434 Open source projects that are alternatives of or similar to Fast_Stacked_Hourglass_Network_OpenVino

Perception toolkit for sim2real training and validation

Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software Engineers and Data Scientists wanting to learn the TF.Keras Machine Learning framework

PyTorch Implementation for "TransPose: Keypoint localization via Transformer", ICCV 2021.

LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)

face keypoints deteciton based on stackedhourglass

A face recognition solution on mobile device.

Monitor mechanical bolts as they move down a conveyor belt. When a bolt of an irregular size is detected, this solution emits an alert.

Repository for Single Shot MultiBox Detector and its variants, implemented with pytorch, python3.

Perform Human Pose Estimation in OpenCV Using OpenPose MobileNet

Powerful computer vision assisted Lego mosaic creator · Over 500,000 images created (so far!)

A human perception library

The smart city reference pipeline shows how to integrate various media building blocks, with analytics powered by the OpenVINO™ Toolkit, for traffic or stadium sensing, analytics and management tasks.

RMPE: Regional Multi-person Pose Estimation, forked from Caffe. Research purpose only.

OpenMMLab Image Classification Toolbox and Benchmark

We present MocapNET2, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance (70 fps in CPU-only execution).

Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)

DREAM: Deep Robot-to-Camera Extrinsics for Articulated Manipulators (ICRA 2020)

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

Code for paper "A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image". ICCV2019

Use the YOLO v4 and v5 (ONNX) models for object detection in C# using ML.Net

嵌入式AI公众号: NeuralTalk，Weekly report and awesome list of embedded-ai.

This work is used for pose estimation(yaw, pitch and roll) by Face landmarks(left eye, right eye, nose, left mouth, right mouth and chin)

Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

PSGAN running with ncnn⚡妆容迁移/仿妆⚡Imitation Makeup/Makeup Transfer⚡

U-Net Model conditioned with MobileNet features for Grayscale -> Color mapping

Data preparation and loader for AMASS

⚡ Open-source software for deep learning-based digital pathology

A Light CNN based Method for Hand Detection and Orientation Estimation

3D hand pose estimation via dense regression

Tengine is a lite, high performance, modular inference engine for embedded device

Official repository for "GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition" (ICIP'21)

A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

API for the dataset proposed in "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.

Visualizer for neural network, deep learning, and machine learning models

OpenNCC Kit

php wrapper for opencv

Activity Recognition from 2D pose using an LSTM RNN

Kaldi model converter to ONNX

GUI based on the python api of openpose in windows using cuda10 and cudnn7. Support body , hand, face keypoints estimation and data saving. Realtime gesture recognition is realized through two-layer neural network based on the skeleton collected from the gui.

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.

LiLi-OM is a tightly-coupled, keyframe-based LiDAR-inertial odometry and mapping system for both solid-state-LiDAR and conventional LiDARs.

[CVPR 2020, Oral] Category-Level Articulated Object Pose Estimation

Official PyTorch Implementation of "Ego-Pose Estimation and Forecasting as Real-Time PD Control". ICCV 2019.

Pure C# machine learning framework

SynthDet - An end-to-end object detection pipeline using synthetic data

MLModelCI is a complete MLOps platform for managing, converting, profiling, and deploying MLaaS (Machine Learning-as-a-Service), bridging the gap between current ML training and serving systems.

GPU Accelerated TensorFlow Lite applications on Android NDK. Higher accuracy face detection, Age and gender estimation, Human pose estimation, Artistic style transfer

Open standard for machine learning interoperability

MobileNet trained with VoxCeleb dataset and used for voice verification

separate from 6dpose repo for deployment

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

caffe based mobilenet v2 deploy

[cvpr 20] Demo, training and evaluation code for joint hand-object pose estimation in sparsely annotated videos

Light-weight Single Person Pose Estimator

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021

Awesome work on object 6 DoF pose estimation

Multi-Stage Pose Network

YOLOv5 in PyTorch > ONNX > RKNN

nGraph™ Backend for ONNX

Predict performance issues with manufacturing equipment motors. Perform local or cloud analytics of the issues found, and then display the data on a user interface to determine when failures might arise.