YuliangXiu / Mobilepose Pytorch
Light-weight Single Person Pose Estimator
Stars: ✭ 427
Labels
Projects that are alternatives of or similar to Mobilepose Pytorch
MobilePose
Light-weight Single Person Pose Estimator
Stars: ✭ 588 (+37.7%)
Mutual labels: lightweight, heatmap, realtime, dataloader, data-augmentation, pose-estimation, mobilenetv2
Keras realtime multi Person pose estimation
Keras version of Realtime Multi-Person Pose Estimation project
Stars: ✭ 728 (+70.49%)
Mutual labels: jupyter-notebook, pose-estimation, real-time
Poseflow
PoseFlow: Efficient Online Pose Tracking (BMVC'18)
Stars: ✭ 330 (-22.72%)
Mutual labels: pose-estimation, real-time, realtime
Gccpm Look Into Person Cvpr19.pytorch
Fast and accurate single-person pose estimation, ranked 10th at CVPR'19 LIP challenge. Contains implementation of "Global Context for Convolutional Pose Machines" paper.
Stars: ✭ 137 (-67.92%)
Mutual labels: lightweight, pose-estimation, real-time
FastPose
pytorch realtime multi person keypoint estimation
Stars: ✭ 36 (-91.57%)
Mutual labels: real-time, realtime, pose-estimation
Dab
Data Augmentation by Backtranslation (DAB) ヽ( •_-)ᕗ
Stars: ✭ 294 (-31.15%)
Mutual labels: jupyter-notebook, data-augmentation
Sc Crud Sample
Sample real-time CRUD inventory tracking app built with SocketCluster
Stars: ✭ 323 (-24.36%)
Mutual labels: real-time, realtime
Lightweight Human Pose Estimation 3d Demo.pytorch
Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.
Stars: ✭ 331 (-22.48%)
Mutual labels: lightweight, real-time
Amazon Forest Computer Vision
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks
Stars: ✭ 346 (-18.97%)
Mutual labels: jupyter-notebook, data-augmentation
Lightweight Segmentation
Lightweight models for real-time semantic segmentation(include mobilenetv1-v3, shufflenetv1-v2, igcv3, efficientnet).
Stars: ✭ 261 (-38.88%)
Mutual labels: lightweight, real-time
Aws Mobile Appsync Events Starter React
GraphQL starter application with Realtime and Offline functionality using AWS AppSync
Stars: ✭ 337 (-21.08%)
Mutual labels: real-time, realtime
Clearly
Clearly see and debug your celery cluster in real time!
Stars: ✭ 287 (-32.79%)
Mutual labels: real-time, realtime
Android Ddp
[UNMAINTAINED] Meteor's Distributed Data Protocol (DDP) for clients on Android
Stars: ✭ 271 (-36.53%)
Mutual labels: real-time, realtime
Deltapy
DeltaPy - Tabular Data Augmentation (by @firmai)
Stars: ✭ 344 (-19.44%)
Mutual labels: jupyter-notebook, data-augmentation
Yolact
A simple, fully convolutional model for real-time instance segmentation.
Stars: ✭ 4,057 (+850.12%)
Mutual labels: real-time, realtime
Realtime Server
A realtime dedicated game server ( FPS / MOBA ). 一个实时的专用游戏服务器.
Stars: ✭ 358 (-16.16%)
Mutual labels: real-time, realtime
Touchdesigner shared
TouchDesigner toxes and small projects
Stars: ✭ 385 (-9.84%)
Mutual labels: real-time, realtime
Icnet Tensorflow
TensorFlow-based implementation of "ICNet for Real-Time Semantic Segmentation on High-Resolution Images".
Stars: ✭ 396 (-7.26%)
Mutual labels: jupyter-notebook, real-time
MobilePose
MobilePose is a Tiny PyTorch implementation of single person 2D pose estimation framework. The aim is to provide the interface of the training/inference/evaluation, and the dataloader with various data augmentation options. And final trained model can satisfy basic requirements(speed+size+accuracy) for mobile device.
Some codes for networks and display are brought from:
- pytorch-mobilenet-v2
- Vanilla FCN, U-Net, SegNet, PSPNet, GCN, DUC
- Shufflenet-v2-Pytorch
- tf-pose-estimation
- dsntnn
NEWS!
- Mar 2019: Support running on MacBook with decent FPS!
- Feb 2019: ALL the pretrained model files are avaliable!
Requirements
- Python 3.7
- PyTorch 1.0
- dsntnn 1.0
Evaluation Results
Model(+DUC+DSNTNN) | Parmas(M) | Flops(G) | [email protected]:0.95 | [email protected] | [email protected]:0.95 | [email protected] | Link |
---|---|---|---|---|---|---|---|
ResNet18 | 12.26 | 1.64 | 68.2 | 93.9 | 79.7 | 96.7 | 51.5M |
MobileNetV2 | 3.91 | 0.49 | 67.5 | 94.9 | 79.4 | 97.1 | 16.6M |
ShuffleNetV2 | 2.92 | 0.31 | 61.5 | 91.6 | 74.8 | 95.5 | 12.4M |
SqueezeNet1.1 | 2.22 | 0.63 | 58.4 | 92.1 | 72.3 | 95.8 | 9.3M |
Features
- [x] multi-thread dataloader with augmentations (dataloader.py)
- [x] training and inference (training.py)
- [x] performance evaluation (eval.py)
- [x] multiple models support (network.py)
- [x] ipython notebook visualization (demo.ipynb)
- [x] Macbook camera realtime display script (run_webcam.py)
Usage
- Installation:
pip install -r requirements.txt
- Training:
python training.py --model shufflenetv2 --gpu 0 --inputsize 224 --lr 1e-3 --batchsize 128 --t7 ./models/shufflenetv2_224_adam_best.t7
- Evaluation
ln -s cocoapi/PythonAPI/pycocotools
cd cocoapi/PythonAPI && make
python eval.py --t7 ./models/resnet18_224_adam_best.t7 --model resnet18 --gpu 0
- Web Camera Demo (MacBook)
python run_webcam.py --model squeezenet --inp_dim 224 --camera 0
Contributors
MobilePose is developed and maintained by Yuliang Xiu, Zexin Chen and Yinghong Fang.
License
MobilePose is freely available for free non-commercial use. For commercial queries, please contact Cewu Lu.
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].