fvcore is a light-weight core library that provides the most common and essential functionality shared in various computer vision frameworks developed in FAIR, such as Detectron2. This library is based on Python 3.6+ and PyTorch. All the components in this library are type-annotated, tested, and benchmarked.
The computer vision team in FAIR is responsible for maintaining this library.
fvcore requires python >= 3.6.
Use one of the following ways to install:
pip install -U fvcore
conda install -c conda-forge yacs
conda install -c fvcore fvcore
pip install -U 'git+https://github.com/facebookresearch/fvcore'
git clone https://github.com/facebookresearch/fvcore
pip install -e fvcore
This library is released under the Apache 2.0 license.