Discover PINTO0309/DirectMHP_YOLOv7 Open Source project

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.

3,504

onnx2tf

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

669

OpenVINO-YoloV3

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

535

Tensorflow-bin

[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

478

MobileNet-SSD-RealSense

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.

355

openvino2tensorflow

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.

318

simple-onnx-processing-tools

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.

266

tflite2tensorflow

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

239

TensorflowLite-bin

[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.

181

Keras-OneClassAnomalyDetection

Jupyter Notebook

120

mediapipe-bin

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

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

113

MobileNetV2-PoseEstimation

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

105

MobileNet-SSD

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.

wsl2_linux_kernel_usbcam_enable_conf

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

TPU-MobilenetSSD

ONNX implementation of Whisper. PyTorch free.

whisper-onnx-cpu

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.

TensorflowLite-UNet

WHENet - ONNX, OpenVINO, TFLite, TensorRT, EdgeTPU, CoreML, TFJS, YOLOv4/YOLOv4-tiny-3L

HeadPoseEstimation-WHENet-yolov4-onnx-openvino

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.

DMHead

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

OpenVINO-EmotionRecognition

ONNX and TensorRT implementation of Whisper

whisper-onnx-tensorrt

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

scs4onnx

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

MobileNet-SSDLite-RealSense-TF

[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

OpenVINO-DeeplabV3

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.

hand-gesture-recognition-using-onnx

Jupyter Notebook

TPU-Posenet

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

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

faster-whisper-env

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.

facemesh_onnx_tensorrt

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.

yolact_edge_onnx_tensorrt_myriad

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

crowdhuman_hollywoodhead_yolo_convert

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.

simple_fisheye_calibrator

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

onnx2json

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

tflite2json2tflite

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.

mtomo

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

MobileNetv2-SSDLite

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

Bazel_bin

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

BoT-SORT-ONNX-TensorRT

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

pytorch4raspberrypi

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.

scc4onnx

onnxruntime for RaspberryPi armv7l

onnxruntime4raspberrypi

zumo32u4

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

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

20220228_intel_deeplearning_day_hitnet_demo

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

TensorflowLite-flexdelegate

C++

sit4onnx

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

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.

spo4onnx

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

hand_landmark

Converts a JSON file to an ONNX file.

json2onnx

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

snc4onnx

Simple tool to change the INPUT and OUTPUT shape of ONNX.

sio4onnx

Provide Docker build sequences of Open3D for various environments.

Open3D-build

Drone + OpenVINO + ObjectDetection + FaceRecognition + MobileNetV2 PoseEstiation

gesture-drone

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

OpenVINO-ADAS

OpenVINO installer storage location (Full version)

OpenVINO-bin

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.

sne4onnx

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.

jetson-tensorflow-pytorch-build

Provide Docker build sequences of PyTorch for various environments.

PyTorch-build

Masked Face Image Augmentation Tool for Dataset 300W-LP with 6D Head Pose Information.

Face_Mask_Augmentation

A very simple tool to rewrite parameters such as attributes and constants for OPs in ONNX models. Simple Attribute and Constant Modifier for ONNX.

sam4onnx

A simple program that returns RFC5646 style language codes and country code symbols from microphone input or wav byte arrays. e.g. ja-JP, en-US, ...

onnx-speech-language-detection

[WIP] ONNX parts yard. The various operations described in Operator Schemas are converted in advance into OP stand-alone ONNX files.

components_of_onnx

This tool displays tflite signatures and rewrites the input/output OP name to the name of the signature. There is no need to install TensorFlow or TFLite.

tflite-input-output-rewriter

Build an ffmpeg RTSP distribution server using an old alpine:3.8 Docker Image.

rtspserver-ffmpeg

Monocular 3D pose estimation. OpenVINO. CPU inference or iGPU (OpenCL) inference.

human-pose-estimation-3d-python-cpp

A very simple tool that forces a change in the opset of an ONNX graph. Simple Opset Changer for ONNX.

soc4onnx

A very simple script that only initializes the batch size of ONNX. Simple Batchsize Initialization for ONNX.

sbi4onnx

Simple ONNX operation generator. Simple Operation Generator for ONNX.

sog4onnx

Simple node deletion tool for onnx.

snd4onnx

Very simple recording tool using only OpenCV. Automatically record the camera capture to mp4, press C key or left mouse button click captures the image.

simple_camera_capture

ONNX export environment for mmaction2

mmaction2-onnx-export-env

OS image repository for RaspberryPi3.

RaspberryPi-bin

Simple ONNX constant encoder/decoder. Since the constant values in the JSON files generated by onnx2json are Base64-encoded values, ASCII <-> Base64 conversion is required when rewriting JSON constant values.

sed4onnx

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

TinyYolo

Simple OP Renamer for ONNX.

PINTO0309

sor4onnx

Deb package for introducing OpenCV to RaspberryPi3.

OpenCVonARMv7

sna4onnx

Simple node addition tool for onnx. Simple Node Addition for ONNX.

Checker with simple ONNX model structure. Simple Structure Checker for ONNX.

ssc4onnx

RealSense execution environment built on a Docker container on Ubuntu 20.04. NIVIDA GPU and OpenGL capable. CUADA 11.4.

realsense-cuda-opengl-docker

A set of simple tools for ROS2 of my own making.

simple-ros2-processing-tools

300W_LP_AFLW2000_viewer

Simple model Output OP Additional tools for ONNX.

soa4onnx

Execution environment of mmrotate

mmrotate-exec-env

TVM build and run test environment

tvm-build

Simple Shape Inference tool for ONNX.

ssi4onnx

Prebuilt binary for EdgeTPU PythonAPI standalone installer.

edgetpu-bin

NITEC-ONNX-TensorRT

ONNX implementation of "NITEC: Versatile Hand-Annotated Eye Contact Dataset for Ego-Vision Interaction" https://github.com/thohemp/nitec

Simply crop the face from the image at high speed and save.

Human-Face-Crop-ONNX-TensorRT

NVIDIA Maxine - A playground for running the Audio Effects SDK.

Maxine-env

RaspberryPi3へのTBB(Intel Threading Building Blocks)導入用debパッケージ保管庫

TBBonARMv7

sod4onnx

Simple model Output OP Deletion tools for ONNX.

A very simple tool that forces a change in the IR Version of an ONNX graph. Simple IR version Changer for ONNX.

sic4onnx

RTSP distribution server for USB camera video using v4l2 with Docker container on Ubuntu 20.04.

rtspserver-v4l2

Procedures and tools for semi-mechanically automatically generating YoloV2 original learning data from video.

YoloTrainDataGenerate

A simple tool to record ROS2 Image topics to MP4.

rosdepth2mp4

ZED2 SDK Installed Containers

ZED2-Docker

Simple doc_string eraser for ONNX.

sde4onnx

DeepLearningMugenKnock

Tensorflow implementation of SegNet Tensorflow 1.11.0 + Python (I made minor bugfixes for toimcio/SegNet-tensorflow)

SegNet-TF

Jupyter Notebook

yolov9-wholebody25-tensorflowjs-web-test

A test environment running yolov9-wholebody25 on TensorFlow.js.

HTML

100

svs4onnx

A very simple tool to swap connections between output and input variables in an ONNX graph. Simple Variable Switch for ONNX.