2026-10-15T12:40:29Z https://data.mendeley.com/oai

oai:data.mendeley.com/jtv3f9pbdb.2 2021-09-06T13:11:55Z

S. Tabrizi, Sahar LSTM and CNN Parameter Tuning results Mendeley Data The published data are part of the virtual-coach Table Tennis shadow-play training system developing results. Two deep models (LSTM and 2DCNN) were trained and tested based on the self-collected Table Tennis Forehand strokes sensory data The Models' parameters are tuned with the following values: 1) The Epoch number in range (100, 250, and 500), 2) The batch size in range (10, 50,100, 500 and1000), 3) The number of the LSTM and CNN layer in range (1, 2, and 3), 4) The number of filters in range (16 to 256), 5) The rate of dropout in range (0.1, 0.2, 0.3, ..., 0.9), 6) The number of the denes layer in range (1, 2, and 3), and 7) The number of the neurons in the dense layer is in the range (8 to 64) The published results contain all possible models' performance on the testing dataset. Machine Learning Pashazadeh, Saeid Dataset doi:10.17632/jtv3f9pbdb.2 oai:data.mendeley.com/jtv3f9pbdb.2 Creative Commons Attribution 4.0 International http://creativecommons.org/licenses/by/4.0 https://data.mendeley.com/datasets/jtv3f9pbdb 2021-09-06T13:11:55Z