Reproducing Learning-based Video Motion Magnification in pytorch
We write the code with reference to the original tensorflow implementation from the authors
This code is tested on python 3.5 and pytorch 0.4.1.
We use the dataset opened by the authors. Please refer to the authors repository.
python train.py [--additional option]
ex) to run training on gpu number 0
python train.py --gpu 0
- https://github.com/12dmodel/deep_motion_mag
- Oh, Tae-Hyun, et al. "Learning-based Video Motion Magnification." arXiv preprint arXiv:1804.02684 (2018).