Pytorch implementation of FlowTrack.
Simple Baselines for Human Pose Estimation and Tracking (https://arxiv.org/pdf/1804.06208.pdf)
- Human detection
- Single person pose estimation
- Optical flow estimation
- Box propagation
- Pose tracking
pytorch >= 0.4.0
torchvision
pycocotools
tensorboardX
cd lib
./make.sh
Disable cudnn for batch_norm:
# PYTORCH=/path/to/pytorch
# for pytorch v0.4.0
sed -i "1194s/torch\.backends\.cudnn\.enabled/False/g" ${PYTORCH}/torch/nn/functional.py
# for pytorch v0.4.1
sed -i "1254s/torch\.backends\.cudnn\.enabled/False/g" ${PYTORCH}/torch/nn/functional.py
Download data folder as $ROOT/data
.
python ./tools/pose/main.py
The official code is released on Microsoft/human-pose-estimation.pytorch.
#TODO
Download pretrained detection model into models/detection/
. Refer to pytorch-faster-rcnn for more information.
python ./tools/detection/demo.py
Download pretrained flownet into models/flownet/
. Refer to flownet2-pytorch for more information.
python ./tools/flownet/demo.py --model </path/to/model>
2018.12.05:
- Add Pose Estimation Models
- Deconv DenseNet
- Stacked Hourglass Network
- FPN