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