Shypd.aiThe largest open index of AI toolsfvcore is a Coding & Development tool that provides a light-weight core library for computer vision frameworks. It offers common functionalities like PyTorch layers, flop counting, and hyperparameter scheduling, shared among FAIR's research projects.
Trending
About
fvcore is a light-weight core library developed by FAIR (Facebook AI Research) that provides essential and common functionalities shared across various computer vision frameworks. It is specifically designed to support projects like Detectron2, PySlowFast, and ClassyVision. The library emphasizes quality, with all components being type-annotated, thoroughly tested, and benchmarked for reliability. Key features include common PyTorch layers, functions, and losses, a hierarchical per-operator flop counting tool, recursive parameter counting, and a stateless, scale-invariant hyperparameter scheduler. fvcore aims to streamline computer vision research and development workflows by offering robust, shared utilities.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
