• License: BSD-3-Clause
• Home: https://github.com/best-of-acrv/fcos
• Development: https://github.com/best-of-acrv/fcos
• Documentation: https://github.com/best-of-acrv/fcos
• 145379 total downloads
• Last upload: 27 days and 8 hours ago

Description

Fully convolutional one-stage object detection (FCOS) is a framework for per-pixel prediction of objects in images. FCOS doesn't rely on expensive anchor box calculations and their hyper-parameters, which is in contrast to state-of-the-art object detectors like RetinaNet, YOLOv3, and Faster R-CNN. It includes a Python API, & scripts for command line usage.