Skip to content
This repository has been archived by the owner on Dec 15, 2021. It is now read-only.

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

License

Notifications You must be signed in to change notification settings

Lyears/maskrcnn-benchmark

 
 

Repository files navigation

MaskRCNN Benchmark for Skyeye dataset

This project is fork from maskrcnn-benchmark, the steps of installation, training and test are shown in Original README.md.

Skyeye dataset

The annotation of skyeye dataset.

[
{"id": -1, "name": "ignore", "count": 434}, 
{"id": 1, "name": "mask_person_top", "count": 129}, 
{"id": 2, "name": "mask_plastic_3_pallet_top", "count": 18}, 
{"id": 3, "name": "mask_goods_pallet_top", "count": 1525}
]

Modification for skyeye dataset

The modification for skyeye dataset is located at mobilenet backbone, RPN and ROI.

Main Result

The specific results can be seem from the directory whose prefix is skyeye.

About

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Resources

License

Code of conduct

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 77.7%
  • Cuda 17.5%
  • C++ 4.2%
  • Dockerfile 0.6%