search

felixchenfy / Realtime-Action-Recognition

Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)
MIT License
875 stars 256 forks source link

can you explain more detail about features preprocessing algorithm #72

Open bewithme opened 3 years ago

bewithme commented 3 years ago

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?

felixchenfy commented 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