tfjs
openpose
Our great sponsors
tfjs | openpose | |
---|---|---|
27 | 36 | |
18,041 | 29,627 | |
0.6% | 1.4% | |
8.8 | 5.2 | |
6 days ago | 12 days ago | |
TypeScript | C++ | |
Apache License 2.0 | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tfjs
-
Machine Learning in NodeJS || Part 1: TensorflowJS Basics
TensorflowJS GitHub Repository
- PyTorch Primitives in WebGPU for the Browser
-
I want to talk about WebGPU
Also, Tensorflow.js WebGPU backend has been in the works for quite some time: https://github.com/tensorflow/tfjs/tree/master/tfjs-backend-...
-
WebGPU Fundamentals
It's a pity that tfjs never truly developed any decent ops. E.g. you need lgamma to implement the cap for zero-inflated poisson regression and tfjs simply doesn't have that: https://github.com/tensorflow/tfjs/issues/2011
-
Chrome Ships WebGPU
People have been doing it for long with WebGL, see eg https://github.com/tensorflow/tfjs and https://cloudblogs.microsoft.com/opensource/2021/09/02/onnx-...
-
How to get rotation (yaw/pitch/roll) from face detection keypoints?
thanks, no not unity, going to show it as a demo with threejs + tensorflow on the web. I found a github request to add face orientation https://github.com/tensorflow/tfjs/issues/3835 looks like they assigned someone to add it but doesn't look like its available yet, but there's some posts about the math I can use to get rotations based on some of the landmarks
-
[P] Supporting neural network inference in web browsers
There already exist a wide variety of neural network inference engines that run in web browsers (e.g. TensorFlow.js and, my personal favorite for use with PyTorch models, ONNX Runtime Web), but pre- and post-processing has always required imperative manipulations on flat buffers rather than a clean ndarray interface.
-
Tensorflow JS model crashing on mobile
Full docs and code: https://github.com/tensorflow/tfjs/tree/master/e2e/benchmarks/local-benchmark
-
I built a react native app to recognize if a food is a hot dog or a "not hot dog", inspired by Mr. Jian-Yang (not Mr. Jian, and not Mr. Yang) from Silicon Valley
In this app I used this dataset and trained a custom image classification model using teachable machine. Then I used expo, tfjs, and tfjs-react-native to build the react native app that feeds the camera stream to the model and renders the inference results.
-
Export as tfjs layers model
I haven't looked deeply in how the tfjs layers model is exported, but from Lobe we make a TensorFlow SavedModel and use that as the basis for conversion for the other formats (I believe we use the official tfjs converter for this: https://github.com/tensorflow/tfjs/tree/master/tfjs-converter).
openpose
-
AI "Artists" Are Lazy, and the Ultimate Goal of AI Image Generation (hint: its sloth)
Open Pose, a multi-person keypoint detection library for body, face, hands, and foot estimation [10], is used for posing generated characters;
-
Analyze defects and errors in the created images
OpenPose
-
[D] Which open source models can replicate wonder dynamics's drag'n'drop cg characters?
Perhaps something like OpenPose for pose estimation?
-
Do we have Locally Run AI mocap yet?
OpenPose looks like what you're looking for, it seems to have plugins for Unity. I can't say I've used it though.
-
Accelerate Machine Learning Local Development and Test Workflows with Nvidia Docker
FROM nvidia/cuda:10.0-cudnn7-devel-ubuntu18.04 # https://hub.docker.com/r/nvidia/cuda ENV DEBIAN_FRONTEND=noninteractive # install the dependencies for building OpenPose RUN apt-get update && # The rest is ignored for brevity. RUN pip3 install --no-cache-dir # The rest is ignored for brevity. # install cmake, clone OpenPose and download models RUN wget https://cmake.org/files/v3.20/cmake-3.20.2-linux-x86_64.tar.gz && \ # The rest is ignored for brevity. WORKDIR /openpose/build RUN alias python=python3 && cmake -DBUILD_PYTHON=OFF -DWITH_GTK=OFF -DUSE_CUDNN=ON .. # Build OpenPose. Cudnn 8 causes memory issues this is why we are using base with CUDA 10 and Cudnn 7 # Fix for CUDA 10.0 and Cudnn 7 based on the post below. # https://github.com/CMU-Perceptual-Computing-Lab/openpose/issues/1753#issuecomment-792431838 RUN sed -ie 's/set(AMPERE "80 86")/#&/g' ../cmake/Cuda.cmake && \ sed -ie 's/set(AMPERE "80 86")/#&/g' ../3rdparty/caffe/cmake/Cuda.cmake && \ make -j`nproc` && \ make install WORKDIR /openpose
- nub needs some directions
- How to get rotation (yaw/pitch/roll) from face detection keypoints?
-
Help finding an appropriate model for human pose estimation
Openpose: This is supposedly realtime (I assume on a gpu, 24fps?) and they provide training code
-
We built a free, open-source markerless motion capture system during the pandemic. This animation was created with 4x $20US webcams and a gaming PC, details in the comments [OC]
The pose tracking OP’s using relies on openpose - if you look at the GIFs in their readme, they appear to track individual fingers with fairly high resolution, so I’d imagine it would be fairly straightforward to map that to fret positions.
while I congratulate you for putting together a pipeline, I think it has to be said that the basis of this - the very powerful openpose - has a license that is not completely FOSS. It might be open source but is definitely not free as free beer. So if you consider using this for a fancy project (i.e. marketing an app), you have to get in touch with university of california first https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/LICENSE
What are some alternatives?
mediapipe - Cross-platform, customizable ML solutions for live and streaming media.
AlphaPose - Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
detectron2 - Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
mmpose - OpenMMLab Pose Estimation Toolbox and Benchmark.
lightweight-human-pose-estimation.pytorch - Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
BlazePose-tensorflow - A third-party Tensorflow Implementation for paper "BlazePose: On-device Real-time Body Pose tracking".
MocapNET - We present MocapNET, 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
freemocap - Free Motion Capture for Everyone 💀✨
jetson-inference - Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
VIBE - Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
face-api.js - JavaScript API for face detection and face recognition in the browser and nodejs with tensorflow.js
webhl - WebHL is a fork of hlviewer.js that uses the File System Access API to load game assets direct from your computer rather than from a server.