Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

flownet2-pytorch

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks.
FlowNet2 Caffe implementation : flownet2

Multiple GPU training is supported, and the code provides examples for training or inference on MPI-Sintel clean and final datasets. The same commands can be used for training or inference with other datasets. See below for more detail.

Inference using fp16 (half-precision) is also supported.

For more help, type

python main.py --help

Network architectures

Below are the different flownet neural network architectures that are provided.
A batchnorm version for each network is available.

• FlowNet2S
• FlowNet2C
• FlowNet2CS
• FlowNet2CSS
• FlowNet2SD
• FlowNet2

Custom layers

FlowNet2 or FlowNet2C* achitectures rely on custom layers Resample2d or Correlation.
A pytorch implementation of these layers with cuda kernels are available at ./networks.
Note : Currently, half precision kernels are not available for these layers.

Data Loaders

Dataloaders for FlyingChairs, FlyingThings, ChairsSDHom and ImagesFromFolder are available in datasets.py.

Loss Functions

L1 and L2 losses with multi-scale support are available in losses.py.

Installation

# get flownet2-pytorch sourcegit clone https://github.com/NVIDIA/flownet2-pytorch.gitcd flownet2-pytorch# install custom layersbash install.sh

Docker image

Libraries and other dependencies for this project include: Ubuntu 16.04, Python 2.7, Pytorch 0.2, CUDNN 6.0, CUDA 8.0

A Dockerfile with the above dependencies is available

# Build and launch docker imagebash launch_docker.sh

Inference

# Example on MPISintel Clean   python main.py --inference --model FlowNet2 --save_flow --inference_dataset MpiSintelClean \--inference_dataset_root /path/to/mpi-sintel/clean/dataset \--resume /path/to/checkpoints

Training and validation

# Example on MPISintel Final and Clean, with L1Loss on FlowNet2 modelpython main.py --batch_size 8 --model FlowNet2 --loss=L1Loss --optimizer=Adam --optimizer_lr=1e-4 \--training_dataset MpiSintelFinal --training_dataset_root /path/to/mpi-sintel/final/dataset  \--validation_dataset MpiSintelClean --validation_dataset_root /path/to/mpi-sintel/clean/dataset# Example on MPISintel Final and Clean, with MultiScale loss on FlowNet2C modelpython main.py --batch_size 8 --model FlowNet2C --optimizer=Adam --optimizer_lr=1e-4 \--loss=MultiScale --loss_norm=L1 loss_numScales=5 loss_startScale=4 \--training_dataset MpiSintelFinal --training_dataset_root /path/to/mpi-sintel/final/dataset  \--validation_dataset MpiSintelClean --validation_dataset_root /path/to/mpi-sintel/clean/dataset

Results on MPI-Sintel

Acknowledgments

The Flownet-S model in this project was derived from ClementPinard/FlowNetPytorch.

To restore the repository download the bundle

wget https://archive.org/download/github.com-NVIDIA-flownet2-pytorch_-_2017-12-06_07-12-41/NVIDIA-flownet2-pytorch_-_2017-12-06_07-12-41.bundle

and run:

 git clone NVIDIA-flownet2-pytorch_-_2017-12-06_07-12-41.bundle 

Source: https://github.com/NVIDIA/flownet2-pytorch
Uploader: NVIDIA
Upload date: 2017-12-06

plus-circle Add Review

comment

Reviews