Skip to main content Link Menu Expand (external link) Document Search Copy Copied


  1. Install EasyMocap Quickly
  2. Prepare SMPL models
  3. Install EasyMocap Step-by-Step
  4. Install EasyMocap
  5. Install PyTorch
  6. Install human body prior
  7. Other Modules
    1. NeuralBody

Briefly, you can following our one-step installation instructions. If you want to install the full package or install to you own environments, please see installation instructions.

Install EasyMocap Quickly

Make sure that you have installed cuda11.1 and conda.

git clone
conda create -n easymocap python=3.9 -y
conda activate easymocap
wget -c
wget -c
python3 -m pip install ./torch-1.9.1+cu111-cp39-cp39-linux_x86_64.whl
python3 -m pip install ./torchvision-0.10.1+cu111-cp39-cp39-linux_x86_64.whl
python -m pip install -r requirements.txt
# install pyrender if you have a screen
python3 -m pip install pyrender
python develop

Prepare SMPL models

Download and prepare the needed models as follows. If you just use SMPL model, you can place the smplv1.1.0 here.

To download the SMPL model go to this(version 1.1.0) project website and register to get access to the downloads section. After the downloading, place and extract it at data/bodymodels/:

└── SMPL_python_v.1.1.0
    └── smpl
        ├── models
        │   ├── basicmodel_f_lbs_10_207_0_v1.1.0.pkl
        │   ├── basicmodel_m_lbs_10_207_0_v1.1.0.pkl
        │   └── basicmodel_neutral_lbs_10_207_0_v1.1.0.pkl
        └── smpl_webuser

Other models are optional.

├── FLAME2020
│   ├── flame_dynamic_embedding.npy
│   ├── FLAME_FEMALE.pkl
│   ├── FLAME_MALE.pkl
│   ├── FLAME_NEUTRAL.pkl
│   ├── flame_static_embedding.pkl
│   └── Readme.pdf
├── manov1.2
│   ├── MANO_LEFT.pkl
│   └── MANO_RIGHT.pkl
├── smplhv1.2
│   ├── female
│   ├── info.txt
│   ├── LICENSE.txt
│   ├── male
│   └── neutral
├── SMPL_python_v.1.1.0
│   └── smpl
└── vposer_v02
    ├── snapshots
    ├── V02_05.log
    └── V02_05.yaml

Install EasyMocap Step-by-Step

Briefly, to run the demo, you should at least install:

  1. PyTorch
  2. pyrender for visualization
  3. human body prior
  4. EasyMocap

Install EasyMocap

Then setup the EasyMocap

git clone
python3 -m pip install -r requirements.txt
python3 develop

Install PyTorch

You can install EasyMocap to your current PyTorch environment. Most versions are supported. You can find all versions here

Simply create a conda environment and activate it.

conda create -n easymocap python=3.9 -y
conda activate easymocap
python3 -m pip install torch torchvision

For cuda11.1+Python3.9+torch1.9.1:

conda create -n easymocap python=3.9 -y
conda activate easymocap
wget -c
wget -c
python3 -m pip install ./torch-1.9.1+cu111-cp39-cp39-linux_x86_64.whl
python3 -m pip install ./torchvision-0.10.1+cu111-cp39-cp39-linux_x86_64.whl

Check your cuda environment:

# export CUDA_VER=10.0
# export CUDA_VER=10.1
export CUDA_VER=11.4
export PATH=/usr/local/cuda-$CUDA_VER/bin:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda-$CUDA_VER/lib64:$LD_LIBRARY_PATH

For cuda 10.0:

python3 -m pip install torch-1.4.0+cu100-cp37-cp37m-linux_x86_64.whl
pip install

For cuda 10.1:

conda create -n easymocap python=3.7 -y
conda activate easymocap
wget -c
wget -c
python3 -m pip install ./torch-1.7.1+cu101-cp37-cp37m-linux_x86_64.whl
python3 -m pip install ./torchvision-0.8.2+cu101-cp37-cp37m-linux_x86_64.whl

Install human body prior

You can skip this if you don’t use this module.

bash ./scripts/install/

Other Modules

After this, if you want to use the different modules, you should install their corresponding requirements:


python3 -m pip install -r requirements_neuralbody.txt
python3 -m pip install spconv-cu111
# install pytorch3d when you want to use AniNerf
bash ./scripts/install/

Table of contents