PyTorch-Pose is a PyTorch implementation of the general pipeline for 2D single human pose estimation. The aim is to provide the interface of the training/inference/evaluation, and the dataloader with various data augmentation options for the most popular human pose databases (e.g., the MPII human pose, LSP and FLIC).
Some codes for data preparation and augmentation are brought from the Stacked hourglass network. Thanks to the original author.
Update: this repository is compatible with PyTorch 0.4.1/1.0 now!
- Multi-thread data loading
- Multi-GPU training
- Training/testing results visualization
PyTorch (>= 0.4.1): Please follow the installation instruction of PyTorch. Note that the code is developed with Python2 and has not been tested with Python3 yet.
Clone the repository with submodule
git clone --recursive https://github.com/bearpaw/pytorch-pose.git
Create a symbolic link to the
imagesdirectory of the MPII dataset:
ln -s PATH_TO_MPII_IMAGES_DIR data/mpii/images
For training/testing on COCO, please refer to COCO Readme.
- Download annotation file:
Please refer to TRAINING.md for detailed training recipes!
You may download our pretrained models (e.g., 2-stack hourglass model) for a quick start.
Run the following command in terminal to evaluate the model on MPII validation split (The train/val split is from Tompson et al. CVPR 2015).
CUDA_VISIBLE_DEVICES=0 python example/main.py --dataset mpii -a hg --stacks 2 --blocks 1 --checkpoint checkpoint/mpii/hg_s2_b1 --resume checkpoint/mpii/hg_s2_b1/model_best.pth.tar -e -d
-aspecifies a network architecture
--resumewill load the weight from a specific model
-estands for evaluation only
-dwill visualize the network output. It can be also used during training
The result will be saved as a
.mat file (
preds_valid.mat), which is a
2958x16x2 matrix, in the folder specified by
[email protected] scoreEvaluate the
Evaluate with MATLAB
You may use the matlab script
evaluation/eval_PCKh.m to evaluate your predictions. The evaluation code is ported from Tompson et al. CVPR 2015.
The results ([email protected] score) trained using this code is reported in the following table.
Training / validation curve is visualized as follows.
Evaluate with Python
You may also evaluate the result by running
python evaluation/eval_PCKh.py to evaluate the predictions. It will produce exactly the same result as that of the MATLAB. Thanks @sssruhan1 for the contribution.
Run the following command in terminal to train an 8-stack of hourglass network on the MPII human pose dataset.
CUDA_VISIBLE_DEVICES=0 python example/main.py --dataset mpii -a hg --stacks 8 --blocks 1 --checkpoint checkpoint/mpii/hg8 -j 4
CUDA_VISIBLE_DEVICES=0identifies the GPU devices you want to use. For example, use
CUDA_VISIBLE_DEVICES=0,1if you want to use two GPUs with ID
-jspecifies how many workers you want to use for data loading.
--checkpointspecifies where you want to save the models, the log and the predictions to.
- Stacked Hourglass networks
- Xiao et al., Simple Baselines for Human Pose Estimation and Tracking, ECCV 2018 (PDF | GitHub)
Please create a pull request if you want to contribute.