Open bewithme opened 3 years ago
No. I just pick the window_size based on my experience --- I picked 0.5s because I think as a human I can recognize other people's action from a 0.5s video.
It's not related to LSTM at all. This project doesn't use LSTM
can you explain more detail about features preprocessing algorithm in s3_preprocess_features.py ? such as what is window_size, is it the same as time steps in LSTM?