namedBen / Convolutional Pose Machines Pytorch
Pytroch version of Convolutional Pose Machines
Stars: β 77
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Convolutional Pose Machines Pytorch
Hand3d
Network estimating 3D Handpose from single color images
Stars: β 690 (+796.1%)
Mutual labels: pose-estimation
Poseosc
πΉπ€ΈββοΈπ€ΎββοΈπ€Ί PoseNet + OSC: send realtime human pose estimation data to your apps
Stars: β 40 (-48.05%)
Mutual labels: pose-estimation
Supergluepretrainednetwork
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
Stars: β 1,122 (+1357.14%)
Mutual labels: pose-estimation
Keras realtime multi Person pose estimation
Keras version of Realtime Multi-Person Pose Estimation project
Stars: β 728 (+845.45%)
Mutual labels: pose-estimation
Hyperpose
HyperPose: A Collection of Real-time Human Pose Estimation
Stars: β 961 (+1148.05%)
Mutual labels: pose-estimation
Pose Tensorflow
Human Pose estimation with TensorFlow framework
Stars: β 1,042 (+1253.25%)
Mutual labels: pose-estimation
Openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
Stars: β 662 (+759.74%)
Mutual labels: pose-estimation
Adversarial Pose Pytorch
A PyTorch implementation of adversarial pose estimation for multi-person
Stars: β 67 (-12.99%)
Mutual labels: pose-estimation
Hierarchical Localization
Visual localization made easy with hloc
Stars: β 997 (+1194.81%)
Mutual labels: pose-estimation
Wisppn
test example of paper, Can WiFi Estimate Person Pose?
Stars: β 55 (-28.57%)
Mutual labels: pose-estimation
Pytorch Pose
A PyTorch toolkit for 2D Human Pose Estimation.
Stars: β 932 (+1110.39%)
Mutual labels: pose-estimation
Carposedemo
Real-time Mobile Car Pose Estimation with CoreML
Stars: β 49 (-36.36%)
Mutual labels: pose-estimation
Pytorch Openpose
pytorch implementation of openpose including Hand and Body Pose Estimation.
Stars: β 716 (+829.87%)
Mutual labels: pose-estimation
Mmpose
OpenMMLab Pose Estimation Toolbox and Benchmark.
Stars: β 674 (+775.32%)
Mutual labels: pose-estimation
Oat
Real-time position tracker for behavioral research
Stars: β 45 (-41.56%)
Mutual labels: pose-estimation
Fight detection
Real time Fight Detection Based on 2D Pose Estimation and RNN Action Recognition
Stars: β 65 (-15.58%)
Mutual labels: pose-estimation
Chinesetrafficpolicepose
Detects Chinese traffic police commanding poses ζ£ζ΅δΈε½δΊ€θ¦ζζ₯ζεΏ
Stars: β 49 (-36.36%)
Mutual labels: pose-estimation
Convolutional-Pose-Machines-Pytorch
This is a pytroch version of Convolutional Pose Machines, you can find more details in the original paper Convolutional Pose Machines
Results
The result is generated by the model, which has trained 100 epoches.
Requirements
- Python 2.7
- PyTorch 0.3.0
- torchvision 0.2.0
- OpenCv > 2.4.9
The data set
- Download the data set for training LSPet
- (Alternative) Download the data set for validation LSP
- When you want to train some other datasets, please change the code to correspond to your datasets.
Usage
Train
- Set the train parameters in " config/config.yml ".
- Go to the "train_val" folder
cd train_val
. -
python cpm_train.py --gpu 0 1 --train_dir ../dataset/train/lspet_dataset --val_dir ../dataset/val/lsp_dataset --config ../config/config.yml
python cpm_train.py --gpu 0 1 --train_dir ../dataset/train/lspet_dataset --config ../config/config.yml
- You can also train the model like
sudo sh cpm_train.sh
Test
- Go to the "test" folder
cd test
.
python cpm_test.py
Pre-trained model
Notice
- The code of test is just used for visualization,you can change the code to test your own image on condition that you have trained another model "person-center-network"(similar to CPMs).
- I hope that'll be helpful for you.
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].