Pytorch implementation of MaskFlownet

Last update: Nov 02, 2022

Overview

MaskFlownet-Pytorch

Unofficial PyTorch implementation of MaskFlownet (https://github.com/microsoft/MaskFlownet).

Tested with:

PyTorch 1.5.0
CUDA 10.1

Install

The correlation package must be installed first:

cd model/correlation_package
python setup.py install

Inference

Right now, I implemented the inference script for KITTI 2012/2015, MPI Sintel and FlyingChairs.

python predict.py CONFIG -c CHECKPOINT --dataset_cfg DATASET -f ROOT_FOLDER [-b BATCH_SIZE]

For example:

python predict.py MaskFlownet.yaml -c 5adNov03-0005_1000000.pth --dataset_cfg sintel.yaml -f ./SINTEL -b 4
python predict.py MaskFlownet.yaml -c 8caNov12-1532_300000.pth --dataset_cfg kitti.yaml -f ./KITTI -b 4
python predict.py MaskFlownet_S.yaml -c 771Sep25-0735_500000.pth --dataset_cfg chairs.yaml -f ./FLYINGCHAIRS -b 4
python predict.py MaskFlownet_S.yaml -c dbbSep30-1206_1000000.pth --dataset_cfg sintel.yaml -f ./SINTEL -b 4

Differences with the original implementation

The results are slightly different from the original implementation:

Checkpoint	Network	Implementation	KITTI2012	KITTI2015	Sintel Clean	Sintel Final	FlyingChairs
771Sep25	MaskFlownet_S	Original AEPE: PyTorch AEPE:	4.12 4.18	11.52 11.82	3.38 3.38	4.71 4.70	1.84 1.83
dbbSep30	MaskFlownet_S	Original AEPE: PyTorch AEPE:	1.27 1.28	1.92 1.93	2.76 2.78	3.29 3.32	2.36 2.36
5adNov03	MaskFlownet	Original AEPE: PyTorch AEPE:	1.16 1.18	1.66 1.68	2.58 2.59	3.14 3.17	2.23 2.23
8caNov12	MaskFlownet	Original AEPE: PyTorch AEPE:	0.82 0.82	1.38 1.38	4.34 4.40	5.27 5.33	4.01 3.99

Examples

KITTI Original implementation:

KITTI This implementation:

Sintel Original implementation:

Sintel This implementation:

FlyingChairs Original implementation:

FlyingChairs This implementation:

Notes

If you use my implementation for training, it might happen that you encounter this error:

CUDA error: an illegal memory access was encountered

This is due to a bug in the torchvision implementation of deformable convolutions. (still present in version 0.7.0)

To solve it, you need to use the nightly version of torchvision.

Acknowledgment

Original MXNet implementation: here

correlation_package was taken from flownet2

Pytorch implementation of MaskFlownet

Related tags

Overview

MaskFlownet-Pytorch

Install

Inference

Differences with the original implementation

Examples

Notes

Acknowledgment

Owner

Daniele Cattaneo

Code for "My(o) Armband Leaks Passwords: An EMG and IMU Based Keylogging Side-Channel Attack" paper

VSR-Transformer - This paper proposes a new Transformer for video super-resolution (called VSR-Transformer).

Deep Text Search is an AI-powered multilingual text search and recommendation engine with state-of-the-art transformer-based multilingual text embedding (50+ languages).

Pca-on-genotypes - Mini bioinformatics project - PCA on genotypes

Implementation of Shape and Electrostatic similarity metric in deepFMPO.

Training neural models with structured signals.

Implementation of momentum^2 teacher

Stochastic gradient descent with model building

PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM

Generate image analogies using neural matching and blending

PyTorch implementation of U-TAE and PaPs for satellite image time series panoptic segmentation.

Interactive Image Segmentation via Backpropagating Refinement Scheme

Volsdf - Volume Rendering of Neural Implicit Surfaces

Official code of "Mitigating the Mutual Error Amplification for Semi-Supervised Object Detection"

Simulation of moving particles under microscopic imaging

Social Fabric: Tubelet Compositions for Video Relation Detection

Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch

Predicting path with preference based on user demonstration using Maximum Entropy Deep Inverse Reinforcement Learning in a continuous environment

First-Order Probabilistic Programming Language

Writeups for the challenges from DownUnderCTF 2021