Skip to content

Latest commit

 

History

History
44 lines (36 loc) · 1.31 KB

INSTALL.md

File metadata and controls

44 lines (36 loc) · 1.31 KB
Raw

Installation

Requirements

  • 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)

Pytorch

Please follow PyTorch official instructions to install from source: git clone --recursive https://github.com/pytorch/pytorch

PySlowFast

Clone the PySlowFast Video Understanding repository.

git clone https://github.com/facebookresearch/slowfast

Add this repository to $PYTHONPATH.

export PYTHONPATH=/path/to/PySlowFast/lib:$PYTHONPATH

Build PySlowFast

After having the above dependencies, run:

git clone git@github.com:facebookresearch/slowfast.git
cd slowfast
python setup.py build develop

Now the installation is finished, run the pipeline with:

python tools/run_net.py --cfg configs/Kinetics/C2D_8x8_R50.yaml NUM_GPUS 1 TRAIN.BATCH_SIZE 8 SOLVER.BASE_LR 0.0125 DATA.PATH_TO_DATA_DIR path_to_your_data_folder