Skip to content

Implementation of Optical Flow predictions throught deep learning using LightFlow architecture proposed in https://arxiv.org/pdf/1804.05830.pdf

Notifications You must be signed in to change notification settings

stanlee321/LightFlow-TensorFlow

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

89 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LightFlow Tensorflow/Keras implementation

Implementation of Optical Flow predictions using deep learning LightFlow architecture proposed in Towards High Performance Video Object Detection for Mobiles

The main training procedure is based on https://github.com/sampepose/flownet2-tf , and the network was builded using Keras.

Tensorbaord logs

lightflow tensorboard Loss lightflow tensorboard Val image

Actual input/output

inputs inputs

lightflow Actual output

TODOs

  • Fix error with the BatchNorm layer in Keras, model does not converge.
  • Migrate Keras model definition to TensorFlow
  • Work in progress

Reference article, thanks

About

Implementation of Optical Flow predictions throught deep learning using LightFlow architecture proposed in https://arxiv.org/pdf/1804.05830.pdf

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published