This code is for action recognition using the two stream networks (rgb and optical flow). Each stream is constructed by CNN and LSTM. I implemented this code for practice because I have not written any deep learning code from scratch!
- Linux (I used Ubuntu 14.04)
- GPU (I used GTX TitanX x2)
- Keras + TensorFlow (I recommend to install Keras via docker)
Download UCF-101 dataset, and set to arbitary directory.
Use scripts/extract_optical_flow.sh in TSN (ECCV2016).
Use scripts/build_file_list.sh in TSN (ECCV2016).
You can train a model and test it.
bash run.sh
- Modify to accept the various length input sequences (Fixed number of frames are extracted from a sequence now)