deepOF

TensorFlow implementation for "Guided Optical Flow Learning". You can refer to paper for more details at Openreview or Arxiv.

The code is ready to run, but the accuracy is a little lower than both Caffe and Pytorch implementation.

Proceed if you really want to use TensorFlow.

Name		Name	Last commit message	Last commit date
Latest commit History 33 Commits
.idea		.idea
version1		version1
FlyingChairs_train_val.txt		FlyingChairs_train_val.txt
README.md		README.md
Sintel_train_val.txt		Sintel_train_val.txt
analyze_test_loss.py		analyze_test_loss.py
check_loss.py		check_loss.py
deepOF.py		deepOF.py
deepOF_fc.py		deepOF_fc.py
flyingChairsLoader.py		flyingChairsLoader.py
flyingChairsTrain.py		flyingChairsTrain.py
flyingChairsTrain_vgg.py		flyingChairsTrain_vgg.py
flyingChairsUtils.py		flyingChairsUtils.py
flyingChairsWrapFlow.py		flyingChairsWrapFlow.py
flyingChairsWrapFlow_vgg.py		flyingChairsWrapFlow_vgg.py
sintelLoader.py		sintelLoader.py
sintelLoader.pyc		sintelLoader.pyc
sintelTrain.py		sintelTrain.py
sintelWrapFlow.py		sintelWrapFlow.py
ucf101Loader.py		ucf101Loader.py
ucf101train.py		ucf101train.py
ucf101wrapFlow.py		ucf101wrapFlow.py
utils.py		utils.py

yanizhang101/deepOF