Mask R-CNN Benchmark is a PyTorch-based framework that provides high-performance implementations of object detection, instance segmentation, and keypoint detection models. Originally built to benchmark Mask R-CNN and related models, it offers a clean, modular design to train and evaluate detection systems efficiently on standard datasets like COCO. The framework integrates critical components—region proposal networks (RPNs), RoIAlign layers, mask heads, and backbone architectures such as ResNet and FPN—optimized for both accuracy and speed. It supports multi-GPU distributed training, mixed precision, and custom data loaders for new datasets. Built as a reference implementation, it became a foundation for the next-generation Detectron2, yet remains widely used for research needing a stable, reproducible environment. Visualization tools, model zoo checkpoints, and benchmark scripts make it easy to replicate state-of-the-art results or fine-tune models for custom tasks.
Features
- High-performance implementations of Mask R-CNN, Faster R-CNN, and keypoint models
- Modular components for RPNs, RoIAlign, mask heads, and backbones
- Multi-GPU distributed training and mixed precision support
- Dataset support and loaders for COCO, Pascal VOC, and custom datasets
- Visualization and evaluation tools for detection and segmentation results
- Reproducible reference implementation for benchmarking and fine-tuning