DeepPose
NOTE: This is not official implementation. Original paper is DeepPose: Human Pose Estimation via Deep Neural Networks.
Requirements
I strongly recommend to use Anaconda environment. This repo may be able to be used in Python 2.7 environment, but I haven't tested.
Installation of dependencies
pip install chainer
pip install numpy
pip install scikit-image
# for python3
conda install -c https://conda.binstar.org/menpo opencv3
# for python2
conda install opencv
Dataset preparation
bash datasets/download.sh
python datasets/flic_dataset.py
python datasets/lsp_dataset.py
python datasets/mpii_dataset.py
MPII Dataset
Start training
Starting with the prepared shells is the easiest way. If you want to run train.py
with your own settings, please check the options first by python scripts/train.py --help
and modify one of the following shells to customize training settings.
For FLIC Dataset
bash shells/train_flic.sh
For LSP Dataset
bash shells/train_lsp.sh
For MPII Dataset
bash shells/train_mpii.sh
GPU memory requirement
AlexNet
batchsize: 128 -> about 2870 MiB
batchsize: 64 -> about 1890 MiB
batchsize: 32 (default) -> 1374 MiB
ResNet50
Prediction
Will add some tools soon