mkocabas / Pose Residual Network
Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network (ECCV 2018)' paper
Stars: ✭ 337
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Pose Residual Network
Unofficial Implement Of Openpose
Implement of Openpose use Tensorflow
Stars: ✭ 222 (-34.12%)
Mutual labels: deep-neural-networks, pose-estimation
Poseestimationformobile
💃 Real-time single person pose estimation for Android and iOS.
Stars: ✭ 783 (+132.34%)
Mutual labels: deep-neural-networks, pose-estimation
Pytorch Cpn
A PyTorch re-implementation of CPN (Cascaded Pyramid Network for Multi-Person Pose Estimation)
Stars: ✭ 403 (+19.58%)
Mutual labels: deep-neural-networks, pose-estimation
Pose Residual Network Pytorch
Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network' paper https://arxiv.org/abs/1807.04067
Stars: ✭ 277 (-17.8%)
Mutual labels: deep-neural-networks, pose-estimation
Agentnet
Deep Reinforcement Learning library for humans
Stars: ✭ 298 (-11.57%)
Mutual labels: deep-neural-networks
Cascaded Fcn
Source code for the MICCAI 2016 Paper "Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional NeuralNetworks and 3D Conditional Random Fields"
Stars: ✭ 296 (-12.17%)
Mutual labels: deep-neural-networks
Adversarial Examples Pytorch
Implementation of Papers on Adversarial Examples
Stars: ✭ 293 (-13.06%)
Mutual labels: deep-neural-networks
Deepcut
A Thai word tokenization library using Deep Neural Network
Stars: ✭ 330 (-2.08%)
Mutual labels: deep-neural-networks
Ai Deadlines
⏰ AI conference deadline countdowns
Stars: ✭ 3,852 (+1043.03%)
Mutual labels: deep-neural-networks
Tensorflow Image Detection
A generic image detection program that uses Google's Machine Learning library, Tensorflow and a pre-trained Deep Learning Convolutional Neural Network model called Inception.
Stars: ✭ 306 (-9.2%)
Mutual labels: deep-neural-networks
Awesome Deep Vision Web Demo
A curated list of awesome deep vision web demo
Stars: ✭ 298 (-11.57%)
Mutual labels: deep-neural-networks
Rezero
Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"
Stars: ✭ 317 (-5.93%)
Mutual labels: deep-neural-networks
Deep Learning Uncertainty
Literature survey, paper reviews, experimental setups and a collection of implementations for baselines methods for predictive uncertainty estimation in deep learning models.
Stars: ✭ 296 (-12.17%)
Mutual labels: deep-neural-networks
Cntk
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
Stars: ✭ 17,113 (+4978.04%)
Mutual labels: deep-neural-networks
Model Compression Papers
Papers for deep neural network compression and acceleration
Stars: ✭ 296 (-12.17%)
Mutual labels: deep-neural-networks
Rgn
Recurrent Geometric Networks for end-to-end differentiable learning of protein structure
Stars: ✭ 302 (-10.39%)
Mutual labels: deep-neural-networks
Bytenet Tensorflow
ByteNet for character-level language modelling
Stars: ✭ 319 (-5.34%)
Mutual labels: deep-neural-networks
Attention is all you need
Transformer of "Attention Is All You Need" (Vaswani et al. 2017) by Chainer.
Stars: ✭ 303 (-10.09%)
Mutual labels: deep-neural-networks
Yolo V2 Pytorch
YOLO for object detection tasks
Stars: ✭ 302 (-10.39%)
Mutual labels: deep-neural-networks
Pose Residual Network
This repository contains a Keras implementation of the Pose Residual Network (PRN) presented in our ECCV 2018 paper:
Muhammed Kocabas, Salih Karagoz, Emre Akbas. MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network. In ECCV, 2018. Arxiv
PRN is described in Section 3.2 of the paper.
Getting Started
We have tested our method on COCO Dataset
Prerequisites
python
tensorflow
keras
numpy
tqdm
pycocotools
progress
scikit-image
Installing
-
Clone this repository:
git clone https://github.com/mkocabas/pose-residual-network.git -
Install Tensorflow.
-
pip install -r src/requirements.txt -
To download COCO dataset train2017 and val2017 annotations run:
bash data/coco.sh. (data size: ~240Mb)
Training
python main.py
For more options take a look at opt.py
Results
Results on COCO val2017 Ground Truth data.
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.894
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.971
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.912
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.875
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.918
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.909
Average Recall (AR) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.972
Average Recall (AR) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.928
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.896
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets= 20 ] = 0.947
License
Other Implementations
Citation
If you find this code useful for your research, please consider citing our paper:
@Inproceedings{kocabas18prn,
Title = {Multi{P}ose{N}et: Fast Multi-Person Pose Estimation using Pose Residual Network},
Author = {Kocabas, Muhammed and Karagoz, Salih and Akbas, Emre},
Booktitle = {European Conference on Computer Vision (ECCV)},
Year = {2018}
}
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].