We appreciate all contributions improving MMFlow. Results and models are available in the model zoo. Refer to the below tutorials to dive deeper: If you’re familiar with it, check out getting_started to try out MMFlow. If you're new of optical flow, you can start with learn the basics. Guidance in dataset_prepare for dataset preparation. Please refer to install.md for installation and Please refer to changelog.md for details and release history. FlowNet, PWC-Net, RAFT, etc,Īnd representative datasets, FlyingChairs, FlyingThings3D, Sintel, KITTI, etc. The toolbox directly supports popular and contemporary optical flow models, e.g. Plenty of Algorithms and Datasets Out of the Box Which makes it much easy and flexible to build a new model by combining different modules. We decompose the flow estimation framework into different components, MMFlow is the first toolbox that provides a framework for unified implementation and evaluation of optical flow algorithms. The First Unified Framework for Optical Flow The master branch works with PyTorch 1.5+. MMFlow is an open source optical flow toolbox based on PyTorch.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |