Sep 2022 - 559
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.
Python - Released: 11 Apr 2022 - 268
Prebuilt binary with Tensorflow Lite enabled. For RaspberryPi / Jetson Nano. Support for custom operations in MediaPipe. XNNPACK, XNNPACK Multi-Threads, FlexDelegate.
Shell - Released: 18 Oct 2018 - 500
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.
Python - Released: 13 Oct 2021 - 94
Prebuilt binary for TensorFlowLite's standalone installer. For RaspberryPi. A very lightweight installer. I provide a FlexDelegate, MediaPipe Custom OP and XNNPACK enabled binary.
Shell - Released: 15 Nov 2018 - 198
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.
Python - Released: 16 Apr 2022 - 20
MediaPipe Python Wheel installer for RaspberryPi OS aarch64, Ubuntu aarch64, Debian aarch64 and Jetson Nano.
Shell - Released: 29 May 2021 - 118
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.
Python - Released: 17 Sep 2023 - 18
A very simple tool for situations where optimization with onnx-simplifier would exceed the Protocol Buffers upper file size limit of 2GB, or simply to separate onnx files to any size you want.
Python - Released: 06 Apr 2022 - 13
A very simple tool that compresses the overall size of the ONNX model by aggregating duplicate constant values as much as possible.
Python - Released: 03 Apr 2022 - 51
[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.
Jupyter Notebook - Released: 06 Jan 2019 - 127
YOLOv7 training. Generates a head-only dataset in YOLO format. The labels included in the CrowdHuman dataset are Head and FullBody, but ignore FullBody.
Python - Released: 04 Aug 2022 - 27
Tensorflow based Fast Pose estimation. OpenVINO, Tensorflow Lite, NCS, NCS2 + Python.
Python - Released: 29 Apr 2019 - 106
A very simple tool to rewrite parameters such as attributes and constants for OPs in ONNX models. Simple Attribute and Constant Modifier for ONNX.
Python - Released: 13 Apr 2022 - 11
MobileNet-SSD(MobileNetSSD) + Neural Compute Stick(NCS) Faster than YoloV2 + Explosion speed by RaspberryPi · Multiple moving object detection with high accuracy.
Python - Released: 27 Mar 2018 - 93
Edge TPU Accelerator / Multi-TPU + MobileNet-SSD v2 + Python + Async + LattePandaAlpha/RaspberryPi3/LaptopPC
Python - Released: 11 Mar 2019 - 82
WHENet - ONNX, OpenVINO, TFLite, TensorRT, EdgeTPU, CoreML, TFJS, YOLOv4/YOLOv4-tiny-3L
Python - Released: 15 Nov 2021 - 66
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.
Python - Released: 19 Jun 2022 - 62
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.
Python - Released: 18 Oct 2018 - 78
OpenVINO+NCS2/NCS+MutiModel(FaceDetection, EmotionRecognition)+MultiStick+MultiProcess+MultiThread+USB Camera/PiCamera. RaspberryPi 3 compatible. Async.
Python - Released: 02 Mar 2019 - 57
HandLandmark Detection that can be performed only in onnxruntime. Pre-focusing by skeletal detection is not performed. This does not use MediaPipe.
Python - Released: 31 Oct 2023 - 16
Simple ONNX operation generator. Simple Operation Generator for ONNX.
Python - Released: 10 Apr 2022 - 7