hmorimitsu/ptlflow

PyTorch Lightning Optical Flow models, scripts, and pretrained weights.

What it solves

It provides a unified framework for estimating optical flow, allowing users to train and test multiple state-of-the-art deep learning models within a single, consistent environment rather than using fragmented original implementations.

How it works

Built on PyTorch Lightning, the project integrates a vast collection of optical flow models (such as RAFT, FlowFormer, and NeuFlow) and supports various datasets (including Middlebury, Spring, and TartanAir). It includes tools for inference, model benchmarking, and training, with support for FP16 precision and YAML configuration files.

Who it’s for

Computer vision researchers and developers working on motion estimation and optical flow who need a standardized way to compare, train, or deploy different model architectures.

Highlights

  • A comprehensive library of integrated state-of-the-art optical flow models.
  • Unified training and testing pipelines using PyTorch Lightning.
  • Support for multiple industry-standard datasets.
  • Tools for benchmarking model performance and accuracy.
  • Support for FP16 precision and YAML-based configuration.

Related

  • Project
    Lightning-AI/pytorch-lightning

    A deep learning framework that abstracts away the engineering boilerplate of PyTorch, enabling researchers to pretrain and finetune AI models at scale across various hardware.

  • Project
    sktime/pytorch-forecasting

    A PyTorch-based library for time series forecasting that provides a high-level API and state-of-the-art deep learning architectures like Temporal Fusion Transformers and N-BEATS.

  • Project
    microsoft/onnxruntime

    A cross-platform machine learning accelerator that optimizes inference and training for models from various frameworks like PyTorch and TensorFlow.

  • Project
    pytorch-tabular/pytorch_tabular

    A high-level PyTorch framework that provides a unified interface for applying various deep learning architectures to tabular data.

  • Project
    torch-uncertainty/torch-uncertainty

    A deep learning framework for uncertainty quantification that provides tools to make neural networks more reliable through uncertainty-aware training, evaluation, and post-processing.