Skip to content
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.

Latest commit

 

History

History
35 lines (30 loc) · 1.12 KB

DATA_PREP.md

File metadata and controls

35 lines (30 loc) · 1.12 KB

Data preparation

  1. Setup the ZJU-Mocap dataset: Fill in the agreement and email Peng Sida (pengsida@zju.edu.cn) and cc Xiaowei Zhou (xwzhou@zju.edu.cn) to request the download link.

  2. Create a soft link:

mkdir ./data
ln -s /path/to/zju_mocap ./data/zju_mocap
  1. Download the precalculated 3D joints from here and extract them into the respective directories:
unzip zju_joints3d.zip
cp -r ./zju_joints3d/* ./data/zju_mocap/
  1. Execute the following script to make the image names consistent for all subjects:
python preprocess/rename_zju.py --data_dir ./data/zju_mocap

After this step the data directory follows the structure:

${./data/zju_mocap}
├── CoreView_313
├── CoreView_315
├── CoreView_377
├── CoreView_386
├── CoreView_387
├── CoreView_390
├── CoreView_392
├── CoreView_393
├── CoreView_394
└── CoreView_396