GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → YuliangXiu → MobilePose

YuliangXiu / MobilePose

Licence: other
Light-weight Single Person Pose Estimator

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language
matlab
3953 projects
lua
6591 projects
C++
36643 projects - #6 most used programming language
c
50402 projects - #5 most used programming language

Labels

lightweightmachine-learningreal-timedeep-learningheatmaprealtimepytorchdataloadersqueezenetdata-augmentationpose-estimationmobile-deviceshufflenetresnet-18mobilenetv2deepposeshufflenet-v2shufflenetv2dsntnn

Projects that are alternatives of or similar to MobilePose

Mobilepose Pytorch
Light-weight Single Person Pose Estimator
Stars: ✭ 427 (-27.38%)
Mutual labels:  lightweight, heatmap, realtime, dataloader, data-augmentation, pose-estimation, mobilenetv2
Tensorrtx
Implementation of popular deep learning networks with TensorRT network definition API
Stars: ✭ 3,456 (+487.76%)
Mutual labels:  squeezenet, mobilenetv2, shufflenetv2
rmpe dataset server
Realtime Multi-Person Pose Estimation data server. Used as a training and validation data provider in training process.
Stars: ✭ 14 (-97.62%)
Mutual labels:  realtime, pose-estimation
Poseflow
PoseFlow: Efficient Online Pose Tracking (BMVC'18)
Stars: ✭ 330 (-43.88%)
Mutual labels:  realtime, pose-estimation
Mobilenet V2
A Complete and Simple Implementation of MobileNet-V2 in PyTorch
Stars: ✭ 206 (-64.97%)
Mutual labels:  realtime, mobilenetv2
Pytorch Cifar100
Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)
Stars: ✭ 2,423 (+312.07%)
Mutual labels:  squeezenet, shufflenet
Tensorflow-data-loader
Reading data into tensorflow using tf.data function
Stars: ✭ 15 (-97.45%)
Mutual labels:  dataloader, data-augmentation
Alphapose
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
Stars: ✭ 5,697 (+868.88%)
Mutual labels:  realtime, pose-estimation
Tf Pose Estimation
Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
Stars: ✭ 3,856 (+555.78%)
Mutual labels:  realtime, pose-estimation
Heatmap for tushare
Create a heatmap for Real time China stocks price by Tushare's data
Stars: ✭ 41 (-93.03%)
Mutual labels:  heatmap, realtime
Improved Body Parts
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation
Stars: ✭ 202 (-65.65%)
Mutual labels:  heatmap, pose-estimation
LightNet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 710 (+20.75%)
Mutual labels:  shufflenet, mobilenetv2
MobilePose-Pi
MobilePose deployment for Raspberry Pi
Stars: ✭ 15 (-97.45%)
Mutual labels:  pose-estimation, mobilenetv2
FastPose
pytorch realtime multi person keypoint estimation
Stars: ✭ 36 (-93.88%)
Mutual labels:  realtime, pose-estimation
TensorMONK
A collection of deep learning models (PyTorch implemtation)
Stars: ✭ 21 (-96.43%)
Mutual labels:  shufflenet, mobilenetv2
Multi-Person-Pose-using-Body-Parts
No description or website provided.
Stars: ✭ 41 (-93.03%)
Mutual labels:  heatmap, pose-estimation
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 (-76.7%)
Mutual labels:  lightweight, pose-estimation
OffsetGuided
Code for "Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation"
Stars: ✭ 31 (-94.73%)
Mutual labels:  heatmap, pose-estimation
koochak
A minimal & lightweight CSS framework
Stars: ✭ 15 (-97.45%)
Mutual labels:  lightweight
TD-OpenCV3TOP
Touchdesigner OpenCV3 C++ TOP for FaceDetect
Stars: ✭ 90 (-84.69%)
Mutual labels:  realtime
View All Similar Projects ➔

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:

  1. pytorch-mobilenet-v2
  2. Vanilla FCN, U-Net, SegNet, PSPNet, GCN, DUC
  3. Shufflenet-v2-Pytorch
  4. tf-pose-estimation
  5. dsntnn

NEWS!

  • Apr 2021: Siyuan Pan provides MNN version!
  • Mar 2019: Support running on MacBook with decent FPS!
  • Feb 2019: ALL the pretrained model files are avaliable!

Requirements

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

  • multi-thread dataloader with augmentations (dataloader.py)
  • training and inference (training.py)
  • performance evaluation (eval.py)
  • multiple models support (network.py)
  • ipython notebook visualization (demo.ipynb)
  • Macbook camera realtime display script (run_webcam.py)

Usage

  1. Installation:
pip install -r requirements.txt
  1. Training:
python training.py --model shufflenetv2 --gpu 0 --inputsize 224 --lr 1e-3 --batchsize 128 --t7 ./models/shufflenetv2_224_adam_best.t7
  1. Evaluation
ln -s cocoapi/PythonAPI/pycocotools
cd cocoapi/PythonAPI && make

python eval.py --t7 ./models/resnet18_224_adam_best.t7 --model resnet18 --gpu 0
  1. 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. Thanks for Siyuan Pan's implementation of mnn version.

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].