LSTM ball trajectory prediction. Original idea from Applying Deep Learning to Basketball Trajectories
More detail in the jupyter notebook.
-
Install tensorflow for running the python interface.
-
Following tensorflow-cmake to build tensorflow shared library, for running the c++ interface.
-
Train, or download our model.
| Training data | Models |
|---|---|
| coords.csv | export-graph_125.pb |
| coords_30.csv | export-graph_30.pb |
- Build the C++ interface (Optional).
cd src
mkdir build && cd build
cmake ..
makeYou have to modify some path in the CMakeList.txt file in order to build.
Train the model:
python main.pyConvert to .pb format:
python write_pb.pyTest the model:
python test_on_pb.py #or use the jupyter notebookInput data
Trajectory prediction with 30 input data points
Trajectory prediction with only 4 input data points
