All Projects → sydsim → Personlab Tf

sydsim / Personlab Tf

implementation of PersonLab(https://arxiv.org/abs/1803.08225) using TF-slim

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Personlab Tf

Pytorch Pose Estimation
PyTorch Implementation of Realtime Multi-Person Pose Estimation project.
Stars: ✭ 152 (+47.57%)
Mutual labels:  jupyter-notebook, human-pose-estimation
Metrabs
This is a computer vision algorithm that takes a single RGB image as the input and estimates 3D human poses as the output.
Stars: ✭ 123 (+19.42%)
Mutual labels:  jupyter-notebook, human-pose-estimation
Tensorflow realtime multi Person pose estimation
Multi-Person Pose Estimation project for Tensorflow 2.0 with a small and fast model based on MobilenetV3
Stars: ✭ 129 (+25.24%)
Mutual labels:  jupyter-notebook, human-pose-estimation
Keraspersonlab
Keras-tensorflow implementation of PersonLab (https://arxiv.org/abs/1803.08225)
Stars: ✭ 163 (+58.25%)
Mutual labels:  jupyter-notebook, human-pose-estimation
Pytorch realtime multi Person pose estimation
Pytorch version of Realtime Multi-Person Pose Estimation project
Stars: ✭ 205 (+99.03%)
Mutual labels:  jupyter-notebook, human-pose-estimation
Realtime multi Person pose estimation
Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)
Stars: ✭ 4,760 (+4521.36%)
Mutual labels:  jupyter-notebook, human-pose-estimation
Epipolarpose
Self-Supervised Learning of 3D Human Pose using Multi-view Geometry (CVPR2019)
Stars: ✭ 477 (+363.11%)
Mutual labels:  jupyter-notebook, human-pose-estimation
Keras realtime multi Person pose estimation
Keras version of Realtime Multi-Person Pose Estimation project
Stars: ✭ 728 (+606.8%)
Mutual labels:  jupyter-notebook, human-pose-estimation
Dlschl
Stars: ✭ 103 (+0%)
Mutual labels:  jupyter-notebook
Deep ctr
Stars: ✭ 102 (-0.97%)
Mutual labels:  jupyter-notebook
Keras Openpose Reproduce
Keras implementation of Realtime Multi-Person Pose Estimation
Stars: ✭ 102 (-0.97%)
Mutual labels:  jupyter-notebook
Scipy2017 Jupyter Widgets Tutorial
Notebooks for the SciPy 2017 tutorial "The Jupyter Interactive Widget Ecosystem"
Stars: ✭ 102 (-0.97%)
Mutual labels:  jupyter-notebook
Facemesh.pytorch
This is the PyTorch implementation of paper Real-time Facial Surface Geometry from Monocular Video on Mobile GPUs (https://arxiv.org/pdf/1907.06724.pdf)
Stars: ✭ 101 (-1.94%)
Mutual labels:  jupyter-notebook
Models
DLTK Model Zoo
Stars: ✭ 101 (-1.94%)
Mutual labels:  jupyter-notebook
Jumptutorials.jl
Tutorials on using JuMP for mathematical optimization in Julia
Stars: ✭ 103 (+0%)
Mutual labels:  jupyter-notebook
Dataminingnotesandpractice
记录我学习数据挖掘过程的笔记和见到的奇技,持续更新~
Stars: ✭ 103 (+0%)
Mutual labels:  jupyter-notebook
Hic Data Analysis Bootcamp
Workshop on measuring, analyzing, and visualizing the 3D genome with Hi-C data.
Stars: ✭ 102 (-0.97%)
Mutual labels:  jupyter-notebook
Fer
Facial Expression Recognition with a deep neural network as a PyPI package
Stars: ✭ 103 (+0%)
Mutual labels:  jupyter-notebook
Advanced Deep Learning With Python
Advanced Deep Learning with Python
Stars: ✭ 103 (+0%)
Mutual labels:  jupyter-notebook
Advanced Machine Learning With Python
Code repository for Advanced Machine Learning with Python, published by Packt
Stars: ✭ 102 (-0.97%)
Mutual labels:  jupyter-notebook

personlab-tf

This is an implemention of PersonLab using Tensorflow Slim. Resnet and Mobilenet in slim can be used as a pre-trained model. It is explained in the example notebook to understand how to use it.

Environment

this project has tested on this environment.

  • ubuntu 16.04
  • python 3.6
  • numpy 1.14.5
  • tensorflow 1.10.0
  • pycocotools 2.0.0
  • scikit-image 0.14.0

Pretrained Model

MobileNetV2 Based (Didn't measured the accuracy)

--- CAUTION ---

Currently, there is an issue that only appears on CPU environment. (https://github.com/sydsim/personlab-tf/issues/7)

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].