NVIDIA/flownet2-pytorch
A PyTorch implementation of FlowNet 2.0, a deep learning model for optical flow estimation in video sequences.
Not currently ranked — collecting fresh signals.
star history
This repository provides a complete PyTorch implementation of FlowNet 2.0, a convolutional neural network architecture for estimating optical flow between consecutive video frames. It includes multiple network variants (FlowNet2S, FlowNet2C, FlowNet2CS, FlowNet2CSS, FlowNet2SD), custom CUDA layers for correlation and resampling operations, multi-GPU training support, and fp16 inference capabilities. The codebase provides dataloaders for standard optical flow datasets (FlyingChairs, FlyingThings, MPI-Sintel) and multi-scale loss functions for training.
Frequently asked
- What is NVIDIA/flownet2-pytorch?
- A PyTorch implementation of FlowNet 2.0, a deep learning model for optical flow estimation in video sequences.
- Is flownet2-pytorch open source?
- Yes — NVIDIA/flownet2-pytorch is an open-source project tracked on heatdrop.
- What language is flownet2-pytorch written in?
- NVIDIA/flownet2-pytorch is primarily written in Python.
- How popular is flownet2-pytorch?
- NVIDIA/flownet2-pytorch has 3.3k stars on GitHub.
- Where can I find flownet2-pytorch?
- NVIDIA/flownet2-pytorch is on GitHub at https://github.com/NVIDIA/flownet2-pytorch.