- Python >= 3.6
- Numpy
- PyTorch 1.3
- fvcore:
pip install 'git+https://github.com/facebookresearch/fvcore'
- torchvision that matches the PyTorch installation. You can install them together at pytorch.org to make sure of this.
- simplejson:
pip install simplejson
- GCC >= 4.9
- PyAV:
conda install av -c conda-forge
- ffmpeg (4.0 is prefereed, will be installed along with PyAV)
- PyYaml: (will be installed along with fvcore)
- tqdm: (will be installed along with fvcore)
- psutil:
pip install psutil
- OpenCV:
pip install opencv-python
- torchvision:
pip install torchvision
orconda install torchvision -c pytorch
- tensorboard:
pip install tensorboard
- moviepy: (optional, for visualizing video on tensorboard)
conda install -c conda-forge moviepy
orpip install moviepy
- Detectron2:
pip install -U torch torchvision cython
pip install -U 'git+https://github.com/facebookresearch/fvcore.git' 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
git clone https://github.com/facebookresearch/detectron2 detectron2_repo
pip install -e detectron2_repo
# You can find more details at https://github.com/facebookresearch/detectron2/blob/master/INSTALL.md
Clone the LSTC repository and setup the pyslowfast package
git clone https://github.com/facebookresearch/slowfast
cd LSTC
python3 setup.py build
Add the installed package to $PYTHONPATH.
export PYTHONPATH=/path/to/LSTC/build/lib:$PYTHONPATH